Summarizing Situational Tweets in Crisis Scenarios: An Extractive-Abstractive Approach

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

Research output: Contribution to journalArticle

Abstract

Microblogging platforms such as Twitter are widely used by eyewitnesses and affected people to post situational updates during mass convergence events such as natural and man-made disasters. These crisis-related messages disperse among multiple classes/categories such as infrastructure damage, shelter needs, information about missing, injured, and dead people. Moreover, we observe that sometimes people post information about their missing relatives and friends with personal details such as names and last seen location. The information requirements of different stakeholders (government, NGOs, and rescue workers) also vary a lot. This brings twofold challenges: 1) extracting important high-level situational updates from these messages, assigning them appropriate categories, and finally summarizing big trove of information in each category and 2) extracting small-scale time-critical sparse updates related to missing or trapped people. In this article, we propose a classification-summarization framework which first assigns tweets into different situational classes and then summarizes those tweets. In the summarization phase, we propose a two-step extractive-abstractive summarization framework. In the first step, it extracts a set of important tweets from the whole set of information, develops a bigram-based word-graph from those tweets, and generates paths by traversing the word-graph. Next, it uses an optimization technique based on integer linear programming (ILP) to select the most important tweets and paths based on different optimization parameters such as informativeness and coverage of content words. Apart from general classwise summarization, we also show the customization of our summarization model to address time-critical sparse information needs (e.g., missing relatives). Our proposed method is time- and memory-efficient and shows better performance than state-of-the-art methods in terms of both quantitative and qualitative judgment.

Original languageEnglish (US)
Article number8839735
Pages (from-to)981-993
Number of pages13
JournalIEEE Transactions on Computational Social Systems
Volume6
Issue number5
DOIs
StatePublished - Oct 1 2019

Fingerprint

Summarization
scenario
Scenarios
Linear programming
Disasters
Update
Data storage equipment
Path
twitter
Customization
Integer Linear Programming
Parameter Optimization
Graph in graph theory
Disaster
Optimization Techniques
non-governmental organization
Assign
Crisis
disaster
Time Scales

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Social Sciences (miscellaneous)
  • Human-Computer Interaction

Cite this

Rudra, Koustav ; Goyal, Pawan ; Ganguly, Niloy ; Imran, Muhammad ; Mitra, Prasenjit. / Summarizing Situational Tweets in Crisis Scenarios : An Extractive-Abstractive Approach. In: IEEE Transactions on Computational Social Systems. 2019 ; Vol. 6, No. 5. pp. 981-993.
@article{e50d0c83aed14897868b36b6db4621dd,
title = "Summarizing Situational Tweets in Crisis Scenarios: An Extractive-Abstractive Approach",
abstract = "Microblogging platforms such as Twitter are widely used by eyewitnesses and affected people to post situational updates during mass convergence events such as natural and man-made disasters. These crisis-related messages disperse among multiple classes/categories such as infrastructure damage, shelter needs, information about missing, injured, and dead people. Moreover, we observe that sometimes people post information about their missing relatives and friends with personal details such as names and last seen location. The information requirements of different stakeholders (government, NGOs, and rescue workers) also vary a lot. This brings twofold challenges: 1) extracting important high-level situational updates from these messages, assigning them appropriate categories, and finally summarizing big trove of information in each category and 2) extracting small-scale time-critical sparse updates related to missing or trapped people. In this article, we propose a classification-summarization framework which first assigns tweets into different situational classes and then summarizes those tweets. In the summarization phase, we propose a two-step extractive-abstractive summarization framework. In the first step, it extracts a set of important tweets from the whole set of information, develops a bigram-based word-graph from those tweets, and generates paths by traversing the word-graph. Next, it uses an optimization technique based on integer linear programming (ILP) to select the most important tweets and paths based on different optimization parameters such as informativeness and coverage of content words. Apart from general classwise summarization, we also show the customization of our summarization model to address time-critical sparse information needs (e.g., missing relatives). Our proposed method is time- and memory-efficient and shows better performance than state-of-the-art methods in terms of both quantitative and qualitative judgment.",
author = "Koustav Rudra and Pawan Goyal and Niloy Ganguly and Muhammad Imran and Prasenjit Mitra",
year = "2019",
month = "10",
day = "1",
doi = "10.1109/TCSS.2019.2937899",
language = "English (US)",
volume = "6",
pages = "981--993",
journal = "IEEE Transactions on Computational Social Systems",
issn = "2329-924X",
publisher = "IEEE Systems, Man, and Cybernetics Society",
number = "5",

}

Summarizing Situational Tweets in Crisis Scenarios : An Extractive-Abstractive Approach. / Rudra, Koustav; Goyal, Pawan; Ganguly, Niloy; Imran, Muhammad; Mitra, Prasenjit.

