Enhancing situation awareness of public safety events by visualizing topic evolution using social media

Qing Deng, Guoray Cai, Hui Zhang, Yi Liu, Lida Huang, Feng Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Social media contributes to enhancing transparency and openness for the purpose of innovating public services and policy-making. In disaster management, social media data can be mined to discover public perceptions and concerns on large disaster events. However, converting large data streams into useful information remains a challenge due to the unstructured nature of textual data. ?is study proposes an interactive topic modeling method to analyze microblog data for understanding the dynamics of public expressions immediately a?er a major explosion event. First, we extract topics from microblog message data. In order to test the influence of the number of topics, the topics are detected at multiple levels of granularity by varying the number of topics. Second, these topics are used to detect topical compositions of contents at different time slices and assess the topic evolution over time. The topic evolution patterns are visualized by the streamgraph method to discover informative topics to help to take further actions. Third, since the first-level topics are not informative, we conduct a second-level topic (subtopic) analysis to detect key decision elements by choosing "investigation" from the first-level topics, a hot focus in any man-made disaster. The results improve our understanding of the topic composition evolution around major man-made disasters and have implications on officials deciding what and when to release formal investigation information to the public.

Original languageEnglish (US)
Title of host publicationProceedings of the 19th Annual International Conference on Digital Government Research
Subtitle of host publicationGovernance in the Data Age, DG.O 2018
EditorsCharles C. Hinnant, Anneke Zuiderwijk
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450365260
DOIs
StatePublished - May 30 2018
Event19th Annual International Conference on Digital Government Research: Governance in the Data Age, DG.O 2018 - Delf, Netherlands
Duration: May 30 2018Jun 1 2018

Publication series

NameACM International Conference Proceeding Series

Other

Other19th Annual International Conference on Digital Government Research: Governance in the Data Age, DG.O 2018
CountryNetherlands
CityDelf
Period5/30/186/1/18

Fingerprint

Disasters
Chemical analysis
Transparency
Explosions

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Cite this

Deng, Q., Cai, G., Zhang, H., Liu, Y., Huang, L., & Sun, F. (2018). Enhancing situation awareness of public safety events by visualizing topic evolution using social media. In C. C. Hinnant, & A. Zuiderwijk (Eds.), Proceedings of the 19th Annual International Conference on Digital Government Research: Governance in the Data Age, DG.O 2018 [a7] (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3209281.3209378
Deng, Qing ; Cai, Guoray ; Zhang, Hui ; Liu, Yi ; Huang, Lida ; Sun, Feng. / Enhancing situation awareness of public safety events by visualizing topic evolution using social media. Proceedings of the 19th Annual International Conference on Digital Government Research: Governance in the Data Age, DG.O 2018. editor / Charles C. Hinnant ; Anneke Zuiderwijk. Association for Computing Machinery, 2018. (ACM International Conference Proceeding Series).
@inproceedings{7011d7127ac641439d5a4f9585bfdfea,
title = "Enhancing situation awareness of public safety events by visualizing topic evolution using social media",
abstract = "Social media contributes to enhancing transparency and openness for the purpose of innovating public services and policy-making. In disaster management, social media data can be mined to discover public perceptions and concerns on large disaster events. However, converting large data streams into useful information remains a challenge due to the unstructured nature of textual data. ?is study proposes an interactive topic modeling method to analyze microblog data for understanding the dynamics of public expressions immediately a?er a major explosion event. First, we extract topics from microblog message data. In order to test the influence of the number of topics, the topics are detected at multiple levels of granularity by varying the number of topics. Second, these topics are used to detect topical compositions of contents at different time slices and assess the topic evolution over time. The topic evolution patterns are visualized by the streamgraph method to discover informative topics to help to take further actions. Third, since the first-level topics are not informative, we conduct a second-level topic (subtopic) analysis to detect key decision elements by choosing {"}investigation{"} from the first-level topics, a hot focus in any man-made disaster. The results improve our understanding of the topic composition evolution around major man-made disasters and have implications on officials deciding what and when to release formal investigation information to the public.",
author = "Qing Deng and Guoray Cai and Hui Zhang and Yi Liu and Lida Huang and Feng Sun",
year = "2018",
month = "5",
day = "30",
doi = "10.1145/3209281.3209378",
language = "English (US)",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
editor = "Hinnant, {Charles C.} and Anneke Zuiderwijk",
booktitle = "Proceedings of the 19th Annual International Conference on Digital Government Research",

