Vu Anh Claude commited on
Commit
0b1c1cf
·
1 Parent(s): e423877

Update technical report and README with latest SVC model results

Browse files

- Updated technical report abstract and results with SVC accuracy: 71.72%
- Added SVC algorithm details in classification model section
- Updated README performance metrics with latest SVC results
- Updated model filename references to latest exported model
- Training accuracy: 94.31%, Test accuracy: 71.72%, Training time: 7.71s

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

README.md CHANGED
@@ -33,7 +33,7 @@ model-index:
33
  type: undertheseanlp/UTS2017_Bank
34
  metrics:
35
  - type: accuracy
36
- value: 0.7247
37
  name: Test Accuracy (SVC)
38
  - type: accuracy
39
  value: 0.6818
@@ -57,7 +57,7 @@ pipeline_tag: text-classification
57
 
58
  # Pulse Core 1 - Vietnamese Banking Aspect Sentiment Analysis
59
 
60
- A machine learning-based aspect sentiment analysis model designed for Vietnamese banking text processing. Built on TF-IDF feature extraction pipeline combined with various machine learning algorithms, achieving **68.18% accuracy** on UTS2017_Bank aspect sentiment dataset with Logistic Regression.
61
 
62
  📋 **[View Detailed System Card](https://huggingface.co/undertheseanlp/pulse_core_1/blob/main/paper/pulse_core_1_technical_report.tex)** for comprehensive model documentation, performance analysis, and limitations.
63
 
@@ -156,18 +156,19 @@ comparison_results = train_notebook(
156
  ## Performance Metrics
157
 
158
  ### UTS2017_Bank Aspect Sentiment Analysis Performance
159
- - **Training Accuracy**: 73.62%
160
- - **Test Accuracy**: 68.18%
161
  - **Training Samples**: 1,581
162
  - **Test Samples**: 396
163
  - **Number of Classes**: 35 aspect-sentiment combinations
164
- - **Training Time**: ~2.13 seconds
165
  - **Best Performing Classes**:
 
166
  - `CUSTOMER_SUPPORT#positive`: 88% F1-score
167
- - `TRADEMARK#positive`: 86% F1-score
168
- - `CUSTOMER_SUPPORT#negative`: 62% F1-score
169
  - **Challenges**: Class imbalance affects minority aspect-sentiment combinations
170
- - **Model Type**: Logistic Regression with TF-IDF (20k features, 1-2 ngrams)
171
 
172
  ## Using the Pre-trained Models
173
 
@@ -177,7 +178,7 @@ comparison_results = train_notebook(
177
  import joblib
178
 
179
  # Load local exported model
180
- sentiment_model = joblib.load("uts2017_sentiment_20250928_122636.joblib")
181
 
182
  # Or use inference script directly
183
  from inference import predict_text
 
33
  type: undertheseanlp/UTS2017_Bank
34
  metrics:
35
  - type: accuracy
36
+ value: 0.7172
37
  name: Test Accuracy (SVC)
38
  - type: accuracy
39
  value: 0.6818
 
57
 
58
  # Pulse Core 1 - Vietnamese Banking Aspect Sentiment Analysis
59
 
60
+ A machine learning-based aspect sentiment analysis model designed for Vietnamese banking text processing. Built on TF-IDF feature extraction pipeline combined with various machine learning algorithms, achieving **71.72% accuracy** on UTS2017_Bank aspect sentiment dataset with Support Vector Classification (SVC).
61
 
62
  📋 **[View Detailed System Card](https://huggingface.co/undertheseanlp/pulse_core_1/blob/main/paper/pulse_core_1_technical_report.tex)** for comprehensive model documentation, performance analysis, and limitations.
63
 
 
156
  ## Performance Metrics
157
 
158
  ### UTS2017_Bank Aspect Sentiment Analysis Performance
159
+ - **Training Accuracy**: 94.31%
160
+ - **Test Accuracy**: 71.72%
161
  - **Training Samples**: 1,581
162
  - **Test Samples**: 396
163
  - **Number of Classes**: 35 aspect-sentiment combinations
164
+ - **Training Time**: ~7.71 seconds
165
  - **Best Performing Classes**:
166
+ - `TRADEMARK#positive`: 90% F1-score
167
  - `CUSTOMER_SUPPORT#positive`: 88% F1-score
168
+ - `LOAN#negative`: 67% F1-score
169
+ - `CUSTOMER_SUPPORT#negative`: 65% F1-score
170
  - **Challenges**: Class imbalance affects minority aspect-sentiment combinations
171
+ - **Model Type**: Support Vector Classification (SVC) with TF-IDF (20k features, 1-2 ngrams)
172
 
173
  ## Using the Pre-trained Models
174
 
 
178
  import joblib
179
 
180
  # Load local exported model
181
+ sentiment_model = joblib.load("uts2017_sentiment_20250928_131716.joblib")
182
 
183
  # Or use inference script directly
184
  from inference import predict_text
analyze_results.py ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ """
3
+ Script to analyze and compare training results from multiple model runs.
4
+ """
5
+
6
+ import json
7
+ import os
8
+ from pathlib import Path
9
+
10
+ def load_metadata(run_dir):
11
+ """Load metadata from a training run directory"""
12
+ metadata_path = os.path.join(run_dir, "metadata.json")
13
+ if os.path.exists(metadata_path):
14
+ with open(metadata_path, 'r', encoding='utf-8') as f:
15
+ return json.load(f)
16
+ return None
17
+
18
+ def analyze_all_runs():
19
+ """Analyze all training runs and create comparison"""
20
+ runs_dir = Path("runs")
21
+ results = []
22
+
23
+ # Find all metadata files
24
+ for run_dir in runs_dir.glob("*/"):
25
+ if run_dir.is_dir():
26
+ metadata = load_metadata(run_dir)
27
+ if metadata:
28
+ results.append({
29
+ 'run_id': run_dir.name,
30
+ 'model': metadata.get('classifier', 'Unknown'),
31
+ 'dataset': 'VNTC' if 'VNTC' in metadata.get('config_name', '') else 'UTS2017_Bank',
32
+ 'max_features': metadata.get('max_features', 0),
33
+ 'ngram_range': metadata.get('ngram_range', [1,1]),
34
+ 'train_accuracy': metadata.get('train_accuracy', 0),
35
+ 'test_accuracy': metadata.get('test_accuracy', 0),
36
+ 'train_time': metadata.get('train_time', 0),
37
+ 'prediction_time': metadata.get('prediction_time', 0),
38
+ 'train_samples': metadata.get('train_samples', 0),
39
+ 'test_samples': metadata.get('test_samples', 0)
40
+ })
41
+
42
+ return results
43
+
44
+ def print_comparison_table(results):
45
+ """Print formatted comparison table"""
46
+ print("\n" + "="*120)
47
+ print("VIETNAMESE TEXT CLASSIFICATION - MODEL COMPARISON RESULTS")
48
+ print("="*120)
49
+
50
+ # Filter for VNTC results (news classification)
51
+ vntc_results = [r for r in results if r['dataset'] == 'VNTC']
52
+
53
+ if vntc_results:
54
+ print("\nVNTC Dataset (Vietnamese News Classification):")
55
+ print("-"*120)
56
+ print(f"{'Model':<20} {'Features':<10} {'N-gram':<10} {'Train Acc':<12} {'Test Acc':<12} {'Train Time':<12} {'Pred Time':<12}")
57
+ print("-"*120)
58
+
59
+ # Sort by test accuracy
60
+ vntc_results.sort(key=lambda x: x['test_accuracy'], reverse=True)
61
+
62
+ for result in vntc_results:
63
+ model = result['model'][:18]
64
+ features = f"{result['max_features']//1000}k" if result['max_features'] > 0 else "N/A"
65
+ ngram = f"{result['ngram_range'][0]}-{result['ngram_range'][1]}"
66
+ train_acc = f"{result['train_accuracy']:.4f}"
67
+ test_acc = f"{result['test_accuracy']:.4f}"
68
+ train_time = f"{result['train_time']:.1f}s"
69
+ pred_time = f"{result['prediction_time']:.1f}s"
70
+
71
+ print(f"{model:<20} {features:<10} {ngram:<10} {train_acc:<12} {test_acc:<12} {train_time:<12} {pred_time:<12}")
72
+
73
+ # Filter for UTS2017_Bank results
74
+ bank_results = [r for r in results if r['dataset'] == 'UTS2017_Bank']
75
+
76
+ if bank_results:
77
+ print("\nUTS2017_Bank Dataset (Vietnamese Banking Text Classification):")
78
+ print("-"*120)
79
+ print(f"{'Model':<20} {'Features':<10} {'N-gram':<10} {'Train Acc':<12} {'Test Acc':<12} {'Train Time':<12} {'Pred Time':<12}")
80
+ print("-"*120)
81
+
82
+ # Sort by test accuracy
83
+ bank_results.sort(key=lambda x: x['test_accuracy'], reverse=True)
84
+
85
+ for result in bank_results:
86
+ model = result['model'][:18]
87
+ features = f"{result['max_features']//1000}k" if result['max_features'] > 0 else "N/A"
88
+ ngram = f"{result['ngram_range'][0]}-{result['ngram_range'][1]}"
89
+ train_acc = f"{result['train_accuracy']:.4f}"
90
+ test_acc = f"{result['test_accuracy']:.4f}"
91
+ train_time = f"{result['train_time']:.1f}s"
92
+ pred_time = f"{result['prediction_time']:.1f}s"
93
+
94
+ print(f"{model:<20} {features:<10} {ngram:<10} {train_acc:<12} {test_acc:<12} {train_time:<12} {pred_time:<12}")
95
+
96
+ print("="*120)
97
+
98
+ if vntc_results:
99
+ best_vntc = max(vntc_results, key=lambda x: x['test_accuracy'])
100
+ print(f"\nBest VNTC model: {best_vntc['model']} with {best_vntc['test_accuracy']:.4f} test accuracy")
101
+
102
+ if bank_results:
103
+ best_bank = max(bank_results, key=lambda x: x['test_accuracy'])
104
+ print(f"Best UTS2017_Bank model: {best_bank['model']} with {best_bank['test_accuracy']:.4f} test accuracy")
105
+
106
+ def main():
107
+ """Main analysis function"""
108
+ print("Analyzing Vietnamese Text Classification Training Results...")
109
+
110
+ results = analyze_all_runs()
111
+
112
+ if not results:
113
+ print("No training results found in runs/ directory.")
114
+ return
115
+
116
+ print(f"Found {len(results)} training runs.")
117
+ print_comparison_table(results)
118
+
119
+ # Create summary statistics
120
+ vntc_results = [r for r in results if r['dataset'] == 'VNTC']
121
+ bank_results = [r for r in results if r['dataset'] == 'UTS2017_Bank']
122
+
123
+ print("\nSummary:")
124
+ print(f"- VNTC runs: {len(vntc_results)}")
125
+ print(f"- UTS2017_Bank runs: {len(bank_results)}")
126
+
127
+ if vntc_results:
128
+ avg_vntc_acc = sum(r['test_accuracy'] for r in vntc_results) / len(vntc_results)
129
+ print(f"- Average VNTC test accuracy: {avg_vntc_acc:.4f}")
130
+
131
+ if bank_results:
132
+ avg_bank_acc = sum(r['test_accuracy'] for r in bank_results) / len(bank_results)
133
+ print(f"- Average UTS2017_Bank test accuracy: {avg_bank_acc:.4f}")
134
+
135
+ if __name__ == "__main__":
136
+ main()
inference.py CHANGED
@@ -23,11 +23,19 @@ def find_local_models():
23
  if filename.startswith('uts2017_sentiment_'):
24
  models['exported']['uts2017_sentiment'] = filename
25
 
26
- # Find models in runs directory
27
  sentiment_runs = glob.glob('runs/*/models/UTS2017_Bank_AspectSentiment_*.joblib')
28
 
29
  if sentiment_runs:
30
- models['runs']['uts2017_sentiment'] = sorted(sentiment_runs)[-1] # Most recent
 
 
 
 
 
 
 
 
31
 
32
  return models
33
 
@@ -188,8 +196,8 @@ def main():
188
  "--source",
189
  type=str,
190
  choices=["exported", "runs"],
191
- default="exported",
192
- help="Model source: exported files or runs directory (default: exported)"
193
  )
194
 
195
  args = parser.parse_args()
 
23
  if filename.startswith('uts2017_sentiment_'):
24
  models['exported']['uts2017_sentiment'] = filename
25
 
26
+ # Find models in runs directory - prioritize SVC models
27
  sentiment_runs = glob.glob('runs/*/models/UTS2017_Bank_AspectSentiment_*.joblib')
28
 
29
  if sentiment_runs:
30
+ # Sort by modification time (most recent first)
31
+ sentiment_runs.sort(key=lambda x: os.path.getmtime(x), reverse=True)
32
+
33
+ # Prefer SVC models over other types
34
+ svc_models = [m for m in sentiment_runs if 'SVC' in m]
35
+ if svc_models:
36
+ models['runs']['uts2017_sentiment'] = svc_models[0] # Most recent SVC
37
+ else:
38
+ models['runs']['uts2017_sentiment'] = sentiment_runs[0] # Most recent any model
39
 
40
  return models
41
 
 
196
  "--source",
197
  type=str,
198
  choices=["exported", "runs"],
199
+ default="runs",
200
+ help="Model source: exported files or runs directory (default: runs)"
201
  )
202
 
203
  args = parser.parse_args()
paper/pulse_core_1_technical_report.tex CHANGED
@@ -23,7 +23,7 @@
23
  \maketitle
24
 
25
  \begin{abstract}
26
- This paper presents Pulse Core 1, a Vietnamese banking aspect sentiment analysis system employing Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction combined with machine learning classification algorithms. The system is evaluated on the UTS2017\_Bank aspect sentiment dataset containing 35 combined aspect-sentiment categories, achieving 68.18\% accuracy with Logistic Regression and 72.47\% accuracy with Support Vector Classification (SVC). The implementation utilizes a 20,000-dimensional TF-IDF feature space with n-gram analysis and incorporates hash-based caching for computational optimization. The model predicts combined aspect-sentiment labels in the format \texttt{<aspect>\#<sentiment>}, enabling fine-grained analysis of Vietnamese banking customer feedback across 14 banking aspects (ACCOUNT, CARD, CUSTOMER\_SUPPORT, etc.) and 3 sentiment polarities (positive, negative, neutral). These results establish baseline performance metrics for Vietnamese banking aspect sentiment analysis and demonstrate the efficacy of traditional machine learning approaches for Vietnamese financial domain natural language processing tasks.
27
  \end{abstract}
28
 
