Search personalization: Knowledge-based recommendation in digital libraries

Todd Will, Anand Srinivasan, Il Im, Yi Fang Brook Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Recommendation engines have made great strides in understanding and implementing search personalization techniques to provide interesting and relevant documents to users. The latest research effort advances a new type of recommendation technique, Knowledge Based (KB) engines, that strive to understand the context of the user's current information need and then filter information accordingly. The KB engine proposed in this paper requires less effort from the user in representing the search task and is the first of its kind implemented in a digital library setting. The KB engine performance was compared with Content Based (CB) and Collaborative Filtering (CF) recommendation techniques and the text search engine Lucene by asking sixty subjects to perform two different tasks to find relevant documents in a database of 212,000 documents from 22 National Science Digital Library (NSDL) collections. Our KB engine design outperforms CB, CF, and text search techniques in nearly all areas of evaluation.

Original languageEnglish
Title of host publication15th Americas Conference on Information Systems 2009, AMCIS 2009
Pages6443-6450
Number of pages8
Publication statusPublished - 2009 Dec 1
Event15th Americas Conference on Information Systems 2009, AMCIS 2009 - San Francisco, CA, United States
Duration: 2009 Aug 62009 Aug 9

Publication series

Name15th Americas Conference on Information Systems 2009, AMCIS 2009
Volume10

Other

Other15th Americas Conference on Information Systems 2009, AMCIS 2009
CountryUnited States
CitySan Francisco, CA
Period09/8/609/8/9

Fingerprint

Digital libraries
personalization
Engines
Collaborative filtering
knowledge
Recommender systems
Search engines
search engine
science
evaluation
performance

All Science Journal Classification (ASJC) codes

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

Cite this

Will, T., Srinivasan, A., Im, I., & Wu, Y. F. B. (2009). Search personalization: Knowledge-based recommendation in digital libraries. In 15th Americas Conference on Information Systems 2009, AMCIS 2009 (pp. 6443-6450). (15th Americas Conference on Information Systems 2009, AMCIS 2009; Vol. 10).
Will, Todd ; Srinivasan, Anand ; Im, Il ; Wu, Yi Fang Brook. / Search personalization : Knowledge-based recommendation in digital libraries. 15th Americas Conference on Information Systems 2009, AMCIS 2009. 2009. pp. 6443-6450 (15th Americas Conference on Information Systems 2009, AMCIS 2009).
@inproceedings{951dd3f7f8a74f4eb4ba29738b4e029d,
title = "Search personalization: Knowledge-based recommendation in digital libraries",
abstract = "Recommendation engines have made great strides in understanding and implementing search personalization techniques to provide interesting and relevant documents to users. The latest research effort advances a new type of recommendation technique, Knowledge Based (KB) engines, that strive to understand the context of the user's current information need and then filter information accordingly. The KB engine proposed in this paper requires less effort from the user in representing the search task and is the first of its kind implemented in a digital library setting. The KB engine performance was compared with Content Based (CB) and Collaborative Filtering (CF) recommendation techniques and the text search engine Lucene by asking sixty subjects to perform two different tasks to find relevant documents in a database of 212,000 documents from 22 National Science Digital Library (NSDL) collections. Our KB engine design outperforms CB, CF, and text search techniques in nearly all areas of evaluation.",
author = "Todd Will and Anand Srinivasan and Il Im and Wu, {Yi Fang Brook}",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9781615675814",
series = "15th Americas Conference on Information Systems 2009, AMCIS 2009",
pages = "6443--6450",
booktitle = "15th Americas Conference on Information Systems 2009, AMCIS 2009",

}

Will, T, Srinivasan, A, Im, I & Wu, YFB 2009, Search personalization: Knowledge-based recommendation in digital libraries. in 15th Americas Conference on Information Systems 2009, AMCIS 2009. 15th Americas Conference on Information Systems 2009, AMCIS 2009, vol. 10, pp. 6443-6450, 15th Americas Conference on Information Systems 2009, AMCIS 2009, San Francisco, CA, United States, 09/8/6.

Search personalization : Knowledge-based recommendation in digital libraries. / Will, Todd; Srinivasan, Anand; Im, Il; Wu, Yi Fang Brook.

15th Americas Conference on Information Systems 2009, AMCIS 2009. 2009. p. 6443-6450 (15th Americas Conference on Information Systems 2009, AMCIS 2009; Vol. 10).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Search personalization

T2 - Knowledge-based recommendation in digital libraries

AU - Will, Todd

AU - Srinivasan, Anand

AU - Im, Il

AU - Wu, Yi Fang Brook

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Recommendation engines have made great strides in understanding and implementing search personalization techniques to provide interesting and relevant documents to users. The latest research effort advances a new type of recommendation technique, Knowledge Based (KB) engines, that strive to understand the context of the user's current information need and then filter information accordingly. The KB engine proposed in this paper requires less effort from the user in representing the search task and is the first of its kind implemented in a digital library setting. The KB engine performance was compared with Content Based (CB) and Collaborative Filtering (CF) recommendation techniques and the text search engine Lucene by asking sixty subjects to perform two different tasks to find relevant documents in a database of 212,000 documents from 22 National Science Digital Library (NSDL) collections. Our KB engine design outperforms CB, CF, and text search techniques in nearly all areas of evaluation.

AB - Recommendation engines have made great strides in understanding and implementing search personalization techniques to provide interesting and relevant documents to users. The latest research effort advances a new type of recommendation technique, Knowledge Based (KB) engines, that strive to understand the context of the user's current information need and then filter information accordingly. The KB engine proposed in this paper requires less effort from the user in representing the search task and is the first of its kind implemented in a digital library setting. The KB engine performance was compared with Content Based (CB) and Collaborative Filtering (CF) recommendation techniques and the text search engine Lucene by asking sixty subjects to perform two different tasks to find relevant documents in a database of 212,000 documents from 22 National Science Digital Library (NSDL) collections. Our KB engine design outperforms CB, CF, and text search techniques in nearly all areas of evaluation.

UR - http://www.scopus.com/inward/record.url?scp=84870328860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870328860&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84870328860

SN - 9781615675814

T3 - 15th Americas Conference on Information Systems 2009, AMCIS 2009

SP - 6443

EP - 6450

BT - 15th Americas Conference on Information Systems 2009, AMCIS 2009

ER -

Will T, Srinivasan A, Im I, Wu YFB. Search personalization: Knowledge-based recommendation in digital libraries. In 15th Americas Conference on Information Systems 2009, AMCIS 2009. 2009. p. 6443-6450. (15th Americas Conference on Information Systems 2009, AMCIS 2009).