Published Paper Details:

Social Media has emerged as a popular medium for individuals to express themselves and share their ideas with others. The number of users across various social networks is growing at an exponential rate. Twitter has become a vital source of real-time information and communication, with a plethora of trending topics being discussed by users at any given moment. These topics cover a wide range of subjects, reflecting people's daily lives and interests. Therefore, it is essential to implement an effective methodology to identify short-term, high-intensity discussion topics. The proposed work utilizes a Multiview clustering approach, which has been shown to be highly effective in unfolding underlying patterns. The Multiview clustering approach used in the analysis of trending Twitter topics considers different views of the data, which include the text content of tweets, like count, retweet count, quote count, and reply count. This analysis can offer valuable insights into the latest trends and have practical applications, such as monitoring public opinion, recommending hot products, and detecting incidents. Additionally, artificially intelligent services like web search systems or recognition systems can also benefit from this analysis. The Twitter data is retrieved and a dataset is created for further analysis using Python's snscrape library. The aim of this work is to cluster topics based on multi-view data to identify the most discussed topics during a specific time period. Experiments on real datasets indicate that the Multiview clustering approach is more effective than single-view clustering in detecting trending topics with a reasonably close approximation to the expected outcome. Nonetheless, the proposed approach has some limitations and challenges, such as the requirement for sufficient and diverse data to ensure the accuracy of the clustering results.