Cross-lingual query expansion in multilingual folksonomies: A case study on Flickr

  • Authors:

  • Jason J. Jung

  • Affiliations:

  • Department of Computer Engineering, Yeungnam University, Republic of Korea

  • Venue:
  • Knowledge-Based Systems
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Many studies on folksonomy analysis have focused on discovering meaningful patterns between three main entities (i.e., users, tags, and resources) from a folksonomy system to provide various information services to users. However, most of them have simply assumed that the tags in the folksonomy are written in a same language, i.e., any tags can be compared with others. In this work, multilingual folksonomies are focused to discover useful matchings between multilingual tags (e.g., among 'Korea' in English, Coreia in Portuguese and 'Coree' in French). Moreover, such matchings can be applied to expand user queries to retrieve additional resources tagged by the other languages. We focus on analyzing a multilingual folksonomy generated by various lingual practices of online users, and discovering meaningful relationships between multilingual tags (e.g., between 'Seoul' in English and 'Coree' in French) co-occurred in the folksonomy. Thereby, we propose novel methods for (i) identifying lingual practices from user tagging patterns to build community of lingual practice and (ii) exploiting the tag matchings to extend simple term-based queries. Thus, additional resources tagged by other languages can be retrieved. To evaluate the proposed multilingual tag matching method, we have collected real tagging datasets from several well-known social tagging websites (e.g., Del.icio.us), and applied to translating queries to other languages without any external dictionaries.