29
  \section{Introduction}
@@ -92,12 +92,20 @@ The system employs Term Frequency-Inverse Document Frequency (TF-IDF) vectorizat
92
 
93
  \subsubsection{Classification Model}
94
 
95
- The system implements logistic regression as the primary classification algorithm with the following hyperparameter configuration:
96
 
 
97
  \begin{itemize}
98
  \item \textbf{Optimization Algorithm}: Limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) quasi-Newton method for efficient convergence
99
  \item \textbf{Regularization}: L2 (Ridge) penalty with automatic parameter tuning to prevent overfitting
100
  \item \textbf{Convergence Criteria}: Maximum 1,000 iterations with tolerance-based early stopping
 
 
 
 
 
 
 
101
  \item \textbf{Multi-class Extension}: One-vs-Rest strategy for handling multi-label classification tasks
102
  \end{itemize}
103
 
@@ -168,7 +176,7 @@ This work establishes the first comprehensive baseline for Vietnamese banking as
168
  \hline
169
  \textbf{Dataset} & \textbf{Method} & \textbf{Accuracy} \\
170
  \hline
171
- UTS2017\_Bank (35 aspect-sentiment) & \textbf{Pulse Core 1 - SVC with TF-IDF} & \textbf{72.47\%} \\
172
  UTS2017\_Bank (35 aspect-sentiment) & \textbf{Pulse Core 1 - Logistic Regression with TF-IDF} & \textbf{68.18\%} \\
173
  \hline
174
  \end{tabular}
@@ -187,7 +195,7 @@ This section presents comprehensive experimental results across both Vietnamese
187
  \textbf{UTS2017\_Bank Dataset (Banking Aspect Sentiment Analysis):}
188
  The system exhibits competitive performance on the banking aspect sentiment analysis task:
189
  \begin{itemize}
190
- \item \textbf{Test Classification Accuracy (SVC)}: 72.47\%
191
  \item \textbf{Test Classification Accuracy (Logistic Regression)}: 68.18\%
192
  \item \textbf{Training Latency (SVC)}: 5.3 seconds
193
  \item \textbf{Training Latency (Logistic Regression)}: 2.13 seconds
@@ -224,14 +232,14 @@ This section presents a detailed comparison of per-class performance between Sup
224
 
225
  \textbf{Model Performance Summary:}
226
  \begin{itemize}
227
- \item \textbf{SVC Model}: 72.47\% overall accuracy with 20k features and 1-2 n-gram range
228
  \item \textbf{Logistic Regression Model}: 70.96\% overall accuracy with 20k features and 1-2 n-gram range
229
  \item \textbf{Performance Gain}: SVC achieves a 1.51 percentage point improvement over Logistic Regression
230
  \end{itemize}
231
 
232
  \textbf{UTS2017\_Bank Dataset Comparative Per-Class Results:}
233
 
234
- The following table presents a side-by-side comparison of per-class performance metrics for both SVC (72.47\% accuracy) and Logistic Regression (70.96\% accuracy) models:
235
 
236
  \begin{longtable}{lcccccccc}
237
  \toprule
@@ -345,7 +353,7 @@ Analysis of the banking aspect sentiment task reveals important insights about V
345
  The experimental results establish that systematically optimized traditional machine learning methodologies maintain competitive performance for Vietnamese banking aspect sentiment analysis tasks, providing an efficient baseline for financial domain applications. These findings yield several significant research implications:
346
 
347
  \begin{itemize}
348
- \item \textbf{Computational Resource Efficiency}: The proposed approach exhibits substantially reduced computational complexity compared to transformer-based alternatives while achieving 72.47\% accuracy on complex aspect sentiment analysis tasks.
349
  \item \textbf{Model Interpretability}: TF-IDF feature representations provide transparent attribution mechanisms for banking aspect sentiment decisions, essential for financial applications requiring algorithmic accountability.
350
  \item \textbf{Production Deployment Viability}: The system's constrained computational requirements (2.13s training time) facilitate deployment in banking environments with limited computational resources.
351
  \end{itemize}
@@ -416,7 +424,7 @@ The current investigation establishes several promising research trajectories fo
416
  This paper presents Pulse Core 1, a Vietnamese banking aspect sentiment analysis system that establishes the viability of systematically optimized traditional machine learning methodologies for financial domain applications. The investigation yields several significant findings:
417
 
418
  \begin{enumerate}
419
- \item Traditional machine learning approaches achieve competitive performance on Vietnamese banking aspect sentiment analysis tasks (72.47\% accuracy with SVC) while maintaining substantial computational efficiency advantages (5.3s training time).
420
  \item Feature engineering methodologies retain critical importance for Vietnamese banking applications, with the implemented 20,000-dimensional TF-IDF representation effectively capturing aspect-sentiment relationships across 35 combined categories.
421
  \item Class distribution imbalance constitutes the primary performance limitation for aspect sentiment analysis, with minority aspect-sentiment combinations achieving zero performance due to insufficient training data.
422
  \item The fundamental trade-off between algorithmic complexity and model interpretability substantially favors TF-IDF approaches for banking applications requiring transparency and regulatory compliance.
 
23
  \maketitle
24
 
25
  \begin{abstract}
26
+ This paper presents Pulse Core 1, a Vietnamese banking aspect sentiment analysis system employing Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction combined with machine learning classification algorithms. The system is evaluated on the UTS2017\_Bank aspect sentiment dataset containing 35 combined aspect-sentiment categories, achieving 68.18\% accuracy with Logistic Regression and 71.72\% accuracy with Support Vector Classification (SVC). The implementation utilizes a 20,000-dimensional TF-IDF feature space with n-gram analysis and incorporates hash-based caching for computational optimization. The model predicts combined aspect-sentiment labels in the format \texttt{<aspect>\#<sentiment>}, enabling fine-grained analysis of Vietnamese banking customer feedback across 14 banking aspects (ACCOUNT, CARD, CUSTOMER\_SUPPORT, etc.) and 3 sentiment polarities (positive, negative, neutral). These results establish baseline performance metrics for Vietnamese banking aspect sentiment analysis and demonstrate the efficacy of traditional machine learning approaches for Vietnamese financial domain natural language processing tasks.
27
  \end{abstract}
28
 
29
  \section{Introduction}
 
92
 
93
  \subsubsection{Classification Model}
94
 
95
+ The system implements both Logistic Regression and Support Vector Classification (SVC) algorithms with the following hyperparameter configurations:
96
 
97
+ \textbf{Logistic Regression}:
98
  \begin{itemize}
99
  \item \textbf{Optimization Algorithm}: Limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) quasi-Newton method for efficient convergence
100
  \item \textbf{Regularization}: L2 (Ridge) penalty with automatic parameter tuning to prevent overfitting
101
  \item \textbf{Convergence Criteria}: Maximum 1,000 iterations with tolerance-based early stopping
102
+ \end{itemize}
103
+
104
+ \textbf{Support Vector Classification (SVC)}:
105
+ \begin{itemize}
106
+ \item \textbf{Kernel Function}: Linear kernel for computational efficiency and interpretability
107
+ \item \textbf{Regularization Parameter}: C=1.0 with automatic tuning capability
108
+ \item \textbf{Probability Estimation}: Enabled for confidence scoring and multi-class probability distribution
109
  \item \textbf{Multi-class Extension}: One-vs-Rest strategy for handling multi-label classification tasks
110
  \end{itemize}
111
 
 
176
  \hline
177
  \textbf{Dataset} & \textbf{Method} & \textbf{Accuracy} \\
178
  \hline
179
+ UTS2017\_Bank (35 aspect-sentiment) & \textbf{Pulse Core 1 - SVC with TF-IDF} & \textbf{71.72\%} \\
180
  UTS2017\_Bank (35 aspect-sentiment) & \textbf{Pulse Core 1 - Logistic Regression with TF-IDF} & \textbf{68.18\%} \\
181
  \hline
182
  \end{tabular}
 
195
  \textbf{UTS2017\_Bank Dataset (Banking Aspect Sentiment Analysis):}
196
  The system exhibits competitive performance on the banking aspect sentiment analysis task:
197
  \begin{itemize}
198
+ \item \textbf{Test Classification Accuracy (SVC)}: 71.72\%
199
  \item \textbf{Test Classification Accuracy (Logistic Regression)}: 68.18\%
200
  \item \textbf{Training Latency (SVC)}: 5.3 seconds
201
  \item \textbf{Training Latency (Logistic Regression)}: 2.13 seconds
 
232
 
233
  \textbf{Model Performance Summary:}
234
  \begin{itemize}
235
+ \item \textbf{SVC Model}: 71.72\% overall accuracy with 20k features and 1-2 n-gram range
236
  \item \textbf{Logistic Regression Model}: 70.96\% overall accuracy with 20k features and 1-2 n-gram range
237
  \item \textbf{Performance Gain}: SVC achieves a 1.51 percentage point improvement over Logistic Regression
238
  \end{itemize}
239
 
240
  \textbf{UTS2017\_Bank Dataset Comparative Per-Class Results:}
241
 
242
+ The following table presents a side-by-side comparison of per-class performance metrics for both SVC (71.72\% accuracy) and Logistic Regression (70.96\% accuracy) models:
243
 
244
  \begin{longtable}{lcccccccc}
245
  \toprule
 
353
  The experimental results establish that systematically optimized traditional machine learning methodologies maintain competitive performance for Vietnamese banking aspect sentiment analysis tasks, providing an efficient baseline for financial domain applications. These findings yield several significant research implications:
354
 
355
  \begin{itemize}
356
+ \item \textbf{Computational Resource Efficiency}: The proposed approach exhibits substantially reduced computational complexity compared to transformer-based alternatives while achieving 71.72\% accuracy on complex aspect sentiment analysis tasks.
357
  \item \textbf{Model Interpretability}: TF-IDF feature representations provide transparent attribution mechanisms for banking aspect sentiment decisions, essential for financial applications requiring algorithmic accountability.
358
  \item \textbf{Production Deployment Viability}: The system's constrained computational requirements (2.13s training time) facilitate deployment in banking environments with limited computational resources.
359
  \end{itemize}
 
424
  This paper presents Pulse Core 1, a Vietnamese banking aspect sentiment analysis system that establishes the viability of systematically optimized traditional machine learning methodologies for financial domain applications. The investigation yields several significant findings:
425
 
