How crowd accidents are reported in the news media: Lexical and sentiment analysis
Claudio Feliciani, Alessandro Corbetta, Milad Haghani, Katsuhiro, Nishinari

TL;DR
This study analyzes how media reports on crowd accidents over more than a century, revealing lexical and emotional patterns that influence public perception and highlighting cross-cultural differences and evolving language use.
Contribution
It provides a comprehensive lexical and sentiment analysis of 372 media reports across diverse sources and time periods, revealing shifts in terminology and emotional tone in reporting.
Findings
'Stampede' is more common than 'panic' in media descriptions.
Western and South Asian media differ in their portrayal patterns.
Use of 'crowd crush' has increased in recent years.
Abstract
The portrayal of crowd accidents by the media can influence public understanding and emotional response, shaping societal perceptions and potentially impacting safety measures and preparedness strategies. This paper critically examines the portrayal of crowd accidents in news coverage by analyzing the texts of 372 media reports of crowd accidents spanning 26 diverse news sources from 1900 to 2019. We investigate how media representations of crowd accidents vary across time and geographical origins. Our methodology combines lexical analysis to unveil prevailing terminologies and sentiment analysis to discern the emotional tenor of the reports. The findings reveal the prevalence of the term "stampede" over "panic" in media descriptions of crowd accidents. Notably, divergent patterns are observable when comparing Western versus South Asian media (notably India and Pakistan), unveiling a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCrime, Deviance, and Social Control · Disaster Management and Resilience · Sentiment Analysis and Opinion Mining
