RecTwitter: A Semantic-Based Recommender System for Twitter Users
ResumoTwitter is a microblog which contains large amounts of users who contribute with messages for a wide variety of real-world events. It is possible to identify users who share interests using the messages published in their timeline. However, this task is an exhausting process because the algorithm has to analyze all users' messages. In this project, we propose a semantic recommendation system based on SWRL rules to recommend accounts to be followed or unfollowed. In order to evaluate the recommendations, we conducted an experiment with real users. The results show that 80% of the recommendations were generated to unfollow and 20% to follow some account.
Palavras-chave: Information Overload, Recommendation, Semantic Web, Twitter
SOUZA, Paulo Roberto de; DURÃO, Frederico Araújo. RecTwitter: A Semantic-Based Recommender System for Twitter Users. In: SIMPÓSIO BRASILEIRO DE SISTEMAS MULTIMÍDIA E WEB (WEBMEDIA), 24. , 2018, Salvador. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2018 . p. 371-378.