Search structures and algorithms for personalized ranking

Gae won You, Seung won Hwang

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

As data of an unprecedented scale are becoming accessible on the Web, personalization, of narrowing down the retrieval to meet the user-specific information needs, is becoming more and more critical. For instance, while web search engines traditionally retrieve the same results for all users, they began to offer beta services to personalize the results to adapt to user-specific contexts such as prior search history or other application contexts. In a clear contrast to search engines dealing with unstructured text data, this paper studies how to enable such personalization in the context of structured data retrieval. In particular, we adopt contextual ranking model to formalize personalization as a cost-based optimization over collected contextual rankings. With this formalism, personalization can be abstracted as a cost-optimal retrieval of contextual ranking, closely matching user-specific retrieval context. With the retrieved matching context, we adopt a machine learning approach, to effectively and efficiently identify the ideal personalized ranked results for this specific user. Our empirical evaluations over synthetic and real-life data validate both the efficiency and effectiveness of our framework.

Original languageEnglish
Pages (from-to)3925-3942
Number of pages18
JournalInformation sciences
Volume178
Issue number20
DOIs
Publication statusPublished - 2008 Oct 15

Fingerprint

Search engines
Personalization
Ranking
Retrieval
Learning systems
Costs
Search Engine
Web Search
Machine Learning
Context
Optimization
Evaluation
Search engine

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

@article{718a484dbfff439f910d208333ad22f0,
title = "Search structures and algorithms for personalized ranking",
abstract = "As data of an unprecedented scale are becoming accessible on the Web, personalization, of narrowing down the retrieval to meet the user-specific information needs, is becoming more and more critical. For instance, while web search engines traditionally retrieve the same results for all users, they began to offer beta services to personalize the results to adapt to user-specific contexts such as prior search history or other application contexts. In a clear contrast to search engines dealing with unstructured text data, this paper studies how to enable such personalization in the context of structured data retrieval. In particular, we adopt contextual ranking model to formalize personalization as a cost-based optimization over collected contextual rankings. With this formalism, personalization can be abstracted as a cost-optimal retrieval of contextual ranking, closely matching user-specific retrieval context. With the retrieved matching context, we adopt a machine learning approach, to effectively and efficiently identify the ideal personalized ranked results for this specific user. Our empirical evaluations over synthetic and real-life data validate both the efficiency and effectiveness of our framework.",
author = "You, {Gae won} and Hwang, {Seung won}",
year = "2008",
month = "10",
day = "15",
doi = "10.1016/j.ins.2008.06.009",
language = "English",
volume = "178",
pages = "3925--3942",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",
number = "20",

}

Search structures and algorithms for personalized ranking. / You, Gae won; Hwang, Seung won.

In: Information sciences, Vol. 178, No. 20, 15.10.2008, p. 3925-3942.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Search structures and algorithms for personalized ranking

AU - You, Gae won

AU - Hwang, Seung won

PY - 2008/10/15

Y1 - 2008/10/15

N2 - As data of an unprecedented scale are becoming accessible on the Web, personalization, of narrowing down the retrieval to meet the user-specific information needs, is becoming more and more critical. For instance, while web search engines traditionally retrieve the same results for all users, they began to offer beta services to personalize the results to adapt to user-specific contexts such as prior search history or other application contexts. In a clear contrast to search engines dealing with unstructured text data, this paper studies how to enable such personalization in the context of structured data retrieval. In particular, we adopt contextual ranking model to formalize personalization as a cost-based optimization over collected contextual rankings. With this formalism, personalization can be abstracted as a cost-optimal retrieval of contextual ranking, closely matching user-specific retrieval context. With the retrieved matching context, we adopt a machine learning approach, to effectively and efficiently identify the ideal personalized ranked results for this specific user. Our empirical evaluations over synthetic and real-life data validate both the efficiency and effectiveness of our framework.

AB - As data of an unprecedented scale are becoming accessible on the Web, personalization, of narrowing down the retrieval to meet the user-specific information needs, is becoming more and more critical. For instance, while web search engines traditionally retrieve the same results for all users, they began to offer beta services to personalize the results to adapt to user-specific contexts such as prior search history or other application contexts. In a clear contrast to search engines dealing with unstructured text data, this paper studies how to enable such personalization in the context of structured data retrieval. In particular, we adopt contextual ranking model to formalize personalization as a cost-based optimization over collected contextual rankings. With this formalism, personalization can be abstracted as a cost-optimal retrieval of contextual ranking, closely matching user-specific retrieval context. With the retrieved matching context, we adopt a machine learning approach, to effectively and efficiently identify the ideal personalized ranked results for this specific user. Our empirical evaluations over synthetic and real-life data validate both the efficiency and effectiveness of our framework.

UR - http://www.scopus.com/inward/record.url?scp=48949102506&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48949102506&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2008.06.009

DO - 10.1016/j.ins.2008.06.009

M3 - Article

AN - SCOPUS:48949102506

VL - 178

SP - 3925

EP - 3942

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

IS - 20

ER -