hmohebbi/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
Implements a comparative benchmark across shallow and deep learning approaches, aggregating sentence-level BERT embeddings via mean pooling for traditional classifiers while using TensorFlow Hub's pre-trained BERT directly with bidirectional LSTMs for end-to-end fine-tuning. Evaluates trade-offs between classical ML pipelines (SVM with BERT embeddings achieving 90.35% accuracy) and neural architectures (Bi-LSTM with BERT reaching 91.34%), providing empirical performance metrics across embedding strategies and classifier combinations on IMDB reviews.
No commits in the last 6 months.
Stars
74
Forks
17
Language
Jupyter Notebook
License
—
Category
Last pushed
Nov 30, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/hmohebbi/SentimentAnalysis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
codelion/adaptive-classifier
A flexible, adaptive classification system for dynamic text classification
jiegzhan/multi-class-text-classification-cnn-rnn
Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN...
jiegzhan/multi-class-text-classification-cnn
Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN...
cbaziotis/datastories-semeval2017-task4
Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention...
iamaziz/ar-embeddings
Sentiment Analysis for Arabic Text (tweets, reviews, and standard Arabic) using word2vec