426
  \begin{enumerate}
427
+ \item Traditional machine learning approaches achieve competitive performance on Vietnamese banking aspect sentiment analysis tasks (71.72\% accuracy with SVC) while maintaining substantial computational efficiency advantages (5.3s training time).
428
  \item Feature engineering methodologies retain critical importance for Vietnamese banking applications, with the implemented 20,000-dimensional TF-IDF representation effectively capturing aspect-sentiment relationships across 35 combined categories.
429
  \item Class distribution imbalance constitutes the primary performance limitation for aspect sentiment analysis, with minority aspect-sentiment combinations achieving zero performance due to insufficient training data.
430
  \item The fundamental trade-off between algorithmic complexity and model interpretability substantially favors TF-IDF approaches for banking applications requiring transparency and regulatory compliance.
runs/20250928_131527/metadata.json ADDED
@@ -0,0 +1,1531 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "timestamp": "20250928_131527",
3
+ "config_name": "UTS2017_Bank_AspectSentiment_SVC_feat20k_ngram1-2",
4
+ "model_name": "svc_linear",
5
+ "classifier": "SVC",
6
+ "max_features": 20000,
7
+ "ngram_range": [
8
+ 1,
9
+ 2
10
+ ],
11
+ "split_ratio": 0.2,
12
+ "n_samples": null,
13
+ "train_samples": 1581,
14
+ "test_samples": 396,
15
+ "unique_labels": 35,
16
+ "labels": [
17
+ "ACCOUNT#negative",
18
+ "CARD#negative",
19
+ "CARD#neutral",
20
+ "CARD#positive",
21
+ "CUSTOMER_SUPPORT#negative",
22
+ "CUSTOMER_SUPPORT#neutral",
23
+ "CUSTOMER_SUPPORT#positive",
24
+ "DISCOUNT#negative",
25
+ "DISCOUNT#neutral",
26
+ "DISCOUNT#positive",
27
+ "INTEREST_RATE#negative",
28
+ "INTEREST_RATE#neutral",
29
+ "INTEREST_RATE#positive",
30
+ "INTERNET_BANKING#negative",
31
+ "INTERNET_BANKING#neutral",
32
+ "INTERNET_BANKING#positive",
33
+ "LOAN#negative",
34
+ "LOAN#positive",
35
+ "MONEY_TRANSFER#negative",
36
+ "MONEY_TRANSFER#positive",
37
+ "OTHER#negative",
38
+ "OTHER#neutral",
39
+ "OTHER#positive",
40
+ "PAYMENT#negative",
41
+ "PAYMENT#positive",
42
+ "PROMOTION#negative",
43
+ "PROMOTION#neutral",
44
+ "PROMOTION#positive",
45
+ "SAVING#negative",
46
+ "SAVING#neutral",
47
+ "SAVING#positive",
48
+ "SECURITY#neutral",
49
+ "SECURITY#positive",
50
+ "TRADEMARK#negative",
51
+ "TRADEMARK#positive"
52
+ ],
53
+ "train_accuracy": 0.9430740037950665,
54
+ "test_accuracy": 0.7171717171717171,
55
+ "train_time": 7.737863779067993,
56
+ "prediction_time": 0.1107940673828125,
57
+ "classification_report": {
58
+ "ACCOUNT#negative": {
59
+ "precision": 0.0,
60
+ "recall": 0.0,
61
+ "f1-score": 0.0,
62
+ "support": 2.0
63
+ },
64
+ "CARD#negative": {
65
+ "precision": 1.0,
66
+ "recall": 0.14285714285714285,
67
+ "f1-score": 0.25,
68
+ "support": 7.0
69
+ },
70
+ "CARD#positive": {
71
+ "precision": 0.0,
72
+ "recall": 0.0,
73
+ "f1-score": 0.0,
74
+ "support": 1.0
75
+ },
76
+ "CUSTOMER_SUPPORT#negative": {
77
+ "precision": 0.4931506849315068,
78
+ "recall": 0.96,
79
+ "f1-score": 0.6515837104072398,
80
+ "support": 75.0
81
+ },
82
+ "CUSTOMER_SUPPORT#neutral": {
83
+ "precision": 0.0,
84
+ "recall": 0.0,
85
+ "f1-score": 0.0,
86
+ "support": 1.0
87
+ },
88
+ "CUSTOMER_SUPPORT#positive": {
89
+ "precision": 0.8641975308641975,
90
+ "recall": 0.8974358974358975,
91
+ "f1-score": 0.8805031446540881,
92
+ "support": 78.0
93
+ },
94
+ "DISCOUNT#negative": {
95
+ "precision": 0.0,
96
+ "recall": 0.0,
97
+ "f1-score": 0.0,
98
+ "support": 5.0
99
+ },
100
+ "DISCOUNT#neutral": {
101
+ "precision": 0.0,
102
+ "recall": 0.0,
103
+ "f1-score": 0.0,
104
+ "support": 1.0
105
+ },
106
+ "DISCOUNT#positive": {
107
+ "precision": 0.0,
108
+ "recall": 0.0,
109
+ "f1-score": 0.0,
110
+ "support": 0.0
111
+ },
112
+ "INTEREST_RATE#negative": {
113
+ "precision": 0.5555555555555556,
114
+ "recall": 0.5,
115
+ "f1-score": 0.5263157894736842,
116
+ "support": 10.0
117
+ },
118
+ "INTERNET_BANKING#negative": {
119
+ "precision": 0.0,
120
+ "recall": 0.0,
121
+ "f1-score": 0.0,
122
+ "support": 12.0
123
+ },
124
+ "INTERNET_BANKING#positive": {
125
+ "precision": 0.0,
126
+ "recall": 0.0,
127
+ "f1-score": 0.0,
128
+ "support": 1.0
129
+ },
130
+ "LOAN#negative": {
131
+ "precision": 0.875,
132
+ "recall": 0.5384615384615384,
133
+ "f1-score": 0.6666666666666666,
134
+ "support": 13.0
135
+ },
136
+ "MONEY_TRANSFER#negative": {
137
+ "precision": 0.0,
138
+ "recall": 0.0,
139
+ "f1-score": 0.0,
140
+ "support": 5.0
141
+ },
142
+ "OTHER#negative": {
143
+ "precision": 0.0,
144
+ "recall": 0.0,
145
+ "f1-score": 0.0,
146
+ "support": 10.0
147
+ },
148
+ "OTHER#neutral": {
149
+ "precision": 0.0,
150
+ "recall": 0.0,
151
+ "f1-score": 0.0,
152
+ "support": 1.0
153
+ },
154
+ "OTHER#positive": {
155
+ "precision": 0.6666666666666666,
156
+ "recall": 0.5,
157
+ "f1-score": 0.5714285714285714,
158
+ "support": 4.0
159
+ },
160
+ "PAYMENT#positive": {
161
+ "precision": 0.0,
162
+ "recall": 0.0,
163
+ "f1-score": 0.0,
164
+ "support": 3.0
165
+ },
166
+ "PROMOTION#negative": {
167
+ "precision": 0.0,
168
+ "recall": 0.0,
169
+ "f1-score": 0.0,
170
+ "support": 4.0
171
+ },
172
+ "PROMOTION#neutral": {
173
+ "precision": 0.0,
174
+ "recall": 0.0,
175
+ "f1-score": 0.0,
176
+ "support": 1.0
177
+ },
178
+ "PROMOTION#positive": {
179
+ "precision": 0.3333333333333333,
180
+ "recall": 0.2,
181
+ "f1-score": 0.25,
182
+ "support": 5.0
183
+ },
184
+ "SAVING#negative": {
185
+ "precision": 0.0,
186
+ "recall": 0.0,
187
+ "f1-score": 0.0,
188
+ "support": 1.0
189
+ },
190
+ "SAVING#positive": {
191
+ "precision": 0.0,
192
+ "recall": 0.0,
193
+ "f1-score": 0.0,
194
+ "support": 2.0
195
+ },
196
+ "SECURITY#negative": {
197
+ "precision": 0.0,
198
+ "recall": 0.0,
199
+ "f1-score": 0.0,
200
+ "support": 1.0
201
+ },
202
+ "SECURITY#neutral": {
203
+ "precision": 0.0,
204
+ "recall": 0.0,
205
+ "f1-score": 0.0,
206
+ "support": 1.0
207
+ },
208
+ "TRADEMARK#negative": {
209
+ "precision": 0.0,
210
+ "recall": 0.0,
211
+ "f1-score": 0.0,
212
+ "support": 14.0
213
+ },
214
+ "TRADEMARK#positive": {
215
+ "precision": 0.8936170212765957,
216
+ "recall": 0.9130434782608695,
217
+ "f1-score": 0.9032258064516129,
218
+ "support": 138.0
219
+ },
220
+ "accuracy": 0.7171717171717171,
221
+ "macro avg": {
222
+ "precision": 0.21042669602325392,
223
+ "recall": 0.17228881692649806,
224
+ "f1-score": 0.1740638403363653,
225
+ "support": 396.0
226
+ },
227
+ "weighted avg": {
228
+ "precision": 0.6464059257634583,
229
+ "recall": 0.7171717171717171,
230
+ "f1-score": 0.6601230396489957,
231
+ "support": 396.0
232
+ }
233
+ },
234
+ "confusion_matrix": [
235
+ [
236
+ 0,
237
+ 0,
238
+ 0,
239
+ 0,
240
+ 1,
241
+ 0,
242
+ 1,
243
+ 0,
244
+ 0,
245
+ 0,
246
+ 0,
247
+ 0,
248
+ 0,
249
+ 0,
250
+ 0,
251
+ 0,
252
+ 0,
253
+ 0,
254
+ 0,
255
+ 0,
256
+ 0,
257
+ 0,
258
+ 0,
259
+ 0,
260
+ 0,
261
+ 0,
262
+ 0,
263
+ 0,
264
+ 0,
265
+ 0,
266
+ 0,
267
+ 0,
268
+ 0,
269
+ 0,
270
+ 0
271
+ ],
272
+ [
273
+ 0,
274
+ 1,
275
+ 0,
276
+ 0,
277
+ 5,
278
+ 0,
279
+ 0,
280
+ 0,
281
+ 0,
282
+ 0,
283
+ 1,
284
+ 0,
285
+ 0,
286
+ 0,
287
+ 0,
288
+ 0,
289
+ 0,
290
+ 0,
291
+ 0,
292
+ 0,
293
+ 0,
294
+ 0,
295
+ 0,
296
+ 0,
297
+ 0,
298
+ 0,
299
+ 0,
300
+ 0,
301
+ 0,
302
+ 0,
303
+ 0,
304
+ 0,
305
+ 0,
306
+ 0,
307
+ 0
308
+ ],
309
+ [
310
+ 0,
311
+ 0,
312
+ 0,
313
+ 0,
314
+ 0,
315
+ 0,
316
+ 0,
317
+ 0,
318
+ 0,
319
+ 0,
320
+ 0,
321
+ 0,
322
+ 0,
323
+ 0,
324
+ 0,
325
+ 0,
326
+ 0,
327
+ 0,
328
+ 0,
329
+ 0,
330
+ 0,
331
+ 0,
332
+ 0,
333
+ 0,
334
+ 0,
335
+ 0,
336
+ 0,
337
+ 0,
338
+ 0,
339
+ 0,
340
+ 0,
341
+ 0,
342
+ 0,
343
+ 0,
344
+ 0
345
+ ],
346
+ [
347
+ 0,
348
+ 0,
349
+ 0,
350
+ 0,
351
+ 0,
352
+ 0,
353
+ 0,
354
+ 0,
355
+ 0,
356
+ 0,
357
+ 0,
358
+ 0,
359
+ 0,
360
+ 0,
361
+ 0,
362
+ 0,
363
+ 0,
364
+ 0,
365
+ 0,
366
+ 0,
367
+ 0,
368
+ 0,
369
+ 0,
370
+ 0,
371
+ 0,
372
+ 0,
373
+ 0,
374
+ 0,
375
+ 0,
376
+ 0,
377
+ 0,
378
+ 0,
379
+ 0,
380
+ 0,
381
+ 1
382
+ ],
383
+ [
384
+ 0,
385
+ 0,
386
+ 0,
387
+ 0,
388
+ 72,
389
+ 0,
390
+ 1,
391
+ 0,
392
+ 0,
393
+ 0,
394
+ 1,
395
+ 0,
396
+ 0,
397
+ 0,
398
+ 0,
399
+ 0,
400
+ 1,
401
+ 0,
402
+ 0,
403
+ 0,
404
+ 0,
405
+ 0,
406
+ 0,
407
+ 0,
408
+ 0,
409
+ 0,
410
+ 0,
411
+ 0,
412
+ 0,
413
+ 0,
414
+ 0,
415
+ 0,
416
+ 0,
417
+ 0,
418
+ 0
419
+ ],
420
+ [
421
+ 0,
422
+ 0,
423
+ 0,
424
+ 0,
425
+ 1,
426
+ 0,
427
+ 0,
428
+ 0,
429
+ 0,
430
+ 0,
431
+ 0,
432
+ 0,
433
+ 0,
434
+ 0,
435
+ 0,
436
+ 0,
437
+ 0,
438
+ 0,
439
+ 0,
440
+ 0,
441
+ 0,
442
+ 0,
443
+ 0,
444
+ 0,
445
+ 0,
446
+ 0,
447
+ 0,
448
+ 0,
449
+ 0,
450
+ 0,
451
+ 0,
452
+ 0,
453
+ 0,
454
+ 0,
455
+ 0
456
+ ],
457
+ [
458
+ 0,
459
+ 0,
460
+ 0,
461
+ 0,
462
+ 6,
463
+ 0,
464
+ 70,
465
+ 0,
466
+ 0,
467
+ 0,
468
+ 0,
469
+ 0,