In: IEEE Transactions on Computational Social Systems, Vol. 6, No. 5, 8839735, 01.10.2019, p. 981-993.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Summarizing Situational Tweets in Crisis Scenarios

T2 - An Extractive-Abstractive Approach

AU - Rudra, Koustav

AU - Goyal, Pawan

AU - Ganguly, Niloy

AU - Imran, Muhammad

AU - Mitra, Prasenjit

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Microblogging platforms such as Twitter are widely used by eyewitnesses and affected people to post situational updates during mass convergence events such as natural and man-made disasters. These crisis-related messages disperse among multiple classes/categories such as infrastructure damage, shelter needs, information about missing, injured, and dead people. Moreover, we observe that sometimes people post information about their missing relatives and friends with personal details such as names and last seen location. The information requirements of different stakeholders (government, NGOs, and rescue workers) also vary a lot. This brings twofold challenges: 1) extracting important high-level situational updates from these messages, assigning them appropriate categories, and finally summarizing big trove of information in each category and 2) extracting small-scale time-critical sparse updates related to missing or trapped people. In this article, we propose a classification-summarization framework which first assigns tweets into different situational classes and then summarizes those tweets. In the summarization phase, we propose a two-step extractive-abstractive summarization framework. In the first step, it extracts a set of important tweets from the whole set of information, develops a bigram-based word-graph from those tweets, and generates paths by traversing the word-graph. Next, it uses an optimization technique based on integer linear programming (ILP) to select the most important tweets and paths based on different optimization parameters such as informativeness and coverage of content words. Apart from general classwise summarization, we also show the customization of our summarization model to address time-critical sparse information needs (e.g., missing relatives). Our proposed method is time- and memory-efficient and shows better performance than state-of-the-art methods in terms of both quantitative and qualitative judgment.

AB - Microblogging platforms such as Twitter are widely used by eyewitnesses and affected people to post situational updates during mass convergence events such as natural and man-made disasters. These crisis-related messages disperse among multiple classes/categories such as infrastructure damage, shelter needs, information about missing, injured, and dead people. Moreover, we observe that sometimes people post information about their missing relatives and friends with personal details such as names and last seen location. The information requirements of different stakeholders (government, NGOs, and rescue workers) also vary a lot. This brings twofold challenges: 1) extracting important high-level situational updates from these messages, assigning them appropriate categories, and finally summarizing big trove of information in each category and 2) extracting small-scale time-critical sparse updates related to missing or trapped people. In this article, we propose a classification-summarization framework which first assigns tweets into different situational classes and then summarizes those tweets. In the summarization phase, we propose a two-step extractive-abstractive summarization framework. In the first step, it extracts a set of important tweets from the whole set of information, develops a bigram-based word-graph from those tweets, and generates paths by traversing the word-graph. Next, it uses an optimization technique based on integer linear programming (ILP) to select the most important tweets and paths based on different optimization parameters such as informativeness and coverage of content words. Apart from general classwise summarization, we also show the customization of our summarization model to address time-critical sparse information needs (e.g., missing relatives). Our proposed method is time- and memory-efficient and shows better performance than state-of-the-art methods in terms of both quantitative and qualitative judgment.

UR - http://www.scopus.com/inward/record.url?scp=85072522966&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072522966&partnerID=8YFLogxK

U2 - 10.1109/TCSS.2019.2937899

DO - 10.1109/TCSS.2019.2937899

M3 - Article

AN - SCOPUS:85072522966

VL - 6

SP - 981

EP - 993

JO - IEEE Transactions on Computational Social Systems

JF - IEEE Transactions on Computational Social Systems

SN - 2329-924X

IS - 5

M1 - 8839735

ER -