An intelligent discussion-bot for answering student queries in threaded discussions

Donghui Feng, Erin Shaw, Jihie Kim, Eduard Hovy

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

82 Scopus citations

Abstract

This paper describes a discussion-bot that provides answers to students' discussion board questions in an unobtrusive and humanlike way. Using information retrieval and natural language processing techniques, the discussion-bot identifies the questioner's interest, mines suitable answers from an annotated corpus of 1236 archived threaded discussions and 279 course documents and chooses an appropriate response. A novel modeling approach was designed for the analysis of archived threaded discussions to facilitate answer extraction. We compare a self-out and an all-in evaluation of the mined answers. The results show that the discussion-bot can begin to meet students' learning requests. We discuss directions that might be taken to increase the effectiveness of the question matching and answer extraction algorithms. The research takes place in the context of an undergraduate computer science course.

Original languageEnglish
Title of host publicationIUI 06 - 2006 International Conference on Intelligent User Interfaces
PublisherAssociation for Computing Machinery (ACM)
Pages171-177
Number of pages7
ISBN (Print)1595932879, 9781595932877
DOIs
StatePublished - 2006
EventIUI 06 - 2006 International Conference on Intelligent User Interfaces - Sydney, Australia
Duration: 29 Jan 20051 Feb 2005

Publication series

NameInternational Conference on Intelligent User Interfaces, Proceedings IUI
Volume2006

Conference

ConferenceIUI 06 - 2006 International Conference on Intelligent User Interfaces
Country/TerritoryAustralia
CitySydney
Period29/01/051/02/05

Keywords

  • Discussion-bot
  • Natural language processing
  • Online learning environment
  • Threaded discussion

Fingerprint

Dive into the research topics of 'An intelligent discussion-bot for answering student queries in threaded discussions'. Together they form a unique fingerprint.

Cite this