470
+ 0,
471
+ 0,
472
+ 0,
473
+ 0,
474
+ 0,
475
+ 0,
476
+ 0,
477
+ 0,
478
+ 0,
479
+ 0,
480
+ 0,
481
+ 0,
482
+ 0,
483
+ 0,
484
+ 0,
485
+ 0,
486
+ 0,
487
+ 0,
488
+ 0,
489
+ 0,
490
+ 0,
491
+ 0,
492
+ 2
493
+ ],
494
+ [
495
+ 0,
496
+ 0,
497
+ 0,
498
+ 0,
499
+ 5,
500
+ 0,
501
+ 0,
502
+ 0,
503
+ 0,
504
+ 0,
505
+ 0,
506
+ 0,
507
+ 0,
508
+ 0,
509
+ 0,
510
+ 0,
511
+ 0,
512
+ 0,
513
+ 0,
514
+ 0,
515
+ 0,
516
+ 0,
517
+ 0,
518
+ 0,
519
+ 0,
520
+ 0,
521
+ 0,
522
+ 0,
523
+ 0,
524
+ 0,
525
+ 0,
526
+ 0,
527
+ 0,
528
+ 0,
529
+ 0
530
+ ],
531
+ [
532
+ 0,
533
+ 0,
534
+ 0,
535
+ 0,
536
+ 1,
537
+ 0,
538
+ 0,
539
+ 0,
540
+ 0,
541
+ 0,
542
+ 0,
543
+ 0,
544
+ 0,
545
+ 0,
546
+ 0,
547
+ 0,
548
+ 0,
549
+ 0,
550
+ 0,
551
+ 0,
552
+ 0,
553
+ 0,
554
+ 0,
555
+ 0,
556
+ 0,
557
+ 0,
558
+ 0,
559
+ 0,
560
+ 0,
561
+ 0,
562
+ 0,
563
+ 0,
564
+ 0,
565
+ 0,
566
+ 0
567
+ ],
568
+ [
569
+ 0,
570
+ 0,
571
+ 0,
572
+ 0,
573
+ 0,
574
+ 0,
575
+ 0,
576
+ 0,
577
+ 0,
578
+ 0,
579
+ 0,
580
+ 0,
581
+ 0,
582
+ 0,
583
+ 0,
584
+ 0,
585
+ 0,
586
+ 0,
587
+ 0,
588
+ 0,
589
+ 0,
590
+ 0,
591
+ 0,
592
+ 0,
593
+ 0,
594
+ 0,
595
+ 0,
596
+ 0,
597
+ 0,
598
+ 0,
599
+ 0,
600
+ 0,
601
+ 0,
602
+ 0,
603
+ 0
604
+ ],
605
+ [
606
+ 0,
607
+ 0,
608
+ 0,
609
+ 0,
610
+ 4,
611
+ 0,
612
+ 0,
613
+ 0,
614
+ 0,
615
+ 0,
616
+ 5,
617
+ 0,
618
+ 0,
619
+ 0,
620
+ 0,
621
+ 0,
622
+ 0,
623
+ 0,
624
+ 0,
625
+ 0,
626
+ 0,
627
+ 0,
628
+ 0,
629
+ 0,
630
+ 0,
631
+ 0,
632
+ 0,
633
+ 0,
634
+ 0,
635
+ 0,
636
+ 0,
637
+ 0,
638
+ 0,
639
+ 0,
640
+ 1
641
+ ],
642
+ [
643
+ 0,
644
+ 0,
645
+ 0,
646
+ 0,
647
+ 0,
648
+ 0,
649
+ 0,
650
+ 0,
651
+ 0,
652
+ 0,
653
+ 0,
654
+ 0,
655
+ 0,
656
+ 0,
657
+ 0,
658
+ 0,
659
+ 0,
660
+ 0,
661
+ 0,
662
+ 0,
663
+ 0,
664
+ 0,
665
+ 0,
666
+ 0,
667
+ 0,
668
+ 0,
669
+ 0,
670
+ 0,
671
+ 0,
672
+ 0,
673
+ 0,
674
+ 0,
675
+ 0,
676
+ 0,
677
+ 0
678
+ ],
679
+ [
680
+ 0,
681
+ 0,
682
+ 0,
683
+ 0,
684
+ 0,
685
+ 0,
686
+ 0,
687
+ 0,
688
+ 0,
689
+ 0,
690
+ 0,
691
+ 0,
692
+ 0,
693
+ 0,
694
+ 0,
695
+ 0,
696
+ 0,
697
+ 0,
698
+ 0,
699
+ 0,
700
+ 0,
701
+ 0,
702
+ 0,
703
+ 0,
704
+ 0,
705
+ 0,
706
+ 0,
707
+ 0,
708
+ 0,
709
+ 0,
710
+ 0,
711
+ 0,
712
+ 0,
713
+ 0,
714
+ 0
715
+ ],
716
+ [
717
+ 0,
718
+ 0,
719
+ 0,
720
+ 0,
721
+ 12,
722
+ 0,
723
+ 0,
724
+ 0,
725
+ 0,
726
+ 0,
727
+ 0,
728
+ 0,
729
+ 0,
730
+ 0,
731
+ 0,
732
+ 0,
733
+ 0,
734
+ 0,
735
+ 0,
736
+ 0,
737
+ 0,
738
+ 0,
739
+ 0,
740
+ 0,
741
+ 0,
742
+ 0,
743
+ 0,
744
+ 0,
745
+ 0,
746
+ 0,
747
+ 0,
748
+ 0,
749
+ 0,
750
+ 0,
751
+ 0
752
+ ],
753
+ [
754
+ 0,
755
+ 0,
756
+ 0,
757
+ 0,
758
+ 0,
759
+ 0,
760
+ 0,
761
+ 0,
762
+ 0,
763
+ 0,
764
+ 0,
765
+ 0,
766
+ 0,
767
+ 0,
768
+ 0,
769
+ 0,
770
+ 0,
771
+ 0,
772
+ 0,
773
+ 0,
774
+ 0,
775
+ 0,
776
+ 0,
777
+ 0,
778
+ 0,
779
+ 0,
780
+ 0,
781
+ 0,
782
+ 0,
783
+ 0,
784
+ 0,
785
+ 0,
786
+ 0,
787
+ 0,
788
+ 0
789
+ ],
790
+ [
791
+ 0,
792
+ 0,
793
+ 0,
794
+ 0,
795
+ 1,
796
+ 0,
797
+ 0,
798
+ 0,
799
+ 0,
800
+ 0,
801
+ 0,
802
+ 0,
803
+ 0,
804
+ 0,
805
+ 0,
806
+ 0,
807
+ 0,
808
+ 0,
809
+ 0,
810
+ 0,
811
+ 0,
812
+ 0,
813
+ 0,
814
+ 0,
815
+ 0,
816
+ 0,
817
+ 0,
818
+ 0,
819
+ 0,
820
+ 0,
821
+ 0,
822
+ 0,
823
+ 0,
824
+ 0,
825
+ 0
826
+ ],
827
+ [
828
+ 0,
829
+ 0,
830
+ 0,
831
+ 0,
832
+ 4,
833
+ 0,
834
+ 0,
835
+ 0,
836
+ 0,
837
+ 0,
838
+ 0,
839
+ 0,
840
+ 0,
841
+ 0,
842
+ 0,
843
+ 0,
844
+ 7,
845
+ 0,
846
+ 0,
847
+ 0,
848
+ 0,
849
+ 0,
850
+ 0,
851
+ 0,
852
+ 0,
853
+ 0,
854
+ 0,
855
+ 0,
856
+ 0,
857
+ 0,
858
+ 0,
859
+ 0,
860
+ 0,
861
+ 2,
862
+ 0
863
+ ],
864
+ [
865
+ 0,
866
+ 0,
867
+ 0,
868
+ 0,
869
+ 0,
870
+ 0,
871
+ 0,
872
+ 0,
873
+ 0,
874
+ 0,
875
+ 0,
876
+ 0,
877
+ 0,
878
+ 0,
879
+ 0,
880
+ 0,
881
+ 0,
882
+ 0,
883
+ 0,
884
+ 0,
885
+ 0,
886
+ 0,
887
+ 0,
888
+ 0,
889
+ 0,
890
+ 0,
891
+ 0,
892
+ 0,
893
+ 0,
894
+ 0,
895
+ 0,
896
+ 0,
897
+ 0,
898
+ 0,
899
+ 0
900
+ ],
901
+ [
902
+ 0,
903
+ 0,
904
+ 0,
905
+ 0,
906
+ 3,
907
+ 0,
908
+ 0,
909
+ 0,
910
+ 0,
911
+ 0,
912
+ 2,
913
+ 0,
914
+ 0,
915
+ 0,
916
+ 0,
917
+ 0,
918
+ 0,
919
+ 0,
920
+ 0,
921
+ 0,
922
+ 0,
923
+ 0,
924
+ 0,
925
+ 0,
926
+ 0,
927
+ 0,
928
+ 0,
929
+ 0,
930
+ 0,
931
+ 0,
932
+ 0,
933
+ 0,
934
+ 0,
935
+ 0,
936
+ 0
937
+ ],
938
+ [
939
+ 0,
940
+ 0,
941
+ 0,
942
+ 0,
943
+ 0,
944
+ 0,
945
+ 0,
946
+ 0,
947
+ 0,
948
+ 0,
949
+ 0,
950
+ 0,
951
+ 0,
952
+ 0,
953
+ 0,
954
+ 0,
955
+ 0,
956
+ 0,
957
+ 0,
958
+ 0,
959
+ 0,
960
+ 0,
961
+ 0,
962
+ 0,
963
+ 0,
964
+ 0,
965
+ 0,
966
+ 0,
967
+ 0,
968
+ 0,
969
+ 0,
970
+ 0,
971
+ 0,
972
+ 0,
973
+ 0
974
+ ],
975
+ [
976
+ 0,
977
+ 0,
978
+ 0,
979
+ 0,
980
+ 8,
981
+ 0,
982
+ 0,
983
+ 0,
984
+ 0,
985
+ 1,
986
+ 0,
987
+ 0,
988
+ 0,
989
+ 0,
990
+ 0,
991
+ 0,
992
+ 0,
993
+ 0,
994
+ 0,
995
+ 0,
996
+ 0,
997
+ 0,
998
+ 0,
999
+ 0,
1000
+ 0,
1001
+ 0,
1002
+ 0,
1003
+ 0,
1004
+ 0,
1005
+ 0,
1006
+ 0,
1007
+ 0,
1008
+ 0,
1009
+ 1,
1010
+ 0
1011
+ ],
1012
+ [
1013
+ 0,
1014
+ 0,
1015
+ 0,
1016
+ 0,
1017
+ 1,
1018
+ 0,
1019
+ 0,
1020
+ 0,
1021
+ 0,
1022
+ 0,
1023
+ 0,
1024
+ 0,
1025
+ 0,
1026
+ 0,
1027
+ 0,
1028
+ 0,
1029
+ 0,
1030
+ 0,
1031
+ 0,
1032
+ 0,
1033
+ 0,
1034
+ 0,
1035
+ 0,
1036
+ 0,
1037
+ 0,
1038
+ 0,
1039
+ 0,
1040
+ 0,
1041
+ 0,
1042
+ 0,
1043
+ 0,
1044
+ 0,
1045
+ 0,
1046
+ 0,
1047
+ 0
1048
+ ],
1049
+ [
1050
+ 0,
1051
+ 0,
1052
+ 0,
1053
+ 0,
1054
+ 1,
1055
+ 0,
1056
+ 0,
1057
+ 0,
1058
+ 0,
1059
+ 0,
1060
+ 0,
1061
+ 0,
1062
+ 0,
1063
+ 0,
1064
+ 0,
1065
+ 0,
1066
+ 0,
1067
+ 0,
1068
+ 0,
1069
+ 0,
1070
+ 0,
1071
+ 0,
1072
+ 2,
1073
+ 0,
1074
+ 0,
1075
+ 0,
1076
+ 0,
1077
+ 0,
1078
+ 0,
1079
+ 0,
1080
+ 0,
1081
+ 0,
1082
+ 0,
1083
+ 0,
1084
+ 1
1085
+ ],
1086
+ [
1087
+ 0,
1088
+ 0,
1089
+ 0,
1090
+ 0,
1091
+ 0,
1092
+ 0,
1093
+ 0,
1094
+ 0,
1095
+ 0,
1096
+ 0,
1097
+ 0,
1098
+ 0,
1099
+ 0,
1100
+ 0,
1101
+ 0,
1102
+ 0,
1103
+ 0,
1104
+ 0,
1105
+ 0,
1106
+ 0,
1107
+ 0,
1108
+ 0,
1109
+ 0,
1110
+ 0,
1111
+ 0,
1112
+ 0,
1113
+ 0,
1114
+ 0,
1115
+ 0,
1116
+ 0,
1117
+ 0,
1118
+ 0,
1119
+ 0,
1120
+ 0,
1121
+ 0
1122
+ ],
1123
+ [
1124
+ 0,
1125
+ 0,
1126
+ 0,
1127
+ 0,
1128
+ 0,
1129
+ 0,
1130
+ 2,
1131
+ 0,
1132
+ 0,
1133
+ 0,
1134
+ 0,
1135
+ 0,
1136
+ 0,
1137
+ 0,
1138
+ 0,
1139
+ 0,
1140
+ 0,
1141
+ 0,
1142
+ 0,
1143
+ 0,
1144
+ 0,
1145
+ 0,
1146
+ 0,
1147
+ 0,
1148
+ 0,
1149
+ 0,
1150
+ 0,
1151
+ 0,
1152
+ 0,
1153
+ 0,
1154
+ 0,
1155
+ 0,
1156
+ 0,
1157
+ 0,
1158
+ 1
1159
+ ],
1160
+ [
1161
+ 0,
1162
+ 0,
1163
+ 0,
1164
+ 0,
1165
+ 3,
1166
+ 0,
1167
+ 0,
1168
+ 0,
1169
+ 0,
1170
+ 0,
1171
+ 0,
1172
+ 0,
1173
+ 0,
1174
+ 0,
1175
+ 0,
1176
+ 0,
1177
+ 0,
1178
+ 0,
1179
+ 0,
1180
+ 0,
1181
+ 0,
1182
+ 0,
1183
+ 0,
1184
+ 0,
1185
+ 0,
1186
+ 0,
1187
+ 0,
1188
+ 1,
1189
+ 0,
1190
+ 0,
1191
+ 0,
1192
+ 0,
1193
+ 0,
1194
+ 0,
1195
+ 0
1196
+ ],
1197
+ [
1198
+ 0,
1199
+ 0,
1200
+ 0,
1201
+ 0,
1202
+ 1,
1203
+ 0,
1204
+ 0,
1205
+ 0,
1206
+ 0,
1207
+ 0,
1208
+ 0,
1209
+ 0,
1210
+ 0,
1211
+ 0,
1212
+ 0,
1213
+ 0,
1214
+ 0,
1215
+ 0,
1216
+ 0,
1217
+ 0,
1218
+ 0,
1219
+ 0,
1220
+ 0,
1221
+ 0,
1222
+ 0,
1223
+ 0,
1224
+ 0,
1225
+ 0,
1226
+ 0,
1227
+ 0,
1228
+ 0,
1229
+ 0,
1230
+ 0,
1231
+ 0,
1232
+ 0
1233
+ ],
1234
+ [
1235
+ 0,
1236
+ 0,
1237
+ 0,
1238
+ 0,
1239
+ 0,
1240
+ 0,
1241
+ 0,
1242
+ 0,
1243
+ 0,
1244
+ 0,
1245
+ 0,
1246
+ 0,
1247
+ 0,
1248
+ 0,
1249
+ 0,
1250
+ 0,
1251
+ 0,
1252
+ 0,
1253
+ 0,
1254
+ 0,
1255
+ 0,
1256
+ 0,
1257
+ 1,
1258
+ 0,
1259
+ 0,
1260
+ 0,
1261
+ 0,
1262
+ 1,
1263
+ 0,
1264
+ 0,
1265
+ 0,
1266
+ 0,
1267
+ 0,
1268
+ 0,
1269
+ 3
1270
+ ],
1271
+ [
1272
+ 0,
1273
+ 0,
1274
+ 0,
1275
+ 0,
1276
+ 1,
1277
+ 0,
1278
+ 0,
1279
+ 0,
1280
+ 0,
1281
+ 0,
1282
+ 0,
1283
+ 0,
1284
+ 0,
1285
+ 0,
1286
+ 0,
1287
+ 0,
1288
+ 0,
1289
+ 0,
1290
+ 0,
1291
+ 0,
1292
+ 0,
1293
+ 0,
1294
+ 0,
1295
+ 0,
1296
+ 0,
1297
+ 0,
1298
+ 0,
1299
+ 0,
1300
+ 0,
1301
+ 0,
1302
+ 0,
1303
+ 0,
1304
+ 0,
1305
+ 0,
1306
+ 0
1307
+ ],
1308
+ [
1309
+ 0,
1310
+ 0,
1311
+ 0,
1312
+ 0,
1313
+ 0,
1314
+ 0,
1315
+ 0,
1316
+ 0,
1317
+ 0,
1318
+ 0,
1319
+ 0,
1320
+ 0,
1321
+ 0,
1322
+ 0,
1323
+ 0,
1324
+ 0,
1325
+ 0,
1326
+ 0,
1327
+ 0,
1328
+ 0,
1329
+ 0,
1330
+ 0,
1331
+ 0,
1332
+ 0,
1333
+ 0,
1334
+ 0,
1335
+ 0,
1336
+ 0,
1337
+ 0,
1338
+ 0,
1339
+ 0,
1340
+ 0,
1341
+ 0,
1342
+ 0,
1343
+ 0
1344
+ ],
1345
+ [
1346
+ 0,
1347
+ 0,
1348
+ 0,
1349
+ 0,
1350
+ 0,
1351
+ 0,
1352
+ 0,
1353
+ 0,
1354
+ 0,
1355
+ 0,
1356
+ 0,
1357
+ 0,
1358
+ 0,
1359
+ 0,
1360
+ 0,
1361
+ 0,
1362
+ 0,
1363
+ 0,
1364
+ 0,
1365
+ 0,
1366
+ 0,
1367
+ 0,
1368
+ 0,
1369
+ 0,
1370
+ 0,
1371
+ 0,
1372
+ 0,
1373
+ 0,
1374
+ 0,
1375
+ 0,
1376
+ 0,
1377
+ 0,
1378
+ 0,
1379
+ 0,
1380
+ 2
1381
+ ],
1382
+ [
1383
+ 0,
1384
+ 0,
1385
+ 0,
1386
+ 0,
1387
+ 1,
1388
+ 0,
1389
+ 0,
1390
+ 0,
1391
+ 0,
1392
+ 0,
1393
+ 0,
1394
+ 0,
1395
+ 0,
1396
+ 0,
1397
+ 0,
1398
+ 0,
1399
+ 0,
1400
+ 0,
1401
+ 0,
1402
+ 0,
1403
+ 0,
1404
+ 0,
1405
+ 0,
