Framework for the Discovery of Newsworthy Events in Social Media

• Autor(a) principal: Duarte, Fernando José Fradique
• Data de Publicação: 2019
• Outros Autores: Pereira, Óscar Mortágua, Aguiar, Rui L.
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10773/26037
• topic: Directed Acyclic Graph; Dynamic Programming; Event Detection; Jarvis-Patrick Clustering; KNN Neighbors; Learning; Machine XGBoost; Naïve Bayes; Random Forest; SVM

The new communication paradigm established by social media along with its growing popularity in recent years contributed to attract an increasing interest of several research fields. One such research field is the field of event detection in social media. The contribution of this article is to implement a system to detect newsworthy events in Twitter. The proposed pipeline first splits the tweets into segments. These segments are then ranked. The top k segments in this ranking are then grouped together. Finally, the resulting candidate events are filtered in order to retain only those related to realworld newsworthy events. The implemented system was tested with three months of data, representing a total of 4,770,636 tweets written in Portuguese. In terms of performance, the proposed approach achieved an overall precision of 88% and a recall of 38%.