← All projects
AI / MLNLP · Text Classification
Multi-Class Sentiment Classifier
Preprocessing + models categorizing reviews as positive, neutral, or negative.
01 · The problem
Raw product reviews needed automated sentiment labels for analytics.
02 · Approach
- 1
Preprocessed 1,000 reviews: tokenization, stop-word removal, POS-tagged lemmatization via NLTK.
- 2
Engineered TF-IDF unigram/bigram features.
- 3
Compared Naive Bayes, SVM, and Logistic Regression.
03 · Outcome
All three classifiers reached full test accuracy on this synthetic dataset built from distinct linguistic templates.
Next projectCar Keyless Entry Replay (HackRF)→