1406
+ 0,
1407
+ 0,
1408
+ 0,
1409
+ 0,
1410
+ 0,
1411
+ 0,
1412
+ 0,
1413
+ 0,
1414
+ 0,
1415
+ 0,
1416
+ 0,
1417
+ 0
1418
+ ],
1419
+ [
1420
+ 0,
1421
+ 0,
1422
+ 0,
1423
+ 0,
1424
+ 0,
1425
+ 0,
1426
+ 0,
1427
+ 0,
1428
+ 0,
1429
+ 0,
1430
+ 0,
1431
+ 0,
1432
+ 0,
1433
+ 0,
1434
+ 0,
1435
+ 0,
1436
+ 0,
1437
+ 0,
1438
+ 0,
1439
+ 0,
1440
+ 0,
1441
+ 0,
1442
+ 0,
1443
+ 0,
1444
+ 0,
1445
+ 0,
1446
+ 0,
1447
+ 0,
1448
+ 0,
1449
+ 0,
1450
+ 0,
1451
+ 0,
1452
+ 0,
1453
+ 0,
1454
+ 0
1455
+ ],
1456
+ [
1457
+ 0,
1458
+ 0,
1459
+ 0,
1460
+ 0,
1461
+ 10,
1462
+ 0,
1463
+ 0,
1464
+ 0,
1465
+ 0,
1466
+ 0,
1467
+ 0,
1468
+ 0,
1469
+ 0,
1470
+ 0,
1471
+ 0,
1472
+ 0,
1473
+ 0,
1474
+ 0,
1475
+ 0,
1476
+ 0,
1477
+ 0,
1478
+ 0,
1479
+ 0,
1480
+ 0,
1481
+ 0,
1482
+ 0,
1483
+ 0,
1484
+ 0,
1485
+ 0,
1486
+ 0,
1487
+ 0,
1488
+ 0,
1489
+ 0,
1490
+ 0,
1491
+ 4
1492
+ ],
1493
+ [
1494
+ 0,
1495
+ 0,
1496
+ 0,
1497
+ 0,
1498
+ 4,
1499
+ 0,
1500
+ 7,
1501
+ 0,
1502
+ 0,
1503
+ 0,
1504
+ 0,
1505
+ 0,
1506
+ 0,
1507
+ 0,
1508
+ 0,
1509
+ 0,
1510
+ 0,
1511
+ 0,
1512
+ 0,
1513
+ 0,
1514
+ 0,
1515
+ 0,
1516
+ 0,
1517
+ 0,
1518
+ 0,
1519
+ 0,
1520
+ 0,
1521
+ 1,
1522
+ 0,
1523
+ 0,
1524
+ 0,
1525
+ 0,
1526
+ 0,
1527
+ 0,
1528
+ 126
1529
+ ]
1530
+ ]
1531
+ }
runs/20250928_131527/models/UTS2017_Bank_AspectSentiment_SVC_feat20k_ngram1-2.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6abcdbb83ea5ae3d75b585cb12a7ce3a054f5e269d8d2c204cb01e732e94b1
3
+ size 2154772
runs/20250928_131527/models/labels.txt ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ACCOUNT#negative
2
+ CARD#negative
3
+ CARD#neutral
4
+ CARD#positive
5
+ CUSTOMER_SUPPORT#negative
6
+ CUSTOMER_SUPPORT#neutral
7
+ CUSTOMER_SUPPORT#positive
8
+ DISCOUNT#negative
9
+ DISCOUNT#neutral
10
+ DISCOUNT#positive
11
+ INTEREST_RATE#negative
12
+ INTEREST_RATE#neutral
13
+ INTEREST_RATE#positive
14
+ INTERNET_BANKING#negative
15
+ INTERNET_BANKING#neutral
16
+ INTERNET_BANKING#positive
17
+ LOAN#negative
18
+ LOAN#positive
19
+ MONEY_TRANSFER#negative
20
+ MONEY_TRANSFER#positive
21
+ OTHER#negative
22
+ OTHER#neutral
23
+ OTHER#positive
24
+ PAYMENT#negative
25
+ PAYMENT#positive
26
+ PROMOTION#negative
27
+ PROMOTION#neutral
28
+ PROMOTION#positive
29
+ SAVING#negative
30
+ SAVING#neutral
31
+ SAVING#positive
32
+ SECURITY#neutral
33
+ SECURITY#positive
34
+ TRADEMARK#negative
35
+ TRADEMARK#positive
runs/20250928_131527/models/model.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6abcdbb83ea5ae3d75b585cb12a7ce3a054f5e269d8d2c204cb01e732e94b1
3
+ size 2154772
runs/20250928_131527/training.log ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-09-28 13:15:27,107 - INFO - Starting training run: 20250928_131527
2
+ 2025-09-28 13:15:27,107 - INFO - Model: svc_linear
3
+ 2025-09-28 13:15:27,107 - INFO - Max features: 20000
4
+ 2025-09-28 13:15:27,107 - INFO - N-gram range: (1, 2)
5
+ 2025-09-28 13:15:27,107 - INFO - Loading UTS2017_Bank aspect sentiment dataset...
6
+ 2025-09-28 13:15:31,618 - INFO - Train samples: 1581
7
+ 2025-09-28 13:15:31,618 - INFO - Test samples: 396
8
+ 2025-09-28 13:15:31,618 - INFO - Unique labels: 35
9
+ 2025-09-28 13:15:31,618 - INFO - Label distribution (train): {np.str_('ACCOUNT#negative'): np.int64(3), np.str_('CARD#negative'): np.int64(47), np.str_('CARD#neutral'): np.int64(1), np.str_('CARD#positive'): np.int64(10), np.str_('CUSTOMER_SUPPORT#negative'): np.int64(288), np.str_('CUSTOMER_SUPPORT#neutral'): np.int64(4), np.str_('CUSTOMER_SUPPORT#positive'): np.int64(328), np.str_('DISCOUNT#negative'): np.int64(13), np.str_('DISCOUNT#neutral'): np.int64(3), np.str_('DISCOUNT#positive'): np.int64(19), np.str_('INTEREST_RATE#negative'): np.int64(45), np.str_('INTEREST_RATE#neutral'): np.int64(1), np.str_('INTEREST_RATE#positive'): np.int64(4), np.str_('INTERNET_BANKING#negative'): np.int64(36), np.str_('INTERNET_BANKING#neutral'): np.int64(2), np.str_('INTERNET_BANKING#positive'): np.int64(19), np.str_('LOAN#negative'): np.int64(48), np.str_('LOAN#positive'): np.int64(13), np.str_('MONEY_TRANSFER#negative'): np.int64(24), np.str_('MONEY_TRANSFER#positive'): np.int64(5), np.str_('OTHER#negative'): np.int64(25), np.str_('OTHER#neutral'): np.int64(3), np.str_('OTHER#positive'): np.int64(26), np.str_('PAYMENT#negative'): np.int64(4), np.str_('PAYMENT#positive'): np.int64(8), np.str_('PROMOTION#negative'): np.int64(13), np.str_('PROMOTION#neutral'): np.int64(2), np.str_('PROMOTION#positive'): np.int64(28), np.str_('SAVING#negative'): np.int64(5), np.str_('SAVING#neutral'): np.int64(1), np.str_('SAVING#positive'): np.int64(4), np.str_('SECURITY#neutral'): np.int64(1), np.str_('SECURITY#positive'): np.int64(1), np.str_('TRADEMARK#negative'): np.int64(33), np.str_('TRADEMARK#positive'): np.int64(514)}
10
+ 2025-09-28 13:15:31,618 - INFO - Label distribution (test): {np.str_('ACCOUNT#negative'): np.int64(2), np.str_('CARD#negative'): np.int64(7), np.str_('CARD#neutral'): np.int64(0), np.str_('CARD#positive'): np.int64(1), np.str_('CUSTOMER_SUPPORT#negative'): np.int64(75), np.str_('CUSTOMER_SUPPORT#neutral'): np.int64(1), np.str_('CUSTOMER_SUPPORT#positive'): np.int64(78), np.str_('DISCOUNT#negative'): np.int64(5), np.str_('DISCOUNT#neutral'): np.int64(1), np.str_('DISCOUNT#positive'): np.int64(0), np.str_('INTEREST_RATE#negative'): np.int64(10), np.str_('INTEREST_RATE#neutral'): np.int64(0), np.str_('INTEREST_RATE#positive'): np.int64(0), np.str_('INTERNET_BANKING#negative'): np.int64(12), np.str_('INTERNET_BANKING#neutral'): np.int64(0), np.str_('INTERNET_BANKING#positive'): np.int64(1), np.str_('LOAN#negative'): np.int64(13), np.str_('LOAN#positive'): np.int64(0), np.str_('MONEY_TRANSFER#negative'): np.int64(5), np.str_('MONEY_TRANSFER#positive'): np.int64(0), np.str_('OTHER#negative'): np.int64(10), np.str_('OTHER#neutral'): np.int64(1), np.str_('OTHER#positive'): np.int64(4), np.str_('PAYMENT#negative'): np.int64(0), np.str_('PAYMENT#positive'): np.int64(3), np.str_('PROMOTION#negative'): np.int64(4), np.str_('PROMOTION#neutral'): np.int64(1), np.str_('PROMOTION#positive'): np.int64(5), np.str_('SAVING#negative'): np.int64(1), np.str_('SAVING#neutral'): np.int64(0), np.str_('SAVING#positive'): np.int64(2), np.str_('SECURITY#neutral'): np.int64(1), np.str_('SECURITY#positive'): np.int64(0), np.str_('TRADEMARK#negative'): np.int64(14), np.str_('TRADEMARK#positive'): np.int64(138)}
11
+ 2025-09-28 13:15:31,619 - INFO - Selected classifier: SVC
12
+ 2025-09-28 13:15:31,619 - INFO - ============================================================
13
+ 2025-09-28 13:15:31,619 - INFO - Training: UTS2017_Bank_AspectSentiment_SVC_feat20k_ngram1-2
14
+ 2025-09-28 13:15:31,619 - INFO - ============================================================
15
+ 2025-09-28 13:15:31,619 - INFO - Creating pipeline with max_features=20000, ngram_range=(1, 2)
16
+ 2025-09-28 13:15:31,619 - INFO - Training model...
17
+ 2025-09-28 13:15:39,357 - INFO - Training completed in 7.74 seconds
18
+ 2025-09-28 13:15:39,357 - INFO - Evaluating on training set...
19
+ 2025-09-28 13:15:39,803 - INFO - Training accuracy: 0.9431
20
+ 2025-09-28 13:15:39,803 - INFO - Evaluating on test set...
21
+ 2025-09-28 13:15:39,914 - INFO - Test accuracy: 0.7172
22
+ 2025-09-28 13:15:39,914 - INFO - Prediction time: 0.11 seconds
23
+ 2025-09-28 13:15:39,914 - INFO - Classification Report:
24
+ 2025-09-28 13:15:39,918 - INFO - precision recall f1-score support
25
+
26
+ ACCOUNT#negative 0.00 0.00 0.00 2
27
+ CARD#negative 1.00 0.14 0.25 7
28
+ CARD#positive 0.00 0.00 0.00 1
29
+ CUSTOMER_SUPPORT#negative 0.49 0.96 0.65 75
30
+ CUSTOMER_SUPPORT#neutral 0.00 0.00 0.00 1
31
+ CUSTOMER_SUPPORT#positive 0.86 0.90 0.88 78
32
+ DISCOUNT#negative 0.00 0.00 0.00 5
33
+ DISCOUNT#neutral 0.00 0.00 0.00 1
34
+ DISCOUNT#positive 0.00 0.00 0.00 0
35
+ INTEREST_RATE#negative 0.56 0.50 0.53 10
36
+ INTERNET_BANKING#negative 0.00 0.00 0.00 12
37
+ INTERNET_BANKING#positive 0.00 0.00 0.00 1
38
+ LOAN#negative 0.88 0.54 0.67 13
39
+ MONEY_TRANSFER#negative 0.00 0.00 0.00 5
40
+ OTHER#negative 0.00 0.00 0.00 10
41
+ OTHER#neutral 0.00 0.00 0.00 1
42
+ OTHER#positive 0.67 0.50 0.57 4
43
+ PAYMENT#positive 0.00 0.00 0.00 3
44
+ PROMOTION#negative 0.00 0.00 0.00 4
45
+ PROMOTION#neutral 0.00 0.00 0.00 1
46
+ PROMOTION#positive 0.33 0.20 0.25 5
47
+ SAVING#negative 0.00 0.00 0.00 1
48
+ SAVING#positive 0.00 0.00 0.00 2
49
+ SECURITY#negative 0.00 0.00 0.00 1
50
+ SECURITY#neutral 0.00 0.00 0.00 1
51
+ TRADEMARK#negative 0.00 0.00 0.00 14
52
+ TRADEMARK#positive 0.89 0.91 0.90 138
53
+
54
+ accuracy 0.72 396
55
+ macro avg 0.21 0.17 0.17 396
56
+ weighted avg 0.65 0.72 0.66 396
57
+
58
+ 2025-09-28 13:15:39,922 - INFO - Confusion Matrix shape: (35, 35)
59
+ 2025-09-28 13:15:40,052 - INFO - Model saved to runs/20250928_131527/models/model.joblib
