Commit
•
deda47c
1
Parent(s):
8aa0a9b
Model files uploaded
Browse files- .gitattributes +4 -9
- README.md +45 -1
- config.json +40 -0
- model.pkl +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -1,35 +1,30 @@
|
|
1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
4 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
-
*.
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
5 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
|
|
6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
|
|
11 |
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
13 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
14 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
15 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
17 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
18 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
19 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
|
|
20 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
21 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
|
|
22 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
23 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
24 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
25 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
28 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,47 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: bsd-3-clause
|
3 |
+
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
|
7 |
+
tags:
|
8 |
+
- sentiment
|
9 |
+
- bert
|
10 |
+
- sentiment-analysis
|
11 |
+
- transformers
|
12 |
+
|
13 |
+
pipeline_tag: text-classification
|
14 |
---
|
15 |
+
> Authors : GRP209
|
16 |
+
|
17 |
+
# User Comment Sentiment Analysis
|
18 |
+
|
19 |
+
This model aims to analyze user comments on products and extracting the expressed sentiments.
|
20 |
+
|
21 |
+
User ratings on the internet do not always provide detailed qualitative information about their experience.
|
22 |
+
|
23 |
+
Therefore, it is important to go beyond these ratings and extract more insightful information that can help a brand improve their product or service.
|
24 |
+
|
25 |
+
# Objective
|
26 |
+
|
27 |
+
The model utilizes the BERT architecture and is trained on a dataset of user comments with sentiment labels.
|
28 |
+
|
29 |
+
The model is capable of analyzing comments and extracting sentiments such as **positive**, **negative**, or **neutral**.
|
30 |
+
|
31 |
+
# Features
|
32 |
+
|
33 |
+
**Sentiment Classification**: The model can classify user comments into positive, negative, or neutral sentiments, providing an overall indication of the expressed opinion.
|
34 |
+
|
35 |
+
**Improvement Suggestions**: In cases where a comment expresses a negative or neutral sentiment, the model suggests an improved version of the text with a more positive sentiment.
|
36 |
+
This can help businesses understand consumer reactions and identify areas for product or service improvement.
|
37 |
+
|
38 |
+
# Usage
|
39 |
+
|
40 |
+
To use this sentiment analysis system, follow these steps:
|
41 |
+
|
42 |
+
- Install the required dependencies by running the command pip install -r requirements.txt.
|
43 |
+
- Once the training is complete, the best-trained model will be saved in the best_model_state.bin file.
|
44 |
+
- To make predictions on new comments, use the analyze_sentiment(comment_text) function, replacing comment_text with the actual comment text to analyze.
|
45 |
+
- The model will return the sentiment expressed in the comment.
|
46 |
+
- To suggest an improved version of a comment, use the suggest_improved_text(comment_text) function.
|
47 |
+
- If the comment expresses a negative or neutral sentiment, the function will generate an improved version of the text with a more positive sentiment. Otherwise, the original text will be returned without modification.
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "negative",
|
15 |
+
"1": "neutral",
|
16 |
+
"2": "positive"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"negative": 0,
|
22 |
+
"neutral": 1,
|
23 |
+
"positive": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_length": 64,
|
27 |
+
"max_position_embeddings": 512,
|
28 |
+
"model_type": "bert",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 0,
|
32 |
+
"padding": "max_length",
|
33 |
+
"position_embedding_type": "absolute",
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.30.0",
|
37 |
+
"type_vocab_size": 2,
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 30522
|
40 |
+
}
|
model.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b4aea8ee080351fdae9509a2b90a9c4dd6a57464acc1f84fc6dcd60201ac7ce
|
3 |
+
size 2848
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4ee83e207cd138b63600f23ca3086e2c73da4ec726274a71d768f838450df33
|
3 |
+
size 438022317
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "AutoTrain", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|