Leveraging the power of informative users for local event detection

Hengtong Zhang, Fenglong Ma, Yaliang Li, Chao Zhang, Tianqi Wang, Yaqing Wang, Jing Gao, Lu Su

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

1 Citation (Scopus)

Abstract

Detecting local events (e.g., protests, accidents) in real-time is an important task needed by a wide spectrum of real-world applications. In recent years, with the proliferation of social media platforms, we can access massive geo- tagged social messages, which can serve as a precious resource for timely local event detection. However, existing local event detection methods either suffer from unsatisfactory performances or need intensive annotations. These limitations make existing methods impractical for large-scale applications. Through the analysis of real-world datasets, we found that the informativeness level of social media users, which is neglected by existing work, plays a highly critical role in distilling event-related information from noisy social media contexts. Motivated by this finding, we propose an unsupervised framework, named LEDetect, to estimate the informativeness level of social media users and leverage the power of highly informative users for local event detection. Experiments on a large-scale real-world dataset show that the proposed LEDetect model can improve the performance of event detection compared with the state-of-the-art unsupervised approach. Also, we use case studies to show that the events discovered by the proposed model are of high quality and the extracted highly informative users are reasonable.

Original languageEnglish (US)
Title of host publicationProceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018
EditorsAndrea Tagarelli, Chandan Reddy, Ulrik Brandes
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages429-436
Number of pages8
ISBN (Electronic)9781538660515
DOIs
StatePublished - Oct 24 2018
Event10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018 - Barcelona, Spain
Duration: Aug 28 2018Aug 31 2018

Publication series

NameProceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018

Conference

Conference10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018
CountrySpain
CityBarcelona
Period8/28/188/31/18

Fingerprint

event
social media
Accidents
Experiments
Event detection
Social media
proliferation
protest
performance
accident
experiment
Informativeness
resources
Annotation
Resources
Leverage
Experiment
Proliferation
Protest

All Science Journal Classification (ASJC) codes

  • Sociology and Political Science
  • Communication
  • Computer Networks and Communications
  • Information Systems and Management

Cite this

Zhang, H., Ma, F., Li, Y., Zhang, C., Wang, T., Wang, Y., ... Su, L. (2018). Leveraging the power of informative users for local event detection. In A. Tagarelli, C. Reddy, & U. Brandes (Eds.), Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018 (pp. 429-436). [8508618] (Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASONAM.2018.8508618
Zhang, Hengtong ; Ma, Fenglong ; Li, Yaliang ; Zhang, Chao ; Wang, Tianqi ; Wang, Yaqing ; Gao, Jing ; Su, Lu. / Leveraging the power of informative users for local event detection. Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018. editor / Andrea Tagarelli ; Chandan Reddy ; Ulrik Brandes. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 429-436 (Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018).
@inproceedings{d504b282b9d54d8282a80f979aa4409a,
title = "Leveraging the power of informative users for local event detection",
abstract = "Detecting local events (e.g., protests, accidents) in real-time is an important task needed by a wide spectrum of real-world applications. In recent years, with the proliferation of social media platforms, we can access massive geo- tagged social messages, which can serve as a precious resource for timely local event detection. However, existing local event detection methods either suffer from unsatisfactory performances or need intensive annotations. These limitations make existing methods impractical for large-scale applications. Through the analysis of real-world datasets, we found that the informativeness level of social media users, which is neglected by existing work, plays a highly critical role in distilling event-related information from noisy social media contexts. Motivated by this finding, we propose an unsupervised framework, named LEDetect, to estimate the informativeness level of social media users and leverage the power of highly informative users for local event detection. Experiments on a large-scale real-world dataset show that the proposed LEDetect model can improve the performance of event detection compared with the state-of-the-art unsupervised approach. Also, we use case studies to show that the events discovered by the proposed model are of high quality and the extracted highly informative users are reasonable.",
author = "Hengtong Zhang and Fenglong Ma and Yaliang Li and Chao Zhang and Tianqi Wang and Yaqing Wang and Jing Gao and Lu Su",
year = "2018",
month = "10",
day = "24",
doi = "10.1109/ASONAM.2018.8508618",
language = "English (US)",
series = "Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "429--436",
editor = "Andrea Tagarelli and Chandan Reddy and Ulrik Brandes",
booktitle = "Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018",
address = "United States",