60
+ 2025-09-28 13:15:40,181 - INFO - Model also saved as runs/20250928_131527/models/UTS2017_Bank_AspectSentiment_SVC_feat20k_ngram1-2.joblib
61
+ 2025-09-28 13:15:40,181 - INFO - Label mapping saved to runs/20250928_131527/models/labels.txt
62
+ 2025-09-28 13:15:40,182 - INFO - Metadata saved to runs/20250928_131527/metadata.json
runs/20250928_131716/metadata.json ADDED
@@ -0,0 +1,1531 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "timestamp": "20250928_131716",
3
+ "config_name": "UTS2017_Bank_AspectSentiment_SVC_feat20k_ngram1-2",
4
+ "model_name": "svc_linear",
5
+ "classifier": "SVC",
6
+ "max_features": 20000,
7
+ "ngram_range": [
8
+ 1,
9
+ 2
10
+ ],
11
+ "split_ratio": 0.2,
12
+ "n_samples": null,
13
+ "train_samples": 1581,
14
+ "test_samples": 396,
15
+ "unique_labels": 35,
16
+ "labels": [
17
+ "ACCOUNT#negative",
18
+ "CARD#negative",
19
+ "CARD#neutral",
20
+ "CARD#positive",
21
+ "CUSTOMER_SUPPORT#negative",
22
+ "CUSTOMER_SUPPORT#neutral",
23
+ "CUSTOMER_SUPPORT#positive",
24
+ "DISCOUNT#negative",
25
+ "DISCOUNT#neutral",
26
+ "DISCOUNT#positive",
27
+ "INTEREST_RATE#negative",
28
+ "INTEREST_RATE#neutral",
29
+ "INTEREST_RATE#positive",
30
+ "INTERNET_BANKING#negative",
31
+ "INTERNET_BANKING#neutral",
32
+ "INTERNET_BANKING#positive",
33
+ "LOAN#negative",
34
+ "LOAN#positive",
35
+ "MONEY_TRANSFER#negative",
36
+ "MONEY_TRANSFER#positive",
37
+ "OTHER#negative",
38
+ "OTHER#neutral",
39
+ "OTHER#positive",
40
+ "PAYMENT#negative",
41
+ "PAYMENT#positive",
42
+ "PROMOTION#negative",
43
+ "PROMOTION#neutral",
44
+ "PROMOTION#positive",
45
+ "SAVING#negative",
46
+ "SAVING#neutral",
47
+ "SAVING#positive",
48
+ "SECURITY#neutral",
49
+ "SECURITY#positive",
50
+ "TRADEMARK#negative",
51
+ "TRADEMARK#positive"
52
+ ],
53
+ "train_accuracy": 0.9430740037950665,
54
+ "test_accuracy": 0.7171717171717171,
55
+ "train_time": 7.706280946731567,
56
+ "prediction_time": 0.10988211631774902,
57
+ "classification_report": {
58
+ "ACCOUNT#negative": {
59
+ "precision": 0.0,
60
+ "recall": 0.0,
61
+ "f1-score": 0.0,
62
+ "support": 2.0
63
+ },
64
+ "CARD#negative": {
65
+ "precision": 1.0,
66
+ "recall": 0.14285714285714285,
67
+ "f1-score": 0.25,
68
+ "support": 7.0
69
+ },
70
+ "CARD#positive": {
71
+ "precision": 0.0,
72
+ "recall": 0.0,
73
+ "f1-score": 0.0,
74
+ "support": 1.0
75
+ },
76
+ "CUSTOMER_SUPPORT#negative": {
77
+ "precision": 0.4931506849315068,
78
+ "recall": 0.96,
79
+ "f1-score": 0.6515837104072398,
80
+ "support": 75.0
81
+ },
82
+ "CUSTOMER_SUPPORT#neutral": {
83
+ "precision": 0.0,
84
+ "recall": 0.0,
85
+ "f1-score": 0.0,
86
+ "support": 1.0
87
+ },
88
+ "CUSTOMER_SUPPORT#positive": {
89
+ "precision": 0.8641975308641975,
90
+ "recall": 0.8974358974358975,
91
+ "f1-score": 0.8805031446540881,
92
+ "support": 78.0
93
+ },
94
+ "DISCOUNT#negative": {
95
+ "precision": 0.0,
96
+ "recall": 0.0,
97
+ "f1-score": 0.0,
98
+ "support": 5.0
99
+ },
100
+ "DISCOUNT#neutral": {
101
+ "precision": 0.0,
102
+ "recall": 0.0,
103
+ "f1-score": 0.0,
104
+ "support": 1.0
105
+ },
106
+ "DISCOUNT#positive": {
107
+ "precision": 0.0,
108
+ "recall": 0.0,
109
+ "f1-score": 0.0,
110
+ "support": 0.0
111
+ },
112
+ "INTEREST_RATE#negative": {
113
+ "precision": 0.5555555555555556,
114
+ "recall": 0.5,
115
+ "f1-score": 0.5263157894736842,
116
+ "support": 10.0
117
+ },
118
+ "INTERNET_BANKING#negative": {
119
+ "precision": 0.0,
120
+ "recall": 0.0,
121
+ "f1-score": 0.0,
122
+ "support": 12.0
123
+ },
124
+ "INTERNET_BANKING#positive": {
125
+ "precision": 0.0,
126
+ "recall": 0.0,
127
+ "f1-score": 0.0,
128
+ "support": 1.0
129
+ },
130
+ "LOAN#negative": {
131
+ "precision": 0.875,
132
+ "recall": 0.5384615384615384,
133
+ "f1-score": 0.6666666666666666,
134
+ "support": 13.0
135
+ },
136
+ "MONEY_TRANSFER#negative": {
137
+ "precision": 0.0,
138
+ "recall": 0.0,
139
+ "f1-score": 0.0,
140
+ "support": 5.0
141
+ },
142
+ "OTHER#negative": {
143
+ "precision": 0.0,
144
+ "recall": 0.0,
145
+ "f1-score": 0.0,
146
+ "support": 10.0
147
+ },
148
+ "OTHER#neutral": {
149
+ "precision": 0.0,
150
+ "recall": 0.0,
151
+ "f1-score": 0.0,
152
+ "support": 1.0
153
+ },
154
+ "OTHER#positive": {
155
+ "precision": 0.6666666666666666,
156
+ "recall": 0.5,
157
+ "f1-score": 0.5714285714285714,
158
+ "support": 4.0
159
+ },
160
+ "PAYMENT#positive": {
161
+ "precision": 0.0,
162
+ "recall": 0.0,
163
+ "f1-score": 0.0,
164
+ "support": 3.0
165
+ },
166
+ "PROMOTION#negative": {
167
+ "precision": 0.0,
168
+ "recall": 0.0,
169
+ "f1-score": 0.0,
170
+ "support": 4.0
171
+ },
172
+ "PROMOTION#neutral": {
173
+ "precision": 0.0,
174
+ "recall": 0.0,
175
+ "f1-score": 0.0,
176
+ "support": 1.0
177
+ },
178
+ "PROMOTION#positive": {
179
+ "precision": 0.3333333333333333,
180
+ "recall": 0.2,
181
+ "f1-score": 0.25,
182
+ "support": 5.0
183
+ },
184
+ "SAVING#negative": {
185
+ "precision": 0.0,
186
+ "recall": 0.0,
187
+ "f1-score": 0.0,
188
+ "support": 1.0
189
+ },
190
+ "SAVING#positive": {
191
+ "precision": 0.0,
192
+ "recall": 0.0,
193
+ "f1-score": 0.0,
194
+ "support": 2.0
195
+ },
196
+ "SECURITY#negative": {
197
+ "precision": 0.0,
198
+ "recall": 0.0,
199
+ "f1-score": 0.0,
200
+ "support": 1.0
201
+ },
202
+ "SECURITY#neutral": {
203
+ "precision": 0.0,
204
+ "recall": 0.0,
205
+ "f1-score": 0.0,
206
+ "support": 1.0
207
+ },
208
+ "TRADEMARK#negative": {
209
+ "precision": 0.0,
210
+ "recall": 0.0,
211
+ "f1-score": 0.0,
212
+ "support": 14.0
213
+ },
214
+ "TRADEMARK#positive": {
215
+ "precision": 0.8936170212765957,
216
+ "recall": 0.9130434782608695,
217
+ "f1-score": 0.9032258064516129,
218
+ "support": 138.0
219
+ },
220
+ "accuracy": 0.7171717171717171,
221
+ "macro avg": {
222
+ "precision": 0.21042669602325392,
223
+ "recall": 0.17228881692649806,
224
+ "f1-score": 0.1740638403363653,
225
+ "support": 396.0
226
+ },
227
+ "weighted avg": {
228
+ "precision": 0.6464059257634583,
229
+ "recall": 0.7171717171717171,
230
+ "f1-score": 0.6601230396489957,
231
+ "support": 396.0
232
+ }
233
+ },
234
+ "confusion_matrix": [
235
+ [
236
+ 0,
237
+ 0,
238
+ 0,
239
+ 0,
240
+ 1,
241
+ 0,
242
+ 1,
243
+ 0,
244
+ 0,
245
+ 0,
246
+ 0,
247
+ 0,
248
+ 0,
249
+ 0,
250
+ 0,
251
+ 0,
252
+ 0,
253
+ 0,
254
+ 0,
255
+ 0,
256
+ 0,
257
+ 0,
258
+ 0,
259
+ 0,
260
+ 0,
261
+ 0,
262
+ 0,
263
+ 0,
264
+ 0,
265
+ 0,
266
+ 0,
267
+ 0,
268
+ 0,
269
+ 0,
270
+ 0
271
+ ],
272
+ [
273
+ 0,
274
+ 1,
275
+ 0,
276
+ 0,
277
+ 5,
278
+ 0,
279
+ 0,
280
+ 0,
281
+ 0,
282
+ 0,
283
+ 1,
284
+ 0,
285
+ 0,
286
+ 0,
287
+ 0,
288
+ 0,
289
+ 0,
290
+ 0,
291
+ 0,
292
+ 0,
293
+ 0,
294
+ 0,
295
+ 0,
296
+ 0,
297
+ 0,
298
+ 0,
299
+ 0,
300
+ 0,
301
+ 0,
302
+ 0,
303
+ 0,
304
+ 0,
305
+ 0,
306
+ 0,
307
+ 0
308
+ ],
309
+ [
310
+ 0,
311
+ 0,
312
+ 0,
313
+ 0,
314
+ 0,
315
+ 0,
316
+ 0,
317
+ 0,
318
+ 0,
319
+ 0,
320
+ 0,
321
+ 0,
322
+ 0,
323
+ 0,
324
+ 0,
325
+ 0,
326
+ 0,
327
+ 0,
328
+ 0,
329
+ 0,
330
+ 0,
331
+ 0,
332
+ 0,
333
+ 0,
334
+ 0,
335
+ 0,
336
+ 0,
337
+ 0,
338
+ 0,
339
+ 0,
340
+ 0,
341
+ 0,
342
+ 0,
343
+ 0,
344
+ 0
345
+ ],
346
+ [
347
+ 0,
348
+ 0,
349
+ 0,
350
+ 0,
351
+ 0,
352
+ 0,
353
+ 0,
354
+ 0,
355
+ 0,
356
+ 0,
357
+ 0,
358
+ 0,
359
+ 0,
360
+ 0,
361
+ 0,
362
+ 0,
363
+ 0,
364
+ 0,
365
+ 0,
366
+ 0,
367
+ 0,
368
+ 0,
369
+ 0,
370
+ 0,
371
+ 0,
372
+ 0,
373
+ 0,
374
+ 0,
375
+ 0,
376
+ 0,
377
+ 0,
378
+ 0,
379
+ 0,
380
+ 0,
381
+ 1
382
+ ],
383
+ [
384
+ 0,
385
+ 0,
386
+ 0,
387
+ 0,
388
+ 72,
389
+ 0,
390
+ 1,
391
+ 0,
392
+ 0,
393
+ 0,
394
+ 1,
395
+ 0,
396
+ 0,
397
+ 0,
398
+ 0,
399
+ 0,
400
+ 1,
401
+ 0,
402
+ 0,
403
+ 0,
404
+ 0,
405
+ 0,
406
+ 0,
407
+ 0,
408
+ 0,
409
+ 0,
410
+ 0,
411
+ 0,
412
+ 0,
413
+ 0,
414
+ 0,
415
+ 0,
416
+ 0,
417
+ 0,
418
+ 0
419
+ ],
420
+ [
421
+ 0,
422
+ 0,
423
+ 0,
424
+ 0,
425
+ 1,
426
+ 0,
427
+ 0,
428
+ 0,
429
+ 0,
430
+ 0,
431
+ 0,
432
+ 0,
433
+ 0,
434
+ 0,
435
+ 0,
436
+ 0,
437
+ 0,
438
+ 0,
439
+ 0,
440
+ 0,
441
+ 0,
442
+ 0,
443
+ 0,
444
+ 0,
445
+ 0,
446
+ 0,
447
+ 0,
448
+ 0,
449
+ 0,
450
+ 0,
451
+ 0,
452
+ 0,
453
+ 0,
454
+ 0,
455
+ 0
456
+ ],
457
+ [
458
+ 0,
459
+ 0,
460
+ 0,
461
+ 0,
462
+ 6,
463
+ 0,
464
+ 70,
465
+ 0,
466
+ 0,
467
+ 0,
468
+ 0,
469
+ 0,
470
+ 0,
471
+ 0,
472
+ 0,
473
+ 0,
474
+ 0,
475
+ 0,
476
+ 0,
477
+ 0,
478
+ 0,
479
+ 0,
480
+ 0,
481
+ 0,
482
+ 0,
483
+ 0,
484
+ 0,
485
+ 0,
486
+ 0,
487
+ 0,
488
+ 0,
489
+ 0,
490
+ 0,
491
+ 0,
492
+ 2
493
+ ],
494
+ [
495
+ 0,
496
+ 0,
497
+ 0,
498
+ 0,
499
+ 5,
500
+ 0,
501
+ 0,
502
+ 0,
503
+ 0,
504
+ 0,
505
+ 0,
506
+ 0,
507
+ 0,
508
+ 0,
509
+ 0,
510
+ 0,
511
+ 0,
512
+ 0,
513
+ 0,
514
+ 0,
515
+ 0,
516
+ 0,
517
+ 0,
518
+ 0,
519
+ 0,
520
+ 0,
521
+ 0,
522
+ 0,
523
+ 0,
524
+ 0,
525
+ 0,
526
+ 0,
527
+ 0,
528
+ 0,
529
+ 0
530
+ ],
531
+ [
532
+ 0,
533
+ 0,
534
+ 0,
535
+ 0,
536
+ 1,
537
+ 0,
538
+ 0,
539
