Topic Wise Hindi Text Clustering Using Real Time Twitter Data

Twitter and other online social media are expanding so quickly. Twitter has recently risen to prominence as one of the most widely used microblogging platforms online. It enables millions of individuals to interact and communicate by sending up to 240-character-long messages. Twitter produces a vast amount of information that must be analyzed automatically in order to determine what individuals are talking about. A lot of study has been done on the English text. Despite being spoken by millions of people worldwide, resource-constrained languages like Hindi have not made much development. However, due to lack of availability of Natural language processing (NLP) tools and techniques for Indian Hindi text languages, it remains challenging to summarize content for low-resource languages like Hindi. Real Time Hindi Twitter data is used to address this challenge. Global Vectors for Word Representation (GLoVe) are employed to extract semantic meaning from Hindi tweets and then categorizing the topics, the K-means clustering technique is used. The experimental outcomes utilizing actual Twitter data demonstrate that the suggested method is superior to other ways in terms of quality and run-time performance.