}

Zhang, H, Ma, F, Li, Y, Zhang, C, Wang, T, Wang, Y, Gao, J & Su, L 2018, Leveraging the power of informative users for local event detection. in A Tagarelli, C Reddy & U Brandes (eds), Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018., 8508618, Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018, Institute of Electrical and Electronics Engineers Inc., pp. 429-436, 10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018, Barcelona, Spain, 8/28/18. https://doi.org/10.1109/ASONAM.2018.8508618

Leveraging the power of informative users for local event detection. / Zhang, Hengtong; Ma, Fenglong; Li, Yaliang; Zhang, Chao; Wang, Tianqi; Wang, Yaqing; Gao, Jing; Su, Lu.

Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018. ed. / Andrea Tagarelli; Chandan Reddy; Ulrik Brandes. Institute of Electrical and Electronics Engineers Inc., 2018. p. 429-436 8508618 (Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018).

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

TY - GEN

T1 - Leveraging the power of informative users for local event detection

AU - Zhang, Hengtong

AU - Ma, Fenglong

AU - Li, Yaliang

AU - Zhang, Chao

AU - Wang, Tianqi

AU - Wang, Yaqing

AU - Gao, Jing

AU - Su, Lu

PY - 2018/10/24

Y1 - 2018/10/24

N2 - Detecting local events (e.g., protests, accidents) in real-time is an important task needed by a wide spectrum of real-world applications. In recent years, with the proliferation of social media platforms, we can access massive geo- tagged social messages, which can serve as a precious resource for timely local event detection. However, existing local event detection methods either suffer from unsatisfactory performances or need intensive annotations. These limitations make existing methods impractical for large-scale applications. Through the analysis of real-world datasets, we found that the informativeness level of social media users, which is neglected by existing work, plays a highly critical role in distilling event-related information from noisy social media contexts. Motivated by this finding, we propose an unsupervised framework, named LEDetect, to estimate the informativeness level of social media users and leverage the power of highly informative users for local event detection. Experiments on a large-scale real-world dataset show that the proposed LEDetect model can improve the performance of event detection compared with the state-of-the-art unsupervised approach. Also, we use case studies to show that the events discovered by the proposed model are of high quality and the extracted highly informative users are reasonable.

AB - Detecting local events (e.g., protests, accidents) in real-time is an important task needed by a wide spectrum of real-world applications. In recent years, with the proliferation of social media platforms, we can access massive geo- tagged social messages, which can serve as a precious resource for timely local event detection. However, existing local event detection methods either suffer from unsatisfactory performances or need intensive annotations. These limitations make existing methods impractical for large-scale applications. Through the analysis of real-world datasets, we found that the informativeness level of social media users, which is neglected by existing work, plays a highly critical role in distilling event-related information from noisy social media contexts. Motivated by this finding, we propose an unsupervised framework, named LEDetect, to estimate the informativeness level of social media users and leverage the power of highly informative users for local event detection. Experiments on a large-scale real-world dataset show that the proposed LEDetect model can improve the performance of event detection compared with the state-of-the-art unsupervised approach. Also, we use case studies to show that the events discovered by the proposed model are of high quality and the extracted highly informative users are reasonable.

UR - http://www.scopus.com/inward/record.url?scp=85057312540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057312540&partnerID=8YFLogxK

U2 - 10.1109/ASONAM.2018.8508618

DO - 10.1109/ASONAM.2018.8508618

M3 - Conference contribution

AN - SCOPUS:85057312540

T3 - Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018

SP - 429

EP - 436

BT - Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018

A2 - Tagarelli, Andrea

A2 - Reddy, Chandan

A2 - Brandes, Ulrik

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Zhang H, Ma F, Li Y, Zhang C, Wang T, Wang Y et al. Leveraging the power of informative users for local event detection. In Tagarelli A, Reddy C, Brandes U, editors, Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 429-436. 8508618. (Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018). https://doi.org/10.1109/ASONAM.2018.8508618