Summarizing situational tweets in crisis scenario

Koustav Rudra, Siddhartha Banerjee, Niloy Ganguly, Pawan Goyal, Muhammad Imran, Prasenjit Mitra

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

30 Citations (Scopus)

Abstract

During mass convergence events such as natural disasters, microblogging platforms like Twitter are widely used by affected people to post situational awareness messages. These crisis-related messages disperse among multiple categories like infrastructure damage, information about missing, injured, and dead people etc. The challenge here is to extract important situational updates from these messages, assign them appropriate informational categories, and finally summarize big trove of information in each category. In this paper, we propose a novel framework which first assigns tweets into different situational classes and then summarize those tweets. In the summarization phase, we propose a two stage summarization framework which first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique and then follows a word graph and content word based abstractive summarization technique to produce the final summary. Our method is time and memory efficient and outperforms the baseline in terms of quality, coverage of events, locations et al., effectiveness, and utility in disaster scenarios.

Original languageEnglish (US)
Title of host publicationHT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media
PublisherAssociation for Computing Machinery, Inc
Pages137-147
Number of pages11
ISBN (Electronic)9781450342476
DOIs
StatePublished - Jul 10 2016
Event27th ACM Conference on Hypertext and Social Media, HT 2016 - Halifax, Canada
Duration: Jul 10 2016Jul 13 2016

Publication series

NameHT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media

Other

Other27th ACM Conference on Hypertext and Social Media, HT 2016
CountryCanada
CityHalifax
Period7/10/167/13/16

Fingerprint

Disasters
Linear programming
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Software
  • Artificial Intelligence

Cite this

Rudra, K., Banerjee, S., Ganguly, N., Goyal, P., Imran, M., & Mitra, P. (2016). Summarizing situational tweets in crisis scenario. In HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media (pp. 137-147). (HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media). Association for Computing Machinery, Inc. https://doi.org/10.1145/2914586.2914600
Rudra, Koustav ; Banerjee, Siddhartha ; Ganguly, Niloy ; Goyal, Pawan ; Imran, Muhammad ; Mitra, Prasenjit. / Summarizing situational tweets in crisis scenario. HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, 2016. pp. 137-147 (HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media).
@inproceedings{753e8e30cd22439084e746659f843324,
title = "Summarizing situational tweets in crisis scenario",
abstract = "During mass convergence events such as natural disasters, microblogging platforms like Twitter are widely used by affected people to post situational awareness messages. These crisis-related messages disperse among multiple categories like infrastructure damage, information about missing, injured, and dead people etc. The challenge here is to extract important situational updates from these messages, assign them appropriate informational categories, and finally summarize big trove of information in each category. In this paper, we propose a novel framework which first assigns tweets into different situational classes and then summarize those tweets. In the summarization phase, we propose a two stage summarization framework which first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique and then follows a word graph and content word based abstractive summarization technique to produce the final summary. Our method is time and memory efficient and outperforms the baseline in terms of quality, coverage of events, locations et al., effectiveness, and utility in disaster scenarios.",
author = "Koustav Rudra and Siddhartha Banerjee and Niloy Ganguly and Pawan Goyal and Muhammad Imran and Prasenjit Mitra",
year = "2016",
month = "7",
day = "10",
doi = "10.1145/2914586.2914600",
language = "English (US)",
series = "HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media",
publisher = "Association for Computing Machinery, Inc",
pages = "137--147",
booktitle = "HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media",

}

Rudra, K, Banerjee, S, Ganguly, N, Goyal, P, Imran, M & Mitra, P 2016, Summarizing situational tweets in crisis scenario. in HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media. HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media, Association for Computing Machinery, Inc, pp. 137-147, 27th ACM Conference on Hypertext and Social Media, HT 2016, Halifax, Canada, 7/10/16. https://doi.org/10.1145/2914586.2914600

Summarizing situational tweets in crisis scenario. / Rudra, Koustav; Banerjee, Siddhartha; Ganguly, Niloy; Goyal, Pawan; Imran, Muhammad; Mitra, Prasenjit.

HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, 2016. p. 137-147 (HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media).

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

TY - GEN

T1 - Summarizing situational tweets in crisis scenario

AU - Rudra, Koustav

AU - Banerjee, Siddhartha

AU - Ganguly, Niloy

AU - Goyal, Pawan

AU - Imran, Muhammad

AU - Mitra, Prasenjit

PY - 2016/7/10

Y1 - 2016/7/10

N2 - During mass convergence events such as natural disasters, microblogging platforms like Twitter are widely used by affected people to post situational awareness messages. These crisis-related messages disperse among multiple categories like infrastructure damage, information about missing, injured, and dead people etc. The challenge here is to extract important situational updates from these messages, assign them appropriate informational categories, and finally summarize big trove of information in each category. In this paper, we propose a novel framework which first assigns tweets into different situational classes and then summarize those tweets. In the summarization phase, we propose a two stage summarization framework which first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique and then follows a word graph and content word based abstractive summarization technique to produce the final summary. Our method is time and memory efficient and outperforms the baseline in terms of quality, coverage of events, locations et al., effectiveness, and utility in disaster scenarios.

AB - During mass convergence events such as natural disasters, microblogging platforms like Twitter are widely used by affected people to post situational awareness messages. These crisis-related messages disperse among multiple categories like infrastructure damage, information about missing, injured, and dead people etc. The challenge here is to extract important situational updates from these messages, assign them appropriate informational categories, and finally summarize big trove of information in each category. In this paper, we propose a novel framework which first assigns tweets into different situational classes and then summarize those tweets. In the summarization phase, we propose a two stage summarization framework which first extracts a set of important tweets from the whole set of information through an Integer-linear programming (ILP) based optimization technique and then follows a word graph and content word based abstractive summarization technique to produce the final summary. Our method is time and memory efficient and outperforms the baseline in terms of quality, coverage of events, locations et al., effectiveness, and utility in disaster scenarios.

UR - http://www.scopus.com/inward/record.url?scp=84980417191&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84980417191&partnerID=8YFLogxK

U2 - 10.1145/2914586.2914600

DO - 10.1145/2914586.2914600

M3 - Conference contribution

T3 - HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media

SP - 137

EP - 147

BT - HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media

PB - Association for Computing Machinery, Inc

ER -

Rudra K, Banerjee S, Ganguly N, Goyal P, Imran M, Mitra P. Summarizing situational tweets in crisis scenario. In HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc. 2016. p. 137-147. (HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media). https://doi.org/10.1145/2914586.2914600