Clustering and Retrieval of News articles using Natural Language Processing

This study focused on organizing and finding news articles from a large dataset using Natural Language Processing (NLP). In journalism, it’s important to manage information effectively due to the increasing amount of data available. Clustering groups similar articles together, while retrieval helps find specific articles based on certain criteria. These techniques help journalists and researchers identify patterns and extract useful information. The study used the Reuters dataset, which contains a lot of news stories. Different clustering algorithms were tested, and one called Agglomerative Clustering performed the best. For retrieval, a system was created that finds articles like user queries using cosine similarity. The study had some limitations, such as unclear categorization and a complex dataset. Future work could involve trying other clustering algorithms, considering additional features like author and publication date, and using a more diverse dataset.