Exploit Social Relations in Sentiment Analysis of Social Media Content for Disaster Management Emergent Research Forum (ERF)

The world has witnessed the prevailing usage of social media for communication during disasters. Being able to monitor and predict public opinions on social media during disasters allows us to design more efficient and effective communication mechanisms during critical times. However, this potential is yet to be materialized due to difficulties in sentiment analysis of social media content. We propose to augment the effectiveness of such analysis by incorporating social relations in sentiment classification models. The proposed study extends previous work substantially by looking at a larger set of social relations and focusing on different communication goals at each stage of disaster management. In addition, we look at sentiments at both individual and community levels. The study can help formulate a better understanding of how opinions are formed and propagated during disasters, thus allow stakeholders to strategize for better communication.