Harnessing linked knowledge sources for topic classification in social media

Amparo E. Cano, Andrea Varga, Matthew Rowe, Fabio Ciravegna, Yulan He

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

Abstract

Topic classification (TC) of short text messages offers an effective and fast way to reveal events happening around the world ranging from those related to Disaster (e.g. Sandy hurricane) to those related to Violence (e.g. Egypt revolution). Previous approaches to TC have mostly focused on exploiting individual knowledge sources (KS) (e.g. DBpedia or Freebase) without considering the graph structures that surround concepts present in KSs when detecting the topics of Tweets. In this paper we introduce a novel approach for harnessing such graph structures from multiple linked KSs, by: (i) building a conceptual representation of the KSs, (ii) leveraging contextual information about concepts by exploiting semantic concept graphs, and (iii) providing a principled way for the combination of KSs. Experiments evaluating our TC classifier in the context of Violence detection (VD) and Emergency Responses (ER) show promising results that significantly outperform various baseline models including an approach using a single KS without linked data and an approach using only Tweets.

Original languageEnglish
Title of host publicationProceedings of the 24th ACM conference on hypertext and social media, HT '13
Place of PublicationNew York, NY (US)
PublisherACM
Pages41-50
Number of pages10
ISBN (Print)978-1-4503-1967-6
DOIs
Publication statusPublished - 10 Jul 2013
Event24th ACM conference on Hypertext and social media - Paris, France
Duration: 1 May 20133 May 2013

Conference

Conference24th ACM conference on Hypertext and social media
Abbreviated titleHypertext 2013
CountryFrance
CityParis
Period1/05/133/05/13

Keywords

  • emergency response
  • linked knowledge sources
  • named entities
  • semantic concept graphs
  • violence detection

Fingerprint Dive into the research topics of 'Harnessing linked knowledge sources for topic classification in social media'. Together they form a unique fingerprint.

  • Research Output

    • 2 Conference publication

    A question of complexity: measuring the maturity of online enquiry communities

    Burel, G. & He, Y., 10 Jul 2013, Proceedings of the 24th ACM conference on hypertext and social media, HT '13. New York, NY (US): ACM, p. 1-10 10 p.

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

  • Mainstream media behavior analysis on Twitter: a case study on UK general election

    Wei, Z., He, Y., Gao, W., Li, B., Zhou, L. & Wong, K-F., 10 Jul 2013, Proceedings of the 24th ACM conference on hypertext and social media, HT '13. New York, NY (US): ACM, p. 174-178 5 p.

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

  • Cite this

    Cano, A. E., Varga, A., Rowe, M., Ciravegna, F., & He, Y. (2013). Harnessing linked knowledge sources for topic classification in social media. In Proceedings of the 24th ACM conference on hypertext and social media, HT '13 (pp. 41-50). ACM. https://doi.org/10.1145/2481492.2481497