+ 0,
540
+ 0,
541
+ 0,
542
+ 0,
543
+ 0,
544
+ 0,
545
+ 0,
546
+ 0,
547
+ 0,
548
+ 0,
549
+ 0,
550
+ 0,
551
+ 0,
552
+ 0,
553
+ 0,
554
+ 0,
555
+ 0,
556
+ 0,
557
+ 0,
558
+ 0,
559
+ 0,
560
+ 0,
561
+ 0,
562
+ 0,
563
+ 0,
564
+ 0,
565
+ 0,
566
+ 0
567
+ ],
568
+ [
569
+ 0,
570
+ 0,
571
+ 0,
572
+ 0,
573
+ 0,
574
+ 0,
575
+ 0,
576
+ 0,
577
+ 0,
578
+ 0,
579
+ 0,
580
+ 0,
581
+ 0,
582
+ 0,
583
+ 0,
584
+ 0,
585
+ 0,
586
+ 0,
587
+ 0,
588
+ 0,
589
+ 0,
590
+ 0,
591
+ 0,
592
+ 0,
593
+ 0,
594
+ 0,
595
+ 0,
596
+ 0,
597
+ 0,
598
+ 0,
599
+ 0,
600
+ 0,
601
+ 0,
602
+ 0,
603
+ 0
604
+ ],
605
+ [
606
+ 0,
607
+ 0,
608
+ 0,
609
+ 0,
610
+ 4,
611
+ 0,
612
+ 0,
613
+ 0,
614
+ 0,
615
+ 0,
616
+ 5,
617
+ 0,
618
+ 0,
619
+ 0,
620
+ 0,
621
+ 0,
622
+ 0,
623
+ 0,
624
+ 0,
625
+ 0,
626
+ 0,
627
+ 0,
628
+ 0,
629
+ 0,
630
+ 0,
631
+ 0,
632
+ 0,
633
+ 0,
634
+ 0,
635
+ 0,
636
+ 0,
637
+ 0,
638
+ 0,
639
+ 0,
640
+ 1
641
+ ],
642
+ [
643
+ 0,
644
+ 0,
645
+ 0,
646
+ 0,
647
+ 0,
648
+ 0,
649
+ 0,
650
+ 0,
651
+ 0,
652
+ 0,
653
+ 0,
654
+ 0,
655
+ 0,
656
+ 0,
657
+ 0,
658
+ 0,
659
+ 0,
660
+ 0,
661
+ 0,
662
+ 0,
663
+ 0,
664
+ 0,
665
+ 0,
666
+ 0,
667
+ 0,
668
+ 0,
669
+ 0,
670
+ 0,
671
+ 0,
672
+ 0,
673
+ 0,
674
+ 0,
675
+ 0,
676
+ 0,
677
+ 0
678
+ ],
679
+ [
680
+ 0,
681
+ 0,
682
+ 0,
683
+ 0,
684
+ 0,
685
+ 0,
686
+ 0,
687
+ 0,
688
+ 0,
689
+ 0,
690
+ 0,
691
+ 0,
692
+ 0,
693
+ 0,
694
+ 0,
695
+ 0,
696
+ 0,
697
+ 0,
698
+ 0,
699
+ 0,
700
+ 0,
701
+ 0,
702
+ 0,
703
+ 0,
704
+ 0,
705
+ 0,
706
+ 0,
707
+ 0,
708
+ 0,
709
+ 0,
710
+ 0,
711
+ 0,
712
+ 0,
713
+ 0,
714
+ 0
715
+ ],
716
+ [
717
+ 0,
718
+ 0,
719
+ 0,
720
+ 0,
721
+ 12,
722
+ 0,
723
+ 0,
724
+ 0,
725
+ 0,
726
+ 0,
727
+ 0,
728
+ 0,
729
+ 0,
730
+ 0,
731
+ 0,
732
+ 0,
733
+ 0,
734
+ 0,
735
+ 0,
736
+ 0,
737
+ 0,
738
+ 0,
739
+ 0,
740
+ 0,
741
+ 0,
742
+ 0,
743
+ 0,
744
+ 0,
745
+ 0,
746
+ 0,
747
+ 0,
748
+ 0,
749
+ 0,
750
+ 0,
751
+ 0
752
+ ],
753
+ [
754
+ 0,
755
+ 0,
756
+ 0,
757
+ 0,
758
+ 0,
759
+ 0,
760
+ 0,
761
+ 0,
762
+ 0,
763
+ 0,
764
+ 0,
765
+ 0,
766
+ 0,
767
+ 0,
768
+ 0,
769
+ 0,
770
+ 0,
771
+ 0,
772
+ 0,
773
+ 0,
774
+ 0,
775
+ 0,
776
+ 0,
777
+ 0,
778
+ 0,
779
+ 0,
780
+ 0,
781
+ 0,
782
+ 0,
783
+ 0,
784
+ 0,
785
+ 0,
786
+ 0,
787
+ 0,
788
+ 0
789
+ ],
790
+ [
791
+ 0,
792
+ 0,
793
+ 0,
794
+ 0,
795
+ 1,
796
+ 0,
797
+ 0,
798
+ 0,
799
+ 0,
800
+ 0,
801
+ 0,
802
+ 0,
803
+ 0,
804
+ 0,
805
+ 0,
806
+ 0,
807
+ 0,
808
+ 0,
809
+ 0,
810
+ 0,
811
+ 0,
812
+ 0,
813
+ 0,
814
+ 0,
815
+ 0,
816
+ 0,
817
+ 0,
818
+ 0,
819
+ 0,
820
+ 0,
821
+ 0,
822
+ 0,
823
+ 0,
824
+ 0,
825
+ 0
826
+ ],
827
+ [
828
+ 0,
829
+ 0,
830
+ 0,
831
+ 0,
832
+ 4,
833
+ 0,
834
+ 0,
835
+ 0,
836
+ 0,
837
+ 0,
838
+ 0,
839
+ 0,
840
+ 0,
841
+ 0,
842
+ 0,
843
+ 0,
844
+ 7,
845
+ 0,
846
+ 0,
847
+ 0,
848
+ 0,
849
+ 0,
850
+ 0,
851
+ 0,
852
+ 0,
853
+ 0,
854
+ 0,
855
+ 0,
856
+ 0,
857
+ 0,
858
+ 0,
859
+ 0,
860
+ 0,
861
+ 2,
862
+ 0
863
+ ],
864
+ [
865
+ 0,
866
+ 0,
867
+ 0,
868
+ 0,
869
+ 0,
870
+ 0,
871
+ 0,
872
+ 0,
873
+ 0,
874
+ 0,
875
+ 0,
876
+ 0,
877
+ 0,
878
+ 0,
879
+ 0,
880
+ 0,
881
+ 0,
882
+ 0,
883
+ 0,
884
+ 0,
885
+ 0,
886
+ 0,
887
+ 0,
888
+ 0,
889
+ 0,
890
+ 0,
891
+ 0,
892
+ 0,
893
+ 0,
894
+ 0,
895
+ 0,
896
+ 0,
897
+ 0,
898
+ 0,
899
+ 0
900
+ ],
901
+ [
902
+ 0,
903
+ 0,
904
+ 0,
905
+ 0,
906
+ 3,
907
+ 0,
908
+ 0,
909
+ 0,
910
+ 0,
911
+ 0,
912
+ 2,
913
+ 0,
914
+ 0,
915
+ 0,
916
+ 0,
917
+ 0,
918
+ 0,
919
+ 0,
920
+ 0,
921
+ 0,
922
+ 0,
923
+ 0,
924
+ 0,
925
+ 0,
926
+ 0,
927
+ 0,
928
+ 0,
929
+ 0,
930
+ 0,
931
+ 0,
932
+ 0,
933
+ 0,
934
+ 0,
935
+ 0,
936
+ 0
937
+ ],
938
+ [
939
+ 0,
940
+ 0,
941
+ 0,
942
+ 0,
943
+ 0,
944
+ 0,
945
+ 0,
946
+ 0,
947
+ 0,
948
+ 0,
949
+ 0,
950
+ 0,
951
+ 0,
952
+ 0,
953
+ 0,
954
+ 0,
955
+ 0,
956
+ 0,
957
+ 0,
958
+ 0,
959
+ 0,
960
+ 0,
961
+ 0,
962
+ 0,
963
+ 0,
964
+ 0,
965
+ 0,
966
+ 0,
967
+ 0,
968
+ 0,
969
+ 0,
970
+ 0,
971
+ 0,
972
+ 0,
973
+ 0
974
+ ],
975
+ [
976
+ 0,
977
+ 0,
978
+ 0,
979
+ 0,
980
+ 8,
981
+ 0,
982
+ 0,
983
+ 0,
984
+ 0,
985
+ 1,
986
+ 0,
987
+ 0,
988
+ 0,
989
+ 0,
990
+ 0,
991
+ 0,
992
+ 0,
993
+ 0,
994
+ 0,
995
+ 0,
996
+ 0,
997
+ 0,
998
+ 0,
999
+ 0,
1000
+ 0,
1001
+ 0,
1002
+ 0,
1003
+ 0,
1004
+ 0,
1005
+ 0,
1006
+ 0,
1007
+ 0,
1008
+ 0,
1009
+ 1,
1010
+ 0
1011
+ ],
1012
+ [
1013
+ 0,
1014
+ 0,
1015
+ 0,
1016
+ 0,
1017
+ 1,
1018
+ 0,
1019
+ 0,
1020
+ 0,
1021
+ 0,
1022
+ 0,
1023
+ 0,
1024
+ 0,
1025
+ 0,
1026
+ 0,
1027
+ 0,
1028
+ 0,
1029
+ 0,
1030
+ 0,
1031
+ 0,
1032
+ 0,
1033
+ 0,
1034
+ 0,
1035
+ 0,
1036
+ 0,
1037
+ 0,
1038
+ 0,
1039
+ 0,
1040
+ 0,
1041
+ 0,
1042
+ 0,
1043
+ 0,
1044
+ 0,
1045
+ 0,
1046
+ 0,
1047
+ 0
1048
+ ],
1049
+ [
1050
+ 0,
1051
+ 0,
1052
+ 0,
1053
+ 0,
1054
+ 1,
1055
+ 0,
1056
+ 0,
1057
+ 0,
1058
+ 0,
1059
+ 0,
1060
+ 0,
1061
+ 0,
1062
+ 0,
1063
+ 0,
1064
+ 0,
1065
+ 0,
1066
+ 0,
1067
+ 0,
1068
+ 0,
1069
+ 0,
1070
+ 0,
1071
+ 0,
1072
+ 2,
1073
+ 0,
1074
+ 0,
1075
+ 0,
1076
+ 0,
1077
+ 0,
1078
+ 0,
1079
+ 0,
1080
+ 0,
1081
+ 0,
1082
+ 0,
1083
+ 0,
1084
+ 1
1085
+ ],
1086
+ [
1087
+ 0,
1088
+ 0,
1089
+ 0,
1090
+ 0,
1091
+ 0,
1092
+ 0,
1093
+ 0,
1094
+ 0,
1095
+ 0,
1096
+ 0,
1097
+ 0,
1098
+ 0,
1099
+ 0,
1100
+ 0,
1101
+ 0,
1102
+ 0,
1103
+ 0,
1104
+ 0,
1105
+ 0,
1106
+ 0,
1107
+ 0,
1108
+ 0,
1109
+ 0,
1110
+ 0,
1111
+ 0,
1112
+ 0,
1113
+ 0,
1114
+ 0,
1115
+ 0,
1116
+ 0,
1117
+ 0,
1118
+ 0,
1119
+ 0,
1120
+ 0,
1121
+ 0
1122
+ ],
1123
+ [
1124
+ 0,
1125
+ 0,
1126
+ 0,
1127
+ 0,
1128
+ 0,
1129
+ 0,
1130
+ 2,
1131
+ 0,
1132
+ 0,
1133
+ 0,
1134
+ 0,
1135
+ 0,
1136
+ 0,
1137
+ 0,
1138
+ 0,
1139
+ 0,
1140
+ 0,
1141
+ 0,
1142
+ 0,
1143
+ 0,
1144
+ 0,
1145
+ 0,
1146
+ 0,
1147
+ 0,
1148
+ 0,
1149
+ 0,
1150
+ 0,
1151
+ 0,
1152
+ 0,
1153
+ 0,
1154
+ 0,
1155
+ 0,
1156
+ 0,
1157
+ 0,
1158
+ 1
1159
+ ],
1160
+ [
1161
+ 0,
1162
+ 0,
1163
+ 0,
1164
+ 0,
1165
+ 3,
1166
+ 0,
1167
+ 0,
1168
+ 0,
1169
+ 0,
1170
+ 0,
1171
+ 0,
1172
+ 0,
1173
+ 0,
1174
+ 0,
1175
+ 0,
1176
+ 0,
1177
+ 0,
1178
+ 0,
1179
+ 0,
1180
+ 0,
1181
+ 0,
1182
+ 0,
1183
+ 0,
1184
+ 0,
1185
+ 0,
1186
+ 0,
1187
+ 0,
1188
+ 1,
1189
+ 0,
1190
+ 0,
1191
+ 0,
1192
+ 0,
1193
+ 0,
1194
+ 0,
1195
+ 0
1196
+ ],
1197
+ [
1198
+ 0,
1199
+ 0,
1200
+ 0,
1201
+ 0,
1202
+ 1,
1203
+ 0,
1204
+ 0,
1205
+ 0,
1206
+ 0,
1207
+ 0,
1208
+ 0,
1209
+ 0,
1210
+ 0,
1211
+ 0,
1212
+ 0,
1213
+ 0,
1214
+ 0,
1215
+ 0,
1216
+ 0,
1217
+ 0,
1218
+ 0,
1219
+ 0,
1220
+ 0,
1221
+ 0,
1222
+ 0,
1223
+ 0,
1224
+ 0,
1225
+ 0,
1226
+ 0,
1227
+ 0,
1228
+ 0,
1229
+ 0,
1230
+ 0,
1231
+ 0,
1232
+ 0
1233
+ ],
1234
+ [
1235
+ 0,
1236
+ 0,
1237
+ 0,
1238
+ 0,
1239
+ 0,
1240
+ 0,
1241
+ 0,
1242
+ 0,
1243
+ 0,
1244
+ 0,
1245
+ 0,
1246
+ 0,
1247
+ 0,
1248
+ 0,
1249
+ 0,
1250
+ 0,
1251
+ 0,
1252
+ 0,
1253
+ 0,
1254
+ 0,
1255
+ 0,
1256
+ 0,
1257
+ 1,
1258
+ 0,
1259
+ 0,
1260
+ 0,
1261
+ 0,
1262
+ 1,
1263
+ 0,
1264
+ 0,
1265
+ 0,
1266
+ 0,
1267
+ 0,
1268
+ 0,
1269
+ 3
1270
+ ],
1271
+ [
1272
+ 0,
1273
+ 0,
1274
+ 0,
1275
+ 0,
1276
+ 1,
1277
+ 0,
1278
+ 0,
1279
+ 0,
1280
+ 0,
1281
+ 0,
1282
+ 0,
1283
+ 0,
1284
+ 0,
1285
+ 0,
1286
+ 0,
1287
+ 0,
1288
+ 0,
1289
+ 0,
1290
+ 0,
1291
+ 0,
1292
+ 0,
1293
+ 0,
1294
+ 0,
1295
+ 0,
1296
+ 0,
1297
+ 0,
1298
+ 0,
1299
+ 0,
1300
+ 0,
1301
+ 0,
1302
+ 0,
1303
+ 0,
1304
+ 0,
1305
+ 0,
1306
+ 0
1307
+ ],
1308
+ [
1309
+ 0,
1310
+ 0,
1311
+ 0,
1312
+ 0,
1313
+ 0,
1314
+ 0,
1315
+ 0,
1316
+ 0,
1317
+ 0,
1318
+ 0,
1319
+ 0,
1320
+ 0,
1321
+ 0,
1322
+ 0,
1323
+ 0,
1324
+ 0,
1325
+ 0,
1326
+ 0,
1327
+ 0,
1328
+ 0,
1329
+ 0,
1330
+ 0,
1331
+ 0,
1332
+ 0,
1333
+ 0,
1334
+ 0,
1335
+ 0,
1336
+ 0,
1337
+ 0,
1338
+ 0,
1339
+ 0,
1340
+ 0,
1341
+ 0,
1342
+ 0,
1343
+ 0
1344
+ ],
1345
+ [
1346
+ 0,
1347
+ 0,
1348
+ 0,
1349
+ 0,
1350
+ 0,
1351
+ 0,
1352
+ 0,
1353
+ 0,
1354
+ 0,
1355
+ 0,
1356
+ 0,
1357
+ 0,
1358
+ 0,
1359
+ 0,
1360
+ 0,
1361
+ 0,
1362
+ 0,
1363
+ 0,
1364
+ 0,
1365
+ 0,
1366
+ 0,
1367
+ 0,
1368
+ 0,
1369
+ 0,
1370
+ 0,
1371
+ 0,
1372
+ 0,
1373
+ 0,
1374
+ 0,
1375
+ 0,
1376
+ 0,
1377
+ 0,
1378
+ 0,
1379
+ 0,
1380
+ 2
1381
+ ],
1382
+ [
1383
+ 0,
1384
+ 0,
1385
+ 0,
1386
+ 0,
1387
+ 1,
1388
+ 0,
1389
+ 0,
1390
+ 0,
1391
+ 0,
1392
+ 0,
1393
+ 0,
1394
+ 0,
1395
+ 0,
1396
+ 0,
1397
+ 0,
1398
+ 0,
1399
+ 0,
1400
+ 0,
1401
+ 0,
1402
+ 0,
1403
+ 0,
1404
+ 0,
1405
+ 0,
1406
+ 0,
1407
+ 0,
1408
+ 0,
1409
+ 0,
1410
+ 0,
1411
+ 0,
1412
+ 0,
1413
+ 0,
1414
+ 0,
1415
+ 0,
1416
+ 0,
1417
+ 0
1418
+ ],
1419
+ [
1420
+ 0,
1421
+ 0,
1422
+ 0,
1423
+ 0,
1424
+ 0,
1425
+ 0,
1426
+ 0,
1427
+ 0,
1428
+ 0,
1429
+ 0,
1430
+ 0,
1431
+ 0,
1432
+ 0,
1433
+ 0,
1434
+ 0,
1435
+ 0,
1436
+ 0,
1437
+ 0,
1438
+ 0,
1439
+ 0,
1440
+ 0,
1441
+ 0,
1442
+ 0,
1443
+ 0,
1444
+ 0,
1445
+ 0,
1446
+ 0,
1447
+ 0,
1448
+ 0,
1449
+ 0,
1450
+ 0,
1451
+ 0,
1452
+ 0,
1453
+ 0,
1454
+ 0
1455
+ ],
1456
+ [
1457
+ 0,
1458
+ 0,
1459
+ 0,
1460
+ 0,
1461
+ 10,
1462
+ 0,
1463
+ 0,
1464
+ 0,
1465
+ 0,
1466
+ 0,
1467
+ 0,
1468
+ 0,
