TweetIT- Analyzing Topics for Twitter Users to garner Maximum Attention

TL;DR

This paper presents a method to analyze Twitter users' most attention-grabbing topics by modeling their top tweets and comparing them with news data, aiming to suggest topics for higher future popularity.

Contribution

It introduces a novel approach combining attention-based tweet selection and topic modeling to identify high-impact topics for Twitter users.

Findings

Effective identification of high-attention topics from user tweets

Correlation between modeled topics and news data

Potential to enhance user popularity through topic suggestions

Abstract

Twitter, a microblogging service, is todays most popular platform for communication in the form of short text messages, called Tweets. Users use Twitter to publish their content either for expressing concerns on information news or views on daily conversations. When this expression emerges, they are experienced by the worldwide distribution network of users and not only by the interlocutor(s). Depending upon the impact of the tweet in the form of the likes, retweets and percentage of followers increases for the user considering a window of time frame, we compute attention factor for each tweet for the selected user profiles. This factor is used to select the top 1000 Tweets, from each user profile, to form a document. Topic modelling is then applied to this document to determine the intent of the user behind the Tweets. After topics are modelled, the similarity is determined between the BBC news data-set containing the modelled topic, and the user document under evaluation. Finally, we determine the top words for a user which would enable us to find the topics which garnered attention and has been posted recently. The experiment is performed using more than 1.1M Tweets from around 500 Twitter profiles spanning Politics, Entertainment, Sports etc. and hundreds of BBC news articles. The results show that our analysis is efficient enough to enable us to find the topics which would act as a suggestion for users to get higher popularity rating for the user in the future.