Visualizing sentiment change in social networks
Omar Valdiviezo, J. Alfredo Sánchez, Ofelia Cervantes · 2017
This paper presents SCWorld, a novel scheme for visualizing sentiment changes in real-time in social networks. Two main features distinguish SCWorld from existing work in sentiment classification in real time: First, it provides a high-level, large-granularity view of sentiment and relationships among dynamic clusters of topics in a social network; second, it allows users to observe animated graphical representations of sentiment changes that reflect the aggregated polarity of postings and other user activities in social networks. SCWorld builds upon Expression, a platform for sentiment classification that also provides a low-granularity topic visualization scheme termed Sentiment Card (SC). SCs merge quantitative and qualitative data that arise from sentiment analysis at the lowest cognitive level and extract the most relevant information. SCWorld seizes and synthesizes the data analyzed by Expression and presents it as a forced-directed diagram, in which topics are represented as nodes, and relationships between nodes that influence a specific topic as links. Nodes and links change in a reactive way based on what is happening in the social network in real time. We present the design of SCWorld as well as initial findings regarding its utility based on user testing of a proof-of-concept prototype.