1469
+ 0,
1470
+ 0,
1471
+ 0,
1472
+ 0,
1473
+ 0,
1474
+ 0,
1475
+ 0,
1476
+ 0,
1477
+ 0,
1478
+ 0,
1479
+ 0,
1480
+ 0,
1481
+ 0,
1482
+ 0,
1483
+ 0,
1484
+ 0,
1485
+ 0,
1486
+ 0,
1487
+ 0,
1488
+ 0,
1489
+ 0,
1490
+ 0,
1491
+ 4
1492
+ ],
1493
+ [
1494
+ 0,
1495
+ 0,
1496
+ 0,
1497
+ 0,
1498
+ 4,
1499
+ 0,
1500
+ 7,
1501
+ 0,
1502
+ 0,
1503
+ 0,
1504
+ 0,
1505
+ 0,
1506
+ 0,
1507
+ 0,
1508
+ 0,
1509
+ 0,
1510
+ 0,
1511
+ 0,
1512
+ 0,
1513
+ 0,
1514
+ 0,
1515
+ 0,
1516
+ 0,
1517
+ 0,
1518
+ 0,
1519
+ 0,
1520
+ 0,
1521
+ 1,
1522
+ 0,
1523
+ 0,
1524
+ 0,
1525
+ 0,
1526
+ 0,
1527
+ 0,
1528
+ 126
1529
+ ]
1530
+ ]
1531
+ }
runs/20250928_131716/models/UTS2017_Bank_AspectSentiment_SVC_feat20k_ngram1-2.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:502ef69d34545f9ad39573ed199b1ef331cb6fa17eb5977d3841e7596125b2a5
3
+ size 2154772
runs/20250928_131716/models/labels.txt ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ACCOUNT#negative
2
+ CARD#negative
3
+ CARD#neutral
4
+ CARD#positive
5
+ CUSTOMER_SUPPORT#negative
6
+ CUSTOMER_SUPPORT#neutral
7
+ CUSTOMER_SUPPORT#positive
8
+ DISCOUNT#negative
9
+ DISCOUNT#neutral
10
+ DISCOUNT#positive
11
+ INTEREST_RATE#negative
12
+ INTEREST_RATE#neutral
13
+ INTEREST_RATE#positive
14
+ INTERNET_BANKING#negative
15
+ INTERNET_BANKING#neutral
16
+ INTERNET_BANKING#positive
17
+ LOAN#negative
18
+ LOAN#positive
19
+ MONEY_TRANSFER#negative
20
+ MONEY_TRANSFER#positive
21
+ OTHER#negative
22
+ OTHER#neutral
23
+ OTHER#positive
24
+ PAYMENT#negative
25
+ PAYMENT#positive
26
+ PROMOTION#negative
27
+ PROMOTION#neutral
28
+ PROMOTION#positive
29
+ SAVING#negative
30
+ SAVING#neutral
31
+ SAVING#positive
32
+ SECURITY#neutral
33
+ SECURITY#positive
34
+ TRADEMARK#negative
35
+ TRADEMARK#positive
runs/20250928_131716/models/model.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:502ef69d34545f9ad39573ed199b1ef331cb6fa17eb5977d3841e7596125b2a5
3
+ size 2154772
runs/20250928_131716/training.log ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-09-28 13:17:16,505 - INFO - Starting training run: 20250928_131716
2
+ 2025-09-28 13:17:16,505 - INFO - Model: svc_linear
3
+ 2025-09-28 13:17:16,505 - INFO - Max features: 20000
4
+ 2025-09-28 13:17:16,505 - INFO - N-gram range: (1, 2)
5
+ 2025-09-28 13:17:16,505 - INFO - Loading UTS2017_Bank aspect sentiment dataset...
6
+ 2025-09-28 13:17:21,253 - INFO - Train samples: 1581
7
+ 2025-09-28 13:17:21,253 - INFO - Test samples: 396
8
+ 2025-09-28 13:17:21,253 - INFO - Unique labels: 35
9
+ 2025-09-28 13:17:21,253 - INFO - Label distribution (train): {np.str_('ACCOUNT#negative'): np.int64(3), np.str_('CARD#negative'): np.int64(47), np.str_('CARD#neutral'): np.int64(1), np.str_('CARD#positive'): np.int64(10), np.str_('CUSTOMER_SUPPORT#negative'): np.int64(288), np.str_('CUSTOMER_SUPPORT#neutral'): np.int64(4), np.str_('CUSTOMER_SUPPORT#positive'): np.int64(328), np.str_('DISCOUNT#negative'): np.int64(13), np.str_('DISCOUNT#neutral'): np.int64(3), np.str_('DISCOUNT#positive'): np.int64(19), np.str_('INTEREST_RATE#negative'): np.int64(45), np.str_('INTEREST_RATE#neutral'): np.int64(1), np.str_('INTEREST_RATE#positive'): np.int64(4), np.str_('INTERNET_BANKING#negative'): np.int64(36), np.str_('INTERNET_BANKING#neutral'): np.int64(2), np.str_('INTERNET_BANKING#positive'): np.int64(19), np.str_('LOAN#negative'): np.int64(48), np.str_('LOAN#positive'): np.int64(13), np.str_('MONEY_TRANSFER#negative'): np.int64(24), np.str_('MONEY_TRANSFER#positive'): np.int64(5), np.str_('OTHER#negative'): np.int64(25), np.str_('OTHER#neutral'): np.int64(3), np.str_('OTHER#positive'): np.int64(26), np.str_('PAYMENT#negative'): np.int64(4), np.str_('PAYMENT#positive'): np.int64(8), np.str_('PROMOTION#negative'): np.int64(13), np.str_('PROMOTION#neutral'): np.int64(2), np.str_('PROMOTION#positive'): np.int64(28), np.str_('SAVING#negative'): np.int64(5), np.str_('SAVING#neutral'): np.int64(1), np.str_('SAVING#positive'): np.int64(4), np.str_('SECURITY#neutral'): np.int64(1), np.str_('SECURITY#positive'): np.int64(1), np.str_('TRADEMARK#negative'): np.int64(33), np.str_('TRADEMARK#positive'): np.int64(514)}
10
+ 2025-09-28 13:17:21,253 - INFO - Label distribution (test): {np.str_('ACCOUNT#negative'): np.int64(2), np.str_('CARD#negative'): np.int64(7), np.str_('CARD#neutral'): np.int64(0), np.str_('CARD#positive'): np.int64(1), np.str_('CUSTOMER_SUPPORT#negative'): np.int64(75), np.str_('CUSTOMER_SUPPORT#neutral'): np.int64(1), np.str_('CUSTOMER_SUPPORT#positive'): np.int64(78), np.str_('DISCOUNT#negative'): np.int64(5), np.str_('DISCOUNT#neutral'): np.int64(1), np.str_('DISCOUNT#positive'): np.int64(0), np.str_('INTEREST_RATE#negative'): np.int64(10), np.str_('INTEREST_RATE#neutral'): np.int64(0), np.str_('INTEREST_RATE#positive'): np.int64(0), np.str_('INTERNET_BANKING#negative'): np.int64(12), np.str_('INTERNET_BANKING#neutral'): np.int64(0), np.str_('INTERNET_BANKING#positive'): np.int64(1), np.str_('LOAN#negative'): np.int64(13), np.str_('LOAN#positive'): np.int64(0), np.str_('MONEY_TRANSFER#negative'): np.int64(5), np.str_('MONEY_TRANSFER#positive'): np.int64(0), np.str_('OTHER#negative'): np.int64(10), np.str_('OTHER#neutral'): np.int64(1), np.str_('OTHER#positive'): np.int64(4), np.str_('PAYMENT#negative'): np.int64(0), np.str_('PAYMENT#positive'): np.int64(3), np.str_('PROMOTION#negative'): np.int64(4), np.str_('PROMOTION#neutral'): np.int64(1), np.str_('PROMOTION#positive'): np.int64(5), np.str_('SAVING#negative'): np.int64(1), np.str_('SAVING#neutral'): np.int64(0), np.str_('SAVING#positive'): np.int64(2), np.str_('SECURITY#neutral'): np.int64(1), np.str_('SECURITY#positive'): np.int64(0), np.str_('TRADEMARK#negative'): np.int64(14), np.str_('TRADEMARK#positive'): np.int64(138)}
11
+ 2025-09-28 13:17:21,253 - INFO - Selected classifier: SVC
12
+ 2025-09-28 13:17:21,253 - INFO - ============================================================
13
+ 2025-09-28 13:17:21,253 - INFO - Training: UTS2017_Bank_AspectSentiment_SVC_feat20k_ngram1-2
14
+ 2025-09-28 13:17:21,253 - INFO - ============================================================
15
+ 2025-09-28 13:17:21,253 - INFO - Creating pipeline with max_features=20000, ngram_range=(1, 2)
16
+ 2025-09-28 13:17:21,253 - INFO - Training model...
17
+ 2025-09-28 13:17:28,959 - INFO - Training completed in 7.71 seconds
18
+ 2025-09-28 13:17:28,959 - INFO - Evaluating on training set...
19
+ 2025-09-28 13:17:29,420 - INFO - Training accuracy: 0.9431
20
+ 2025-09-28 13:17:29,420 - INFO - Evaluating on test set...
21
+ 2025-09-28 13:17:29,530 - INFO - Test accuracy: 0.7172
22
+ 2025-09-28 13:17:29,530 - INFO - Prediction time: 0.11 seconds
23
+ 2025-09-28 13:17:29,530 - INFO - Classification Report:
24
+ 2025-09-28 13:17:29,535 - INFO - precision recall f1-score support
25
+
26
+ ACCOUNT#negative 0.00 0.00 0.00 2
27
+ CARD#negative 1.00 0.14 0.25 7
28
+ CARD#positive 0.00 0.00 0.00 1
29
+ CUSTOMER_SUPPORT#negative 0.49 0.96 0.65 75
30
+ CUSTOMER_SUPPORT#neutral 0.00 0.00 0.00 1
31
+ CUSTOMER_SUPPORT#positive 0.86 0.90 0.88 78
32
+ DISCOUNT#negative 0.00 0.00 0.00 5
33
+ DISCOUNT#neutral 0.00 0.00 0.00 1
34
+ DISCOUNT#positive 0.00 0.00 0.00 0
35
+ INTEREST_RATE#negative 0.56 0.50 0.53 10
36
+ INTERNET_BANKING#negative 0.00 0.00 0.00 12
37
+ INTERNET_BANKING#positive 0.00 0.00 0.00 1
38
+ LOAN#negative 0.88 0.54 0.67 13
39
+ MONEY_TRANSFER#negative 0.00 0.00 0.00 5
40
+ OTHER#negative 0.00 0.00 0.00 10
41
+ OTHER#neutral 0.00 0.00 0.00 1
42
+ OTHER#positive 0.67 0.50 0.57 4
43
+ PAYMENT#positive 0.00 0.00 0.00 3
44
+ PROMOTION#negative 0.00 0.00 0.00 4
45
+ PROMOTION#neutral 0.00 0.00 0.00 1
46
+ PROMOTION#positive 0.33 0.20 0.25 5
47
+ SAVING#negative 0.00 0.00 0.00 1
48
+ SAVING#positive 0.00 0.00 0.00 2
49
+ SECURITY#negative 0.00 0.00 0.00 1
50
+ SECURITY#neutral 0.00 0.00 0.00 1
51
+ TRADEMARK#negative 0.00 0.00 0.00 14
52
+ TRADEMARK#positive 0.89 0.91 0.90 138
53
+
54
+ accuracy 0.72 396
55
+ macro avg 0.21 0.17 0.17 396
56
+ weighted avg 0.65 0.72 0.66 396
57
+
58
+ 2025-09-28 13:17:29,539 - INFO - Confusion Matrix shape: (35, 35)
59
+ 2025-09-28 13:17:29,672 - INFO - Model saved to runs/20250928_131716/models/model.joblib
60
+ 2025-09-28 13:17:29,803 - INFO - Model also saved as runs/20250928_131716/models/UTS2017_Bank_AspectSentiment_SVC_feat20k_ngram1-2.joblib
61
+ 2025-09-28 13:17:29,927 - INFO - Model exported as ./uts2017_sentiment_20250928_131716.joblib
62
+ 2025-09-28 13:17:29,927 - INFO - Label mapping saved to runs/20250928_131716/models/labels.txt
63
+ 2025-09-28 13:17:29,928 - INFO - Metadata saved to runs/20250928_131716/metadata.json
uts2017_sentiment_20250928_131716.joblib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:502ef69d34545f9ad39573ed199b1ef331cb6fa17eb5977d3841e7596125b2a5
3
+ size 2154772