Wang, D., & Kogan, M. (2023). Resonance+: Augmenting Collective Attention to Find Information on Public Cognition and Perception of Risk. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 487–500). Omaha, USA: University of Nebraska at Omaha.
Abstract: Microblogging platforms have been increasingly used by the public and crisis managers in crisis. The increasing volume of data has made such platforms more difficult for officials to find on-the-ground information and understand the public’s perception of the evolving risks. The crisis informatics literature has proposed various technological solutions to find relevant information from social media. However, the cognitive processes of the affected population and their subsequent responses, such as perceptions, emotional and behavioral responses, are still under-examined at scale. Yet, such information is important for gauging public perception of risks, an important task for PIOs and emergency managers. In this work, we leverage the noise-cutting power of collective attention and take cues from the Protective Action Decision Model, to propose a method that estimates shifts in collective attention with a special focus on the cognitive processes of those affected and their subsequent responses.
|
|
Nurollahian, S., Talegaonkar, I., Bell, A. Z., & Kogan, M. (2023). Factors Affecting Public’s Engagement with Tweets by Authoritative Sources During Crisis. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 459–477). Omaha, USA: University of Nebraska at Omaha.
Abstract: People increasingly use social media at the time of crisis, which produces a social media data deluge, where the public may find it difficult to locate trustworthy and credible information. Therefore, they often turn to authoritative sources: official individuals and organizations who are trusted to provide reliable information. It is then imperative that their credible messages reach and engage the widest possible audience, especially among those affected. In this study, we explore the role of metadata and linguistic factors in facilitating three types of engagement — retweets, replies, and favorites— with posts by authoritative sources. We find that many factors are similarly important across models (popularity, sociability, activity). However, some features are salient for only a specific type of engagement. We conclude by providing guidance to authoritative sources on how they may optimize specific types of engagement: retweets for information propagation, replies for in-depth sense-making, and favorites for cross-purpose visibility.
|
|
St. Denis, L. A., & Hughes, A. L. (2023). Use of Statistics in Disaster by Local Individuals: An Examination of Tweets during COVID-19. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 449–458). Omaha, USA: University of Nebraska at Omaha.
Abstract: We report on how individuals local to the US state of Colorado used statistics in tweets to make sense of the early stages of the COVID-19 pandemic. Tweets provided insight into how people interpreted statistical data, sometimes incorrectly, which has implications for crisis responders tasked with understanding public perceptions and providing accurate information. With widespread concerns about the accuracy and quality of online information, we show how monitoring public reactions to and uses of statistics on social media is important for improving crisis communication. Findings suggest that statistics can be a powerful tool for making sense of a crisis and coping with the stress and uncertainty of a global, rapidly evolving event like the COVID-19 pandemic. We conclude with broader implications for how crisis responders might improve their communications around statistics to the public, and suggestions for how this research might be expanded to look at other types of disasters.
|
|
Rode-Hasinger, S., Haberle, M., Racek, D., Kruspe, A., & Zhu Xiao Xiang. (2023). TweEvent: A dataset of Twitter messages about events in the Ukraine conflict. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 407–416). Omaha, USA: University of Nebraska at Omaha.
Abstract: Information about incidents within a conflict, e.g., shelling of an area of interest, is scattered amongst different data or media sources. For example, the ACLED dataset continuously documents local incidents recorded within the context of a specific conflict such as Russia’s war in Ukraine. However, these blocks of information might be incomplete. Therefore, it is useful to collect data from several sources to enrich the information pool of a certain incident. In this paper, we present a dataset of social media messages covering the same war events as those collected in the ACLED dataset. The information is extracted from automatically geocoded Twitter text data using state-of-the-art natural language processing methods based on large pre-trained language models (LMs). Our method can be applied to various textual data sources. Both the data as well as the approach can serve to help human analysts obtain a broader understanding of conflict events.
|
|
Pereira, J., Fidalgo, R., Lotufo, R., & Nogueira, R. (2023). Crisis Event Social Media Summarization with GPT-3 and Neural Reranking. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 371–384). Omaha, USA: University of Nebraska at Omaha.
Abstract: Managing emergency events, such as natural disasters, requires management teams to have an up-to-date view of what is happening throughout the event. In this paper, we demonstrate how a method using a state-of-the-art open-sourced search engine and a large language model can generate accurate and comprehensive summaries by retrieving information from social media and online news sources. We evaluated our method on the TREC CrisisFACTS challenge dataset using automatic summarization metrics (e.g., Rouge-2 and BERTScore) and the manual evaluation performed by the challenge organizers. Our approach is the best in comprehensiveness despite presenting a high redundancy ratio in the generated summaries. In addition, since all pipeline components are few-shot, there is no need to collect training data, allowing us to deploy the system rapidly. Code is available at https://github.com/neuralmind-ai/visconde-crisis-summarization.
|
|