부산대학교 도서관

Television and live internet broadcasts coexist with a stream of social network commentary, engaging audiences in more complex ways than traditional ratings can represent, demanding convergent tools to analyze such contemporary media. In this work, we present PeakVis, an interactive tool that syncs a video recording with a responsive line graph representing the total number of tweets from each moment, the top messages, a dynamic word cloud, and a semantic graph showing word correlation. Thus, this novel interactive approach allows the analysis of broadcast highlights identified through Twitter posts peaks. We explored this freely available tool’s applicability by analyzing two different case studies: the season finale of a reality show and the final episode of a telenovela. We could observe that it allows us to quickly identify the most relevant segments and grasp the discussed subjects in-depth through the obtained results, showing its value in broadcast analysis.