Paper Type
Complete
Abstract
The increasing role of social media in crisis communication has made it a valuable resource for understanding public emotions during natural disasters. Using Computational Design Science research, we developed a system with a Data Module collecting YouTube data via the APISM package, an AI Module detecting emotions aligned with the Integrated Crisis Mapping model, and an Index Module generating the Emotion and Emotion Polarity Indices. These indices represent content creator and community emotions and creator-community emotional alignment. By analyzing 2,463 videos and 750,354 comments from Hurricanes Helene and Milton, we uncovered dynamic emotional trends different from the model’s static view. The AI module’s emotion detection algorithm highlighted that creators and the community expressed positive emotions before the hurricanes. The Emotion Polarity Index showed that their emotions did not align during and after the hurricanes, with the community expressing negative emotions compared to the neutral to positive stance of the creators.
Paper Number
1918
Recommended Citation
Kok-Shun, Brice Valentin; Chan, Johnny; Peko, Gabrielle; and Sundaram, David, "Harnessing Social Media Emotions for Insightful Disaster Communication: A Computational Design Science Research Approach" (2025). AMCIS 2025 Proceedings. 2.
https://aisel.aisnet.org/amcis2025/social_comput/social_comput/2
Harnessing Social Media Emotions for Insightful Disaster Communication: A Computational Design Science Research Approach
The increasing role of social media in crisis communication has made it a valuable resource for understanding public emotions during natural disasters. Using Computational Design Science research, we developed a system with a Data Module collecting YouTube data via the APISM package, an AI Module detecting emotions aligned with the Integrated Crisis Mapping model, and an Index Module generating the Emotion and Emotion Polarity Indices. These indices represent content creator and community emotions and creator-community emotional alignment. By analyzing 2,463 videos and 750,354 comments from Hurricanes Helene and Milton, we uncovered dynamic emotional trends different from the model’s static view. The AI module’s emotion detection algorithm highlighted that creators and the community expressed positive emotions before the hurricanes. The Emotion Polarity Index showed that their emotions did not align during and after the hurricanes, with the community expressing negative emotions compared to the neutral to positive stance of the creators.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SOCCOMP