A Framework for Perception Analysis of Social Media Data During Disease Outbreaks: Uncovering Patterns of Resentment Towards Bats
Files
Date
2024-01-03
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Narrator
Transcriber
Annotator
Journal Title
Journal ISSN
Volume Title
Publisher
Volume
Number/Issue
Starting Page
2475
Ending Page
Alternative Title
Abstract
Despite the growing number of natural language processing (NLP) tools developed for decision-makers to leverage social media for public perception evaluation during crises, a more robust framework is needed. This study explores a domain-specific machine learning framework for perception analysis using tweets about bats during disease outbreaks as a case study. Zoonotic disease outbreaks such as COVID-19 and Ebola are often attributed to bats and have resulted in unnecessary culling of wildlife; therefore, this is a case where perception is meaningful to a species. Analysis of 15,968 tweets showed a pattern in which tweets with anti-bat perceptions were most common during the early phases of an outbreak but declined over time while remaining negative, with 87.6% reliability of the framework according to manual coding of 300 randomly selected tweets. The framework can help stakeholders understand trends in public perception in near real-time and guide responses to spreading misinformation.
Description
Keywords
Data Analytics, Data Mining, and Machine Learning for Social Media, bats, decision-making tools, natural language processing, perception analysis, text analysis
Citation
Extent
10 pages
Format
Geographic Location
Time Period
Related To
Proceedings of the 57th Hawaii International Conference on System Sciences
Related To (URI)
Table of Contents
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
Rights Holder
Local Contexts
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.