Harnessing the power of multi-source media platforms for public perception analysis: Insights from the ohio train derailment. Hu, T., Huang, X., Li, Y., & Fu, X. Big Data and Cognitive Computing, 9(4):88, April, 2025.
Paper doi abstract bibtex Media platforms provide an effective way to gauge public perceptions, especially during mass disruption events. This research explores public responses to the 2023 Ohio train derailment event through Twitter, currently known as X, and Google Trends. It aims to unveil public sentiments and attitudes by employing sentiment analysis using the Valence Aware Dictionary and Sentiment Reasoner (VADER) and topic modeling using Latent Dirichlet Allocation (LDA) on geotagged tweets across three phases of the event: impact and immediate response, investigation, and recovery. Additionally, the Self-Organizing Map (SOM) model is employed to conduct time-series clustering analysis of Google search patterns, offering a deeper understanding into the event’s spatial and temporal impact on society. The results reveal that public perceptions related to pollution in communities exhibited an inverted U-shaped curve during the initial two phases on both the Twitter and Google Search platforms. However, in the third phase, the trends diverged. While public awareness declined on Google Search, it experienced an uptick on Twitter, a shift that can be attributed to governmental responses. Furthermore, the topics of Twitter discussions underwent a transition across three phases, changing from a focus on the causes of fires and evacuation strategies in Phase 1, to river pollution and trusteeship issues in Phase 2, and finally converging on government actions and community safety in Phase 3. Overall, this study advances a multi-platform and multi-method framework to uncover the spatiotemporal dynamics of public perception during disasters, offering actionable insights for real-time, region-specific crisis management.
@article{hu_harnessing_2025,
title = {Harnessing the power of multi-source media platforms for public perception analysis: {Insights} from the ohio train derailment},
volume = {9},
copyright = {http://creativecommons.org/licenses/by/3.0/},
issn = {2504-2289},
shorttitle = {Harnessing the {Power} of {Multi}-{Source} {Media} {Platforms} for {Public} {Perception} {Analysis}},
url = {https://www.mdpi.com/2504-2289/9/4/88},
doi = {10.3390/bdcc9040088},
abstract = {Media platforms provide an effective way to gauge public perceptions, especially during mass disruption events. This research explores public responses to the 2023 Ohio train derailment event through Twitter, currently known as X, and Google Trends. It aims to unveil public sentiments and attitudes by employing sentiment analysis using the Valence Aware Dictionary and Sentiment Reasoner (VADER) and topic modeling using Latent Dirichlet Allocation (LDA) on geotagged tweets across three phases of the event: impact and immediate response, investigation, and recovery. Additionally, the Self-Organizing Map (SOM) model is employed to conduct time-series clustering analysis of Google search patterns, offering a deeper understanding into the event’s spatial and temporal impact on society. The results reveal that public perceptions related to pollution in communities exhibited an inverted U-shaped curve during the initial two phases on both the Twitter and Google Search platforms. However, in the third phase, the trends diverged. While public awareness declined on Google Search, it experienced an uptick on Twitter, a shift that can be attributed to governmental responses. Furthermore, the topics of Twitter discussions underwent a transition across three phases, changing from a focus on the causes of fires and evacuation strategies in Phase 1, to river pollution and trusteeship issues in Phase 2, and finally converging on government actions and community safety in Phase 3. Overall, this study advances a multi-platform and multi-method framework to uncover the spatiotemporal dynamics of public perception during disasters, offering actionable insights for real-time, region-specific crisis management.},
language = {en},
number = {4},
urldate = {2025-04-07},
journal = {Big Data and Cognitive Computing},
author = {Hu, Tao and Huang, Xiao and Li, Yun and Fu, Xiaokang},
month = apr,
year = {2025},
keywords = {/unread, disaster management, sentiment analysis, social media, topic modeling},
pages = {88},
}
Downloads: 0
{"_id":"mYg9qdSgAtffuic7v","bibbaseid":"hu-huang-li-fu-harnessingthepowerofmultisourcemediaplatformsforpublicperceptionanalysisinsightsfromtheohiotrainderailment-2025","author_short":["Hu, T.","Huang, X.","Li, Y.","Fu, X."],"bibdata":{"bibtype":"article","type":"article","title":"Harnessing the power of multi-source media platforms for public perception analysis: Insights from the ohio train derailment","volume":"9","copyright":"http://creativecommons.org/licenses/by/3.0/","issn":"2504-2289","shorttitle":"Harnessing the Power of Multi-Source Media Platforms for Public Perception Analysis","url":"https://www.mdpi.com/2504-2289/9/4/88","doi":"10.3390/bdcc9040088","abstract":"Media platforms provide an effective way to gauge public perceptions, especially during mass disruption events. This research explores public responses to the 2023 Ohio train derailment event through Twitter, currently known as X, and Google Trends. It aims to unveil public sentiments and attitudes by employing sentiment analysis using