NLP support for faceted navigation in scholarly collections

  • Authors:
  • Marti A. Hearst;Emilia Stoica

  • Affiliations:
  • UC Berkeley, Berkeley, CA;Ask.com, Oakland, CA

  • Venue:
  • NLPIR4DL '09 Proceedings of the 2009 Workshop on Text and Citation Analysis for Scholarly Digital Libraries
  • Year:
  • 2009

Quantified Score

Hi-index 0.01

Visualization

Abstract

Hierarchical faceted metadata is a proven and popular approach to organizing information for navigation of information collections. More recently, digital libraries have begun to adopt faceted navigation for collections of scholarly holdings. A key impediment to further adoption is the need for the creation of subject-oriented faceted metadata. The Castanet algorithm was developed for the purpose of (semi) automated creation of such structures. This paper describes the application of Castanet to journal title content, and presents an evaluation suggesting its efficacy. This is followed by a discussion of areas for future work.