Hmohebbi SentimentAnalysis Save
(BOW, TF-IDF, Word2Vec, BERT) Word Embeddings + (SVM, Naive Bayes, Decision Tree, Random Forest) Base Classifiers + Pre-trained BERT on Tensorflow Hub + 1-D CNN and Bi-Directional LSTM on IMDB Movie Reviews Dataset
Project README
SentimentAnalysis
(BOW, TF-IDF, Word2Vec, BERT) Word Embeddings + (SVM, Naive Bayes, Decision Tree, Random Forest) Base Classifiers + Pre-trained BERT on Tensorflow Hub + 1-D CNN and Bi-Directional LSTM on IMDB Movie Reviews Dataset
Results for Base Classifiers
| Rank | Word Embedding | Classifier | Accuracy | F1-Score |
|---|---|---|---|---|
| 1 | BERT Sentence Version (Mean Bert Features per Review) | SVM | 90.35 | 0.90 |
| 2 | BERT Sentence Version (Mean Bert Features per Review) | MLP | 90.32 | 0.90 |
| 3 | TFIDF with Stop Words | SVM | 89.59 | 0.90 |
Results for Deep Neural Networks
| Rank | Word Embedding | Model | Accuracy |
|---|---|---|---|
| 1 | BERT TensorFlow-HUB | Bi-Directional LSTM | 91.34 |
| 2 | BERT Sentence Version (Mean Bert Features per Review) | 1-D CNN | 85.46 |
Open Source Agenda is not affiliated with "Hmohebbi SentimentAnalysis" Project. README Source: hmohebbi/SentimentAnalysis
Stars
65
Open Issues
2
Last Commit
4 years ago
Repository
Open Source Agenda Badge
