Towards a data-driven approach to identify crisis-related topics in social media streams

Muhammad Imran, Carlos Castillo

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

15 Citations (Scopus)

Abstract

While categorizing any type of user-generated content online is a challenging problem, categorizing social media messages during a crisis situation adds an additional layer of complex- ity, due to the volume and variability of information, and to the fact that these messages must be classified as soon as they arrive. Current approaches involve the use of au- tomaticspecification, humanspecification, or a mixture of both. In these types of approaches, there are several reasons to keep the number of information categories small and up- dated, which we examine in this article. This means at the onset of a crisis an expert must select a handful of informa- tion categories into which information will be categorized. The next step, as the crisis unfolds, is to dynamically change the initial set as new information is posted online. In this paper, we propose an effective way to dynamically extract emerging, potentially interesting, new categories from social media data.

Original languageEnglish
Title of host publicationWWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web
PublisherAssociation for Computing Machinery, Inc
Pages1205-1210
Number of pages6
ISBN (Print)9781450334730
DOIs
Publication statusPublished - 18 May 2015
Event24th International Conference on World Wide Web, WWW 2015 - Florence, Italy
Duration: 18 May 201522 May 2015

Other

Other24th International Conference on World Wide Web, WWW 2015
CountryItaly
CityFlorence
Period18/5/1522/5/15

Keywords

  • Information types
  • Social media content analysis
  • Stream classification
  • Text classification

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Cite this

Imran, M., & Castillo, C. (2015). Towards a data-driven approach to identify crisis-related topics in social media streams. In WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web (pp. 1205-1210). Association for Computing Machinery, Inc. https://doi.org/10.1145/2740908.2741729

Towards a data-driven approach to identify crisis-related topics in social media streams. / Imran, Muhammad; Castillo, Carlos.

WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web. Association for Computing Machinery, Inc, 2015. p. 1205-1210.

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

Imran, M & Castillo, C 2015, Towards a data-driven approach to identify crisis-related topics in social media streams. in WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web. Association for Computing Machinery, Inc, pp. 1205-1210, 24th International Conference on World Wide Web, WWW 2015, Florence, Italy, 18/5/15. https://doi.org/10.1145/2740908.2741729
Imran M, Castillo C. Towards a data-driven approach to identify crisis-related topics in social media streams. In WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web. Association for Computing Machinery, Inc. 2015. p. 1205-1210 https://doi.org/10.1145/2740908.2741729
Imran, Muhammad ; Castillo, Carlos. / Towards a data-driven approach to identify crisis-related topics in social media streams. WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web. Association for Computing Machinery, Inc, 2015. pp. 1205-1210
@inproceedings{1c131e2235f44dfb91dfa69496dbfd30,
title = "Towards a data-driven approach to identify crisis-related topics in social media streams",
abstract = "While categorizing any type of user-generated content online is a challenging problem, categorizing social media messages during a crisis situation adds an additional layer of complex- ity, due to the volume and variability of information, and to the fact that these messages must be classified as soon as they arrive. Current approaches involve the use of au- tomaticspecification, humanspecification, or a mixture of both. In these types of approaches, there are several reasons to keep the number of information categories small and up- dated, which we examine in this article. This means at the onset of a crisis an expert must select a handful of informa- tion categories into which information will be categorized. The next step, as the crisis unfolds, is to dynamically change the initial set as new information is posted online. In this paper, we propose an effective way to dynamically extract emerging, potentially interesting, new categories from social media data.",
keywords = "Information types, Social media content analysis, Stream classification, Text classification",
author = "Muhammad Imran and Carlos Castillo",
year = "2015",
month = "5",
day = "18",
doi = "10.1145/2740908.2741729",
language = "English",
isbn = "9781450334730",
pages = "1205--1210",
booktitle = "WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Towards a data-driven approach to identify crisis-related topics in social media streams

AU - Imran, Muhammad

AU - Castillo, Carlos

PY - 2015/5/18

Y1 - 2015/5/18

N2 - While categorizing any type of user-generated content online is a challenging problem, categorizing social media messages during a crisis situation adds an additional layer of complex- ity, due to the volume and variability of information, and to the fact that these messages must be classified as soon as they arrive. Current approaches involve the use of au- tomaticspecification, humanspecification, or a mixture of both. In these types of approaches, there are several reasons to keep the number of information categories small and up- dated, which we examine in this article. This means at the onset of a crisis an expert must select a handful of informa- tion categories into which information will be categorized. The next step, as the crisis unfolds, is to dynamically change the initial set as new information is posted online. In this paper, we propose an effective way to dynamically extract emerging, potentially interesting, new categories from social media data.

AB - While categorizing any type of user-generated content online is a challenging problem, categorizing social media messages during a crisis situation adds an additional layer of complex- ity, due to the volume and variability of information, and to the fact that these messages must be classified as soon as they arrive. Current approaches involve the use of au- tomaticspecification, humanspecification, or a mixture of both. In these types of approaches, there are several reasons to keep the number of information categories small and up- dated, which we examine in this article. This means at the onset of a crisis an expert must select a handful of informa- tion categories into which information will be categorized. The next step, as the crisis unfolds, is to dynamically change the initial set as new information is posted online. In this paper, we propose an effective way to dynamically extract emerging, potentially interesting, new categories from social media data.

KW - Information types

KW - Social media content analysis

KW - Stream classification

KW - Text classification

UR - http://www.scopus.com/inward/record.url?scp=84968552344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84968552344&partnerID=8YFLogxK

U2 - 10.1145/2740908.2741729

DO - 10.1145/2740908.2741729

M3 - Conference contribution

SN - 9781450334730

SP - 1205

EP - 1210

BT - WWW 2015 Companion - Proceedings of the 24th International Conference on World Wide Web

PB - Association for Computing Machinery, Inc

ER -