Monitoring of events in social networks for data collection, information analysis and temporal synchronization

• Grant number: 18/18264-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2018
• End date: October 31, 2019
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Anderson de Rezende Rocha
• Grantee: José Dorivaldo Nascimento Souza Júnior
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 17/12646-3 - Déjà vu: feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events, AP.TEM

Abstract

In order to understand a given event better, it is paramount nowadays analyzing social media items. However, to collect these items, usually it is necessary to define a set of keywords, and this approach invariably brings items not related to the event, plus is not able to collect all items that are really connected to the event. In order to minimize these drawbacks, we propose the development of a query expansion and the test of clustering algorithms in collected social media items. Query expansion consists in, given a set of collected items using a set of keywords previously defined, analyzing the items in order to get new keywords also related to the event, and redoing the query with these new keywords. The main objective is to enhance the set of social media items related to the event. On the other hand, clustering in this work has the goal to identify if a given item is related or not to the defined event. K-means and spectral clustering methods are going to be tested in this work, in order to group the items from the set and define if a given item is related to the event or not.