the Valence Aware Dictionary and Sentiment Reasoner (VADER) and topic modeling using Latent Dirichlet Allocation (LDA) on geotagged tweets across three phases of the event: impact and immediate response, investigation, and recovery. Additionally, the Self-Organizing Map (SOM) model is employed to conduct time-series clustering analysis of Google search patterns, offering a deeper understanding into the event’s spatial and temporal impact on society. The results reveal that public perceptions related to pollution in communities exhibited an inverted U-shaped curve during the initial two phases on both the Twitter and Google Search platforms. However, in the third phase, the trends diverged. While public awareness declined on Google Search, it experienced an uptick on Twitter, a shift that can be attributed to governmental responses. Furthermore, the topics of Twitter discussions underwent a transition across three phases, changing from a focus on the causes of fires and evacuation strategies in Phase 1, to river pollution and trusteeship issues in Phase 2, and finally converging on government actions and community safety in Phase 3. Overall, this study advances a multi-platform and multi-method framework to uncover the spatiotemporal dynamics of public perception during disasters, offering actionable insights for real-time, region-specific crisis management.","language":"en","number":"4","urldate":"2025-04-07","journal":"Big Data and Cognitive Computing","author":[{"propositions":[],"lastnames":["Hu"],"firstnames":["Tao"],"suffixes":[]},{"propositions":[],"lastnames":["Huang"],"firstnames":["Xiao"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Yun"],"suffixes":[]},{"propositions":[],"lastnames":["Fu"],"firstnames":["Xiaokang"],"suffixes":[]}],"month":"April","year":"2025","keywords":"/unread, disaster management, sentiment analysis, social media, topic modeling","pages":"88","bibtex":"@article{hu_harnessing_2025,\n\ttitle = {Harnessing the power of multi-source media platforms for public perception analysis: {Insights} from the ohio train derailment},\n\tvolume = {9},\n\tcopyright = {http://creativecommons.org/licenses/by/3.0/},\n\tissn = {2504-2289},\n\tshorttitle = {Harnessing the {Power} of {Multi}-{Source} {Media} {Platforms} for {Public} {Perception} {Analysis}},\n\turl = {https://www.mdpi.com/2504-2289/9/4/88},\n\tdoi = {10.3390/bdcc9040088},\n\tabstract = {Media platforms provide an effective way to gauge public perceptions, especially during mass disruption events. This research explores public responses to the 2023 Ohio train derailment event through Twitter, currently known as X, and Google Trends. It aims to unveil public sentiments and attitudes by employing sentiment analysis using the Valence Aware Dictionary and Sentiment Reasoner (VADER) and topic modeling using Latent Dirichlet Allocation (LDA) on geotagged tweets across three phases of the event: impact and immediate response, investigation, and recovery. Additionally, the Self-Organizing Map (SOM) model is employed to conduct time-series clustering analysis of Google search patterns, offering a deeper understanding into the event’s spatial and temporal impact on society. The results reveal that public perceptions related to pollution in communities exhibited an inverted U-shaped curve during the initial two phases on both the Twitter and Google Search platforms. However, in the third phase, the trends diverged. While public awareness declined on Google Search, it experienced an uptick on Twitter, a shift that can be attributed to governmental responses. Furthermore, the topics of Twitter discussions underwent a transition across three phases, changing from a focus on the causes of fires and evacuation strategies in Phase 1, to river pollution and trusteeship issues in Phase 2, and finally converging on government actions and community safety in Phase 3. Overall, this study advances a multi-platform and multi-method framework to uncover the spatiotemporal dynamics of public perception during disasters, offering actionable insights for real-time, region-specific crisis management.},\n\tlanguage = {en},\n\tnumber = {4},\n\turldate = {2025-04-07},\n\tjournal = {Big Data and Cognitive Computing},\n\tauthor = {Hu, Tao and Huang, Xiao and Li, Yun and Fu, Xiaokang},\n\tmonth = apr,\n\tyear = {2025},\n\tkeywords = {/unread, disaster management, sentiment analysis, social media, topic modeling},\n\tpages = {88},\n}\n\n","author_short":["Hu, T.","Huang, X.","Li, Y.","Fu, X."],"key":"hu_harnessing_2025","id":"hu_harnessing_2025","bibbaseid":"hu-huang-li-fu-harnessingthepowerofmultisourcemediaplatformsforpublicperceptionanalysisinsightsfromtheohiotrainderailment-2025","role":"author","urls":{"Paper":"https://www.mdpi.com/2504-2289/9/4/88"},"keyword":["/unread","disaster management","sentiment analysis","social media","topic modeling"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/users/3636796/collections/WMCPRNWQ/items?key=2we23lDB9bc8qOnSiv0rA6d0&format=bibtex&limit=100","dataSources":["wpZCCHkYoANYp7Bcv"],"keywords":["/unread","disaster management","sentiment analysis","social media","topic modeling"],"search_terms":["harnessing","power","multi","source","media","platforms","public","perception","analysis","insights","ohio","train","derailment","hu","huang","li","fu"],"title":"Harnessing the power of multi-source media platforms for public perception analysis: Insights from the ohio train derailment","year":2025}