"Listening In": Social Signal Detection for Crisis Prediction

Simple item page
dc.contributor.authorJanzen, Sabine
dc.contributor.authorSaxena, Prajvi
dc.contributor.authorBaer, Sebastian
dc.contributor.authorMaass, Wolfgang
dc.date.accessioned2023-12-26T18:38:02Z
dc.date.available2023-12-26T18:38:02Z
dc.date.issued2024-01-03
dc.identifier.doi10.24251/HICSS.2023.260
dc.identifier.isbn978-0-9981331-7-1
dc.identifier.otheraff87cad-276d-46bc-92fb-5e7174ac874f
dc.identifier.urihttps://hdl.handle.net/10125/106639
dc.language.isoeng
dc.relation.ispartofProceedings of the 57th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectDisaster Information, Resilience, for Emergency and Crisis Technologies
dc.subjectcrisis prediction
dc.subjectopen-domain
dc.subjectsocial media
dc.subjectsocial signal detection
dc.title"Listening In": Social Signal Detection for Crisis Prediction
dc.typeConference Paper
dc.type.dcmiText
dcterms.abstractCrises send out early warning signals; mostly weak and difficult to detect amidst the noise of everyday life. Signal detection based on social media enables early identification of such signals supporting pro-active organizational responses before a crisis occurs. Nonetheless, social signal detection based on Twitter data is not applied in crisis management in practice as it is challenging due to the high volume of noise. With OSOS, we introduce a method for open-domain social signal detection of crisis-related indicators in tweets. OSOS works with multi-lingual Twitter data and combines multiple state-of-the-art models for data pre-processing (SoMaJo) and data filtration (GPT-3). It excels in crisis domains by leveraging fine-tuned GPT-3\textsuperscript{FT} (Curie) model and achieving benchmark results in the CrisisBench dataset. The method was exemplified within a signaling service for crisis management. We were able to evaluate the proposed approach by means of a data set obtained from Twitter (X) in terms of performance in identifying potential social signals for energy-related crisis events.
dcterms.extent10 pages
prism.startingpage2096

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0205.pdf
Size:
681.79 KB
Format:
Adobe Portable Document Format
Download

Collections

Disaster Information, Resilience, for Emergency and Crisis Technologies