Back to Projects
Sentiment Analysis on IMDB Reviews
Completed
ML/AI
Jun 2025Overview
Multi-model sentiment classification on 50k IMDB reviews using classical ML, ANN, and BERT.
Highlights
- •EDA: class balance, review length distribution, word patterns; histograms + word clouds
- •Preprocessing: TF-IDF for NB/LR, Keras tokenization for ANN, HF tokenizer for BERT
- •Evaluated NB, Logistic Regression, ANN, BERT with F1/precision/recall/accuracy
- •Confusion matrices, PR curves for all models
Tech Stack
Pythonscikit-learnKerasHuggingFace Transformers
Related Projects
adviSU — Retrieval-Augmented Academic Advising System
A bilingual (Turkish/English) academic advising assistant that answers degree, course-selection, and scheduling questions from official university curriculum data. Built as a Sabancı University CS455 course project.
EchoSpace-AR
Detects surrounding sounds and renders a directional in-headset icon that moves toward the sound source to improve environmental awareness—especially for Deaf and hard-of-hearing users.
Detecting Online Polarization (SemEval-2026 Task 9)
Multilingual polarization detection (binary classification: Polarized vs Non-Polarized) with emphasis on fair evaluation (Macro-F1).