Automatic extraction of user's search intention from web search logs

Kinam Park, Hyesung Jee, Taemin Lee, Soon Young Jung, Heui Seok Lim

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Web search users complain of the inaccurate results produced by current search engines. Most of these inaccurate results are due to a failure to understand the user's search goal. This paper proposes a method to extract users' intentions and to build an intention map representing these extracted intentions. The proposed method makes intention vectors from clicked pages from previous search logs obtained on a given query. The components of the intention vector are weights of the keywords in a document. It extracts user's intentions by using clustering the intention vectors and extracting intention keywords from each cluster. The extracted the intentions on a query are represented in an intention map. For the efficiency analysis of intention map, we extracted user's intentions using 2,600 search log data a current domestic commercial search engine. The experimental results with a search engine using the intention maps show statistically significant improvements in user satisfaction scores.

Original languageEnglish
Pages (from-to)145-162
Number of pages18
JournalMultimedia Tools and Applications
Volume61
Issue number1
DOIs
Publication statusPublished - 2012 Nov 1

Fingerprint

Search engines

Keywords

  • Clustering
  • Intention map
  • Knowledge representation
  • Search engine
  • User's search log

ASJC Scopus subject areas

  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications
  • Software

Cite this

Automatic extraction of user's search intention from web search logs. / Park, Kinam; Jee, Hyesung; Lee, Taemin; Jung, Soon Young; Lim, Heui Seok.

In: Multimedia Tools and Applications, Vol. 61, No. 1, 01.11.2012, p. 145-162.

Research output: Contribution to journalArticle

@article{bf1d3ee0eec94abb95f41643b67d888b,
title = "Automatic extraction of user's search intention from web search logs",
abstract = "Web search users complain of the inaccurate results produced by current search engines. Most of these inaccurate results are due to a failure to understand the user's search goal. This paper proposes a method to extract users' intentions and to build an intention map representing these extracted intentions. The proposed method makes intention vectors from clicked pages from previous search logs obtained on a given query. The components of the intention vector are weights of the keywords in a document. It extracts user's intentions by using clustering the intention vectors and extracting intention keywords from each cluster. The extracted the intentions on a query are represented in an intention map. For the efficiency analysis of intention map, we extracted user's intentions using 2,600 search log data a current domestic commercial search engine. The experimental results with a search engine using the intention maps show statistically significant improvements in user satisfaction scores.",
keywords = "Clustering, Intention map, Knowledge representation, Search engine, User's search log",
author = "Kinam Park and Hyesung Jee and Taemin Lee and Jung, {Soon Young} and Lim, {Heui Seok}",
year = "2012",
month = "11",
day = "1",
doi = "10.1007/s11042-010-0723-8",
language = "English",
volume = "61",
pages = "145--162",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Automatic extraction of user's search intention from web search logs

AU - Park, Kinam

AU - Jee, Hyesung

AU - Lee, Taemin

AU - Jung, Soon Young

AU - Lim, Heui Seok

PY - 2012/11/1

Y1 - 2012/11/1

N2 - Web search users complain of the inaccurate results produced by current search engines. Most of these inaccurate results are due to a failure to understand the user's search goal. This paper proposes a method to extract users' intentions and to build an intention map representing these extracted intentions. The proposed method makes intention vectors from clicked pages from previous search logs obtained on a given query. The components of the intention vector are weights of the keywords in a document. It extracts user's intentions by using clustering the intention vectors and extracting intention keywords from each cluster. The extracted the intentions on a query are represented in an intention map. For the efficiency analysis of intention map, we extracted user's intentions using 2,600 search log data a current domestic commercial search engine. The experimental results with a search engine using the intention maps show statistically significant improvements in user satisfaction scores.

AB - Web search users complain of the inaccurate results produced by current search engines. Most of these inaccurate results are due to a failure to understand the user's search goal. This paper proposes a method to extract users' intentions and to build an intention map representing these extracted intentions. The proposed method makes intention vectors from clicked pages from previous search logs obtained on a given query. The components of the intention vector are weights of the keywords in a document. It extracts user's intentions by using clustering the intention vectors and extracting intention keywords from each cluster. The extracted the intentions on a query are represented in an intention map. For the efficiency analysis of intention map, we extracted user's intentions using 2,600 search log data a current domestic commercial search engine. The experimental results with a search engine using the intention maps show statistically significant improvements in user satisfaction scores.

KW - Clustering

KW - Intention map

KW - Knowledge representation

KW - Search engine

KW - User's search log

UR - http://www.scopus.com/inward/record.url?scp=84864026563&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864026563&partnerID=8YFLogxK

U2 - 10.1007/s11042-010-0723-8

DO - 10.1007/s11042-010-0723-8

M3 - Article

VL - 61

SP - 145

EP - 162

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 1

ER -