VerificadoProfesional
commited on
Commit
•
c314fb8
1
Parent(s):
ff4586c
Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,8 @@ widget:
|
|
19 |
## Overview
|
20 |
This BERT-based text classifier was developed as a thesis project for the Computer Engineering degree at Universidad de Buenos Aires (UBA).
|
21 |
The model is designed to detect sentiments in Spanish and was fine-tuned on the *dccuchile/bert-base-spanish-wwm-uncased* model using a specific set of hyperparameters.
|
22 |
-
It was trained on a dataset containing 11,500 Spanish tweets collected from various regions, both positive and negative.
|
|
|
23 |
|
24 |
## Team Members
|
25 |
- **[Azul Fuentes](https://github.com/azu26)**
|
@@ -48,8 +49,6 @@ The model's performance was evaluated using the following metrics:
|
|
48 |
* **Precision = _86.46%_**
|
49 |
* **Recall = _86.51%_**
|
50 |
|
51 |
-
|
52 |
-
|
53 |
## Usage
|
54 |
### Installation
|
55 |
You can install the required dependencies using pip:
|
@@ -92,7 +91,8 @@ print(f"Probabilities: {probabilities}")
|
|
92 |
```
|
93 |
|
94 |
## License
|
95 |
-
Apache License 2.0
|
|
|
96 |
|
97 |
## Acknowledgments
|
98 |
Special thanks to DCC UChile for the base Spanish BERT model and to all contributors to the dataset used for training.
|
|
|
19 |
## Overview
|
20 |
This BERT-based text classifier was developed as a thesis project for the Computer Engineering degree at Universidad de Buenos Aires (UBA).
|
21 |
The model is designed to detect sentiments in Spanish and was fine-tuned on the *dccuchile/bert-base-spanish-wwm-uncased* model using a specific set of hyperparameters.
|
22 |
+
It was trained on a dataset containing 11,500 Spanish tweets collected from various regions, both positive and negative. This model was trained using a well-curated combination of datasets from TASS.
|
23 |
+
|
24 |
|
25 |
## Team Members
|
26 |
- **[Azul Fuentes](https://github.com/azu26)**
|
|
|
49 |
* **Precision = _86.46%_**
|
50 |
* **Recall = _86.51%_**
|
51 |
|
|
|
|
|
52 |
## Usage
|
53 |
### Installation
|
54 |
You can install the required dependencies using pip:
|
|
|
91 |
```
|
92 |
|
93 |
## License
|
94 |
+
* Apache License 2.0
|
95 |
+
* [TASS Dataset license](http://tass.sepln.org/tass_data/download.php)
|
96 |
|
97 |
## Acknowledgments
|
98 |
Special thanks to DCC UChile for the base Spanish BERT model and to all contributors to the dataset used for training.
|