movie hunter-Movie search engine

Developed a BM25-based movie search engine for retrieving relevant movies based on user queries.

- Built a complete information retrieval pipeline including preprocessing, indexing, ranking, and search history tracking.

- Used movie metadata such as title, overview, genre, director, and cast to improve search quality.

- Applied NLP techniques including tokenization, stopword removal, lemmatization, and text normalization.

- Added query expansion using synonyms, related terms, and embedding-based techniques.

- Explored multilingual search so Arabic queries can retrieve relevant English movie results.

- Used NLTK, rank_bm25, Scikit-learn, and PyTerrier for search and information retrieval experiments.

- Implemented login/signup validation and user-specific search history.

- Developed a web-based interface using Angular connected to a Flask backend.

Technologies: Python, Flask, Angular, NLTK, rank_bm25, PyTerrier, Scikit-learn, Pandas, NLP, Information Retrieval, BM25, TF-IDF