Tower of babel: A crowdsourcing game building sentiment lexicons for resource-scarce languages

Yoonsung Hong, Haewoon Kwak, Youngmin Baek, Sue Moon

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

8 Citations (Scopus)

Abstract

With the growing amount of textual data produced by online social media today, the demands for sentiment analysis are also rapidly increasing; and, this is true for worldwide. However, non-English languages often lack sentiment lexicons, a core resource in performing sentiment analysis. Our solution, Tower of Babel (ToB), is a language-independent sentiment-lexicon-generating crowdsourcing game. We conducted an experiment with 135 participants to explore the difference between our solution and a conventional manual annotation method. We evaluated ToB in terms of effectiveness, efficiency, and satisfactions. Based on the result of the evaluation, we conclude that sentiment classification via ToB is accurate, productive and enjoyable.

Original languageEnglish
Title of host publicationWWW 2013 Companion - Proceedings of the 22nd International Conference on World Wide Web
Pages549-556
Number of pages8
Publication statusPublished - 1 Dec 2013
Event22nd International Conference on World Wide Web, WWW 2013 - Rio de Janeiro, Brazil
Duration: 13 May 201317 May 2013

Publication series

NameWWW 2013 Companion - Proceedings of the 22nd International Conference on World Wide Web

Other

Other22nd International Conference on World Wide Web, WWW 2013
CountryBrazil
CityRio de Janeiro
Period13/5/1317/5/13

    Fingerprint

Keywords

  • Distributed knowledge acquisition
  • Lexicon construction
  • Online games
  • Sentiment labeling
  • Worldwideweb

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Hong, Y., Kwak, H., Baek, Y., & Moon, S. (2013). Tower of babel: A crowdsourcing game building sentiment lexicons for resource-scarce languages. In WWW 2013 Companion - Proceedings of the 22nd International Conference on World Wide Web (pp. 549-556). (WWW 2013 Companion - Proceedings of the 22nd International Conference on World Wide Web).