}

Deng, Q, Cai, G, Zhang, H, Liu, Y, Huang, L & Sun, F 2018, Enhancing situation awareness of public safety events by visualizing topic evolution using social media. in CC Hinnant & A Zuiderwijk (eds), Proceedings of the 19th Annual International Conference on Digital Government Research: Governance in the Data Age, DG.O 2018., a7, ACM International Conference Proceeding Series, Association for Computing Machinery, 19th Annual International Conference on Digital Government Research: Governance in the Data Age, DG.O 2018, Delf, Netherlands, 5/30/18. https://doi.org/10.1145/3209281.3209378

Enhancing situation awareness of public safety events by visualizing topic evolution using social media. / Deng, Qing; Cai, Guoray; Zhang, Hui; Liu, Yi; Huang, Lida; Sun, Feng.

Proceedings of the 19th Annual International Conference on Digital Government Research: Governance in the Data Age, DG.O 2018. ed. / Charles C. Hinnant; Anneke Zuiderwijk. Association for Computing Machinery, 2018. a7 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Enhancing situation awareness of public safety events by visualizing topic evolution using social media

AU - Deng, Qing

AU - Cai, Guoray

AU - Zhang, Hui

AU - Liu, Yi

AU - Huang, Lida

AU - Sun, Feng

PY - 2018/5/30

Y1 - 2018/5/30

N2 - Social media contributes to enhancing transparency and openness for the purpose of innovating public services and policy-making. In disaster management, social media data can be mined to discover public perceptions and concerns on large disaster events. However, converting large data streams into useful information remains a challenge due to the unstructured nature of textual data. ?is study proposes an interactive topic modeling method to analyze microblog data for understanding the dynamics of public expressions immediately a?er a major explosion event. First, we extract topics from microblog message data. In order to test the influence of the number of topics, the topics are detected at multiple levels of granularity by varying the number of topics. Second, these topics are used to detect topical compositions of contents at different time slices and assess the topic evolution over time. The topic evolution patterns are visualized by the streamgraph method to discover informative topics to help to take further actions. Third, since the first-level topics are not informative, we conduct a second-level topic (subtopic) analysis to detect key decision elements by choosing "investigation" from the first-level topics, a hot focus in any man-made disaster. The results improve our understanding of the topic composition evolution around major man-made disasters and have implications on officials deciding what and when to release formal investigation information to the public.

AB - Social media contributes to enhancing transparency and openness for the purpose of innovating public services and policy-making. In disaster management, social media data can be mined to discover public perceptions and concerns on large disaster events. However, converting large data streams into useful information remains a challenge due to the unstructured nature of textual data. ?is study proposes an interactive topic modeling method to analyze microblog data for understanding the dynamics of public expressions immediately a?er a major explosion event. First, we extract topics from microblog message data. In order to test the influence of the number of topics, the topics are detected at multiple levels of granularity by varying the number of topics. Second, these topics are used to detect topical compositions of contents at different time slices and assess the topic evolution over time. The topic evolution patterns are visualized by the streamgraph method to discover informative topics to help to take further actions. Third, since the first-level topics are not informative, we conduct a second-level topic (subtopic) analysis to detect key decision elements by choosing "investigation" from the first-level topics, a hot focus in any man-made disaster. The results improve our understanding of the topic composition evolution around major man-made disasters and have implications on officials deciding what and when to release formal investigation information to the public.

UR - http://www.scopus.com/inward/record.url?scp=85049032321&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049032321&partnerID=8YFLogxK

U2 - 10.1145/3209281.3209378

DO - 10.1145/3209281.3209378

M3 - Conference contribution

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the 19th Annual International Conference on Digital Government Research

A2 - Hinnant, Charles C.

A2 - Zuiderwijk, Anneke

PB - Association for Computing Machinery

ER -

Deng Q, Cai G, Zhang H, Liu Y, Huang L, Sun F. Enhancing situation awareness of public safety events by visualizing topic evolution using social media. In Hinnant CC, Zuiderwijk A, editors, Proceedings of the 19th Annual International Conference on Digital Government Research: Governance in the Data Age, DG.O 2018. Association for Computing Machinery. 2018. a7. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3209281.3209378