add evaluation
Browse files
README.md
CHANGED
|
@@ -30,6 +30,14 @@ This repository contains a fine-tuned BERT model for sentiment analysis on IMDb
|
|
| 30 |
- **Labels**:
|
| 31 |
- `0`: Negative
|
| 32 |
- `1`: Positive
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
## Usage
|
| 35 |
### **Load the Model in Python**
|
|
|
|
| 30 |
- **Labels**:
|
| 31 |
- `0`: Negative
|
| 32 |
- `1`: Positive
|
| 33 |
+
## Evaluation
|
| 34 |
+
| **Model** | **SST-2 Accuracy** | **Yelp Accuracy** | **Amazon Accuracy** | **IMDB Accuracy** |
|
| 35 |
+
|-----------------------------------|------------------|------------------|------------------|------------------|
|
| 36 |
+
| **philipobiorah/bert-imdb-model** | **0.89** | **0.89** | **0.89** | **0.96** |
|
| 37 |
+
| **DistilBERT-SST-2** | **0.94** | **0.85** | **0.85** | **0.89** |
|
| 38 |
+
| **RoBERTa-Sentiment** | **0.40** | **0.42** | **0.47** | **0.79** |
|
| 39 |
+
| **Logistic Regression** | **0.83** | **0.91** | **0.86** | **0.85** |
|
| 40 |
+
| **Naive Bayes** | **0.77** | **0.86** | **0.84** | **0.85** |
|
| 41 |
|
| 42 |
## Usage
|
| 43 |
### **Load the Model in Python**
|