Welcome to the InfoSci Platform
Reference Hub4
Revealing Learner Interests through Topic Mining from Question-Answering Data

Revealing Learner Interests through Topic Mining from Question-Answering Data

Yijie Dun, Na Wang, Min Wang, Tianyong Hao
Copyright: © 2017 |Volume: 15 |Issue: 2 |Pages: 15
ISSN: 1539-3100|EISSN: 1539-3119|EISBN13: 9781522511083|DOI: 10.4018/IJDET.2017040102
Cite Article Cite Article

MLA

Dun, Yijie, et al. "Revealing Learner Interests through Topic Mining from Question-Answering Data." IJDET vol.15, no.2 2017: pp.18-32. http://doi.org/10.4018/IJDET.2017040102

APA

Dun, Y., Wang, N., Wang, M., & Hao, T. (2017). Revealing Learner Interests through Topic Mining from Question-Answering Data. International Journal of Distance Education Technologies (IJDET), 15(2), 18-32. http://doi.org/10.4018/IJDET.2017040102

Chicago

Dun, Yijie, et al. "Revealing Learner Interests through Topic Mining from Question-Answering Data," International Journal of Distance Education Technologies (IJDET) 15, no.2: 18-32. http://doi.org/10.4018/IJDET.2017040102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In a question-answering system, learner generated content including asked and answered questions is a meaningful resource to capture learning interests. This paper proposes an approach based on question topic mining for revealing learners' concerned topics in real community question-answering systems. The authors' approach firstly preprocesses all questions associated with learners. Afterwards, it analyzes each question with text features and generates a weight feature matrix using a revised TF/IDF method. In order to decrease the sparsity issue of data distribution, the authors employ three concept-mapping strategies including named entity recognition, synonym extension, and hyponym replacement. Applying an SVM classifier, their approach categorizes user questions into representative topics. Three experiments are conducted based on a TREC dataset and an actual dataset containing 1,120 questions posted by learners from a commercial question-answering community. Results demonstrate the effectiveness of the method compared with conventional classifiers as baselines.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.