Modern Information Retrieval - Spring 2021
This GitHub repository showcases three distinct projects in modern information retrieval. The first project focuses on applying machine learning to build a recommendation system using Word2Vec and TF-IDF for semantic analysis, classification, and clustering. The second project is a user-friendly IMDB search engine featuring efficient indexing, typo tolerance, and dataset compression for optimized storage and resource utilization. The third project implements a crawler for the Microsoft Academic website, enabling the creation of a recommendation system for academic papers based on the crawled data. Together, these projects highlight advancements in recommendation systems, search engines, and data-driven analysis.