A task-focused literature recommender system for digital libraries

Wan Shiou Yang, Yi Rong Lin

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Purpose - The scientific literature has played an important role in the dissemination of new knowledge throughout the past century. However, the increasing numbers of scientific articles being published in recent years has intensified the perception of information overload for users attempting to find relevant scientific information. The purpose of this paper is to describe a task-focused strategy that employs the task profiles of users to make recommendations in a digital library. Design/method/approach - This paper combines information retrieval, common citation analysis, and coauthor relationship analysis techniques with a citation network analysis technique - the CiteRank algorithm - to find relevant and high-quality articles. In total, nine variations of the proposed approach were tested using articles downloaded from the CiteSeerX system and usage logs collected from the authors' experimental server. Findings - The results from the authors' experimental evaluations demonstrate that the proposed Content-citation approach outperforms the Relevance-CiteRank, Relevance-citation count, and Relevance-only approaches. Originality/value - This paper describes an original study that has produced a novel way to combine information retrieval, common citation analysis, and coauthor relationship analysis techniques to find relevant and high-quality articles for recommendation in a digital library.

Original languageEnglish
Article number17094551
Pages (from-to)581-601
Number of pages21
JournalOnline Information Review
Volume37
Issue number4
DOIs
Publication statusPublished - 2013 Sep 2

Fingerprint

Digital libraries
Recommender systems
Information retrieval
Electric network analysis
information retrieval
Servers
technical literature
network analysis
literature
evaluation
knowledge
Values

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences

Cite this

@article{69f31ba9619b4d118894f34bd572fbe8,
title = "A task-focused literature recommender system for digital libraries",
abstract = "Purpose - The scientific literature has played an important role in the dissemination of new knowledge throughout the past century. However, the increasing numbers of scientific articles being published in recent years has intensified the perception of information overload for users attempting to find relevant scientific information. The purpose of this paper is to describe a task-focused strategy that employs the task profiles of users to make recommendations in a digital library. Design/method/approach - This paper combines information retrieval, common citation analysis, and coauthor relationship analysis techniques with a citation network analysis technique - the CiteRank algorithm - to find relevant and high-quality articles. In total, nine variations of the proposed approach were tested using articles downloaded from the CiteSeerX system and usage logs collected from the authors' experimental server. Findings - The results from the authors' experimental evaluations demonstrate that the proposed Content-citation approach outperforms the Relevance-CiteRank, Relevance-citation count, and Relevance-only approaches. Originality/value - This paper describes an original study that has produced a novel way to combine information retrieval, common citation analysis, and coauthor relationship analysis techniques to find relevant and high-quality articles for recommendation in a digital library.",
author = "Yang, {Wan Shiou} and Lin, {Yi Rong}",
year = "2013",
month = "9",
day = "2",
doi = "10.1108/OIR-10-2011-0172",
language = "English",
volume = "37",
pages = "581--601",
journal = "Online Information Review",
issn = "1468-4527",
publisher = "Emerald Group Publishing Ltd.",
number = "4",

}

A task-focused literature recommender system for digital libraries. / Yang, Wan Shiou; Lin, Yi Rong.

In: Online Information Review, Vol. 37, No. 4, 17094551, 02.09.2013, p. 581-601.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A task-focused literature recommender system for digital libraries

AU - Yang, Wan Shiou

AU - Lin, Yi Rong

PY - 2013/9/2

Y1 - 2013/9/2

N2 - Purpose - The scientific literature has played an important role in the dissemination of new knowledge throughout the past century. However, the increasing numbers of scientific articles being published in recent years has intensified the perception of information overload for users attempting to find relevant scientific information. The purpose of this paper is to describe a task-focused strategy that employs the task profiles of users to make recommendations in a digital library. Design/method/approach - This paper combines information retrieval, common citation analysis, and coauthor relationship analysis techniques with a citation network analysis technique - the CiteRank algorithm - to find relevant and high-quality articles. In total, nine variations of the proposed approach were tested using articles downloaded from the CiteSeerX system and usage logs collected from the authors' experimental server. Findings - The results from the authors' experimental evaluations demonstrate that the proposed Content-citation approach outperforms the Relevance-CiteRank, Relevance-citation count, and Relevance-only approaches. Originality/value - This paper describes an original study that has produced a novel way to combine information retrieval, common citation analysis, and coauthor relationship analysis techniques to find relevant and high-quality articles for recommendation in a digital library.

AB - Purpose - The scientific literature has played an important role in the dissemination of new knowledge throughout the past century. However, the increasing numbers of scientific articles being published in recent years has intensified the perception of information overload for users attempting to find relevant scientific information. The purpose of this paper is to describe a task-focused strategy that employs the task profiles of users to make recommendations in a digital library. Design/method/approach - This paper combines information retrieval, common citation analysis, and coauthor relationship analysis techniques with a citation network analysis technique - the CiteRank algorithm - to find relevant and high-quality articles. In total, nine variations of the proposed approach were tested using articles downloaded from the CiteSeerX system and usage logs collected from the authors' experimental server. Findings - The results from the authors' experimental evaluations demonstrate that the proposed Content-citation approach outperforms the Relevance-CiteRank, Relevance-citation count, and Relevance-only approaches. Originality/value - This paper describes an original study that has produced a novel way to combine information retrieval, common citation analysis, and coauthor relationship analysis techniques to find relevant and high-quality articles for recommendation in a digital library.

UR - http://www.scopus.com/inward/record.url?scp=84883087144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883087144&partnerID=8YFLogxK

U2 - 10.1108/OIR-10-2011-0172

DO - 10.1108/OIR-10-2011-0172

M3 - Article

AN - SCOPUS:84883087144

VL - 37

SP - 581

EP - 601

JO - Online Information Review

JF - Online Information Review

SN - 1468-4527

IS - 4

M1 - 17094551

ER -