Word association network approach for summarizing Twitter conversation about public election

摘要

Public election viewed as one of the biggest event for democracy as it will start a new phase of government in hundreds of regions across Indonesia. Such a major event will attract a big attention and require careful decision making, thus a real time information for decision support become crucial part. Twitter can serve the purpose as one source of real time information from user generated content, but the wide choice of tools with its own characteristic become a challenge in the process. In this paper, we use Word Association Network based on Graph Theory to visualize Twitter conversation for real time decision making. We are using Pemilihan Kepala Daerah (Pilkada) as the study case which happen in 9th December 2015 with 984694 tweets collected for 15 days since 3rd of December 2015.