EnDSUM: Entropy and Diversity based Disaster Tweet Summarization

Piyush Kumar Garg; Roshni Chakraborty; Sourav Kumar Dandapat

EnDSUM: Entropy and Diversity based Disaster Tweet Summarization

Piyush Kumar Garg^*, Roshni Chakraborty, Sourav Kumar Dandapat

^*Corresponding author for this work

Research output: Contribution to journal › Conference article in Journal › Research › peer-review

2 Citations (Scopus)

Abstract

The huge amount of information shared in Twitter during disaster events are utilized by government agencies and humanitarian organizations to ensure quick crisis response and provide situational updates. However, the huge number of tweets posted makes manual identification of the relevant tweets impossible. To address the information overload, there is a need to automatically generate summary of all the tweets which can highlight the important aspects of the disaster. In this paper, we propose an entropy and diversity based summarizer, termed as EnDSUM, specifically for disaster tweet summarization. Our comprehensive analysis on 6 datasets indicates the effectiveness of EnDSUM and additionally, highlights the scope of improvement of EnDSUM.

Original language	English
Journal	CEUR Workshop Proceedings
Volume	3117
Pages (from-to)	91-96
Number of pages	6
ISSN	1613-0073
Publication status	Published - 2022
Event	5th Workshop on Narrative Extraction From Texts, Text2Story 2022 - Stavanger, Norway Duration: 10 Apr 2022 → …

Conference

Conference	5th Workshop on Narrative Extraction From Texts, Text2Story 2022
Country/Territory	Norway
City	Stavanger
Period	10/04/2022 → …

Bibliographical note

Publisher Copyright:
© 2021 Copyright for this paper by its authors

Keywords

Disaster tweets
Entropy
Social media
Summarization

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{e5e8937c7d024331a09db4a2472e5d6d,

title = "EnDSUM: Entropy and Diversity based Disaster Tweet Summarization",

abstract = "The huge amount of information shared in Twitter during disaster events are utilized by government agencies and humanitarian organizations to ensure quick crisis response and provide situational updates. However, the huge number of tweets posted makes manual identification of the relevant tweets impossible. To address the information overload, there is a need to automatically generate summary of all the tweets which can highlight the important aspects of the disaster. In this paper, we propose an entropy and diversity based summarizer, termed as EnDSUM, specifically for disaster tweet summarization. Our comprehensive analysis on 6 datasets indicates the effectiveness of EnDSUM and additionally, highlights the scope of improvement of EnDSUM.",

keywords = "Disaster tweets, Entropy, Social media, Summarization",

author = "Garg, {Piyush Kumar} and Roshni Chakraborty and Dandapat, {Sourav Kumar}",

note = "Publisher Copyright: {\textcopyright} 2021 Copyright for this paper by its authors; 5th Workshop on Narrative Extraction From Texts, Text2Story 2022 ; Conference date: 10-04-2022",

year = "2022",

language = "English",

volume = "3117",

pages = "91--96",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR Workshop Proceedings",

}

TY - GEN

T1 - EnDSUM

T2 - 5th Workshop on Narrative Extraction From Texts, Text2Story 2022

AU - Garg, Piyush Kumar

AU - Chakraborty, Roshni

AU - Dandapat, Sourav Kumar

PY - 2022

Y1 - 2022

N2 - The huge amount of information shared in Twitter during disaster events are utilized by government agencies and humanitarian organizations to ensure quick crisis response and provide situational updates. However, the huge number of tweets posted makes manual identification of the relevant tweets impossible. To address the information overload, there is a need to automatically generate summary of all the tweets which can highlight the important aspects of the disaster. In this paper, we propose an entropy and diversity based summarizer, termed as EnDSUM, specifically for disaster tweet summarization. Our comprehensive analysis on 6 datasets indicates the effectiveness of EnDSUM and additionally, highlights the scope of improvement of EnDSUM.

AB - The huge amount of information shared in Twitter during disaster events are utilized by government agencies and humanitarian organizations to ensure quick crisis response and provide situational updates. However, the huge number of tweets posted makes manual identification of the relevant tweets impossible. To address the information overload, there is a need to automatically generate summary of all the tweets which can highlight the important aspects of the disaster. In this paper, we propose an entropy and diversity based summarizer, termed as EnDSUM, specifically for disaster tweet summarization. Our comprehensive analysis on 6 datasets indicates the effectiveness of EnDSUM and additionally, highlights the scope of improvement of EnDSUM.

KW - Disaster tweets

KW - Entropy

KW - Social media

KW - Summarization

UR - http://www.scopus.com/inward/record.url?scp=85128771771&partnerID=8YFLogxK

M3 - Conference article in Journal

AN - SCOPUS:85128771771

SN - 1613-0073

VL - 3117

SP - 91

EP - 96

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 10 April 2022

ER -

EnDSUM: Entropy and Diversity based Disaster Tweet Summarization

Abstract

Conference

Bibliographical note

Keywords

AUB Link

Other files and links

Fingerprint

Cite this