Implicit search feature based approach to assist users in exploratory search tasks

Chathra Hendahewa, Chirag Shah

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Analyzing and modeling users' online search behaviors when conducting exploratory search tasks could be instrumental in discovering search behavior patterns that can then be leveraged to assist users in reaching their search task goals. We propose a framework for evaluating exploratory search based on implicit features and user search action sequences extracted from the transactional log data to model different aspects of exploratory search namely uncertainty, creativity, exploration, and knowledge discovery. We show the effectiveness of the proposed framework by demonstrating how it can be used to understand and evaluate user search performance and thereby make meaningful recommendations to improve the overall search performance of users. We used data collected from a user study consisting of 18 users conducting an exploratory search task for two sessions with two different topics in the experimental analysis. With this analysis we show that we can effectively model their behavior using implicit features to predict the user's future performance level with above 70% accuracy in most cases. Further, using simulations we demonstrate that our search process based recommendations improve the search performance of low performing users over time and validate these findings using both qualitative and quantitative approaches.

Original languageEnglish (US)
Pages (from-to)643-661
Number of pages19
JournalInformation Processing and Management
Volume51
Issue number5
DOIs
StatePublished - Jun 20 2015

Fingerprint

Data mining
performance
behavior model
behavior pattern
creativity
uncertainty
Uncertainty
simulation
knowledge
Search behavior

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Library and Information Sciences
  • Media Technology
  • Computer Science Applications
  • Management Science and Operations Research

Keywords

  • Evaluation
  • Exploratory search
  • Implicit features
  • User behavior

Cite this

@article{a7875d13d96d4da88169ff9135089d5c,
title = "Implicit search feature based approach to assist users in exploratory search tasks",
abstract = "Analyzing and modeling users' online search behaviors when conducting exploratory search tasks could be instrumental in discovering search behavior patterns that can then be leveraged to assist users in reaching their search task goals. We propose a framework for evaluating exploratory search based on implicit features and user search action sequences extracted from the transactional log data to model different aspects of exploratory search namely uncertainty, creativity, exploration, and knowledge discovery. We show the effectiveness of the proposed framework by demonstrating how it can be used to understand and evaluate user search performance and thereby make meaningful recommendations to improve the overall search performance of users. We used data collected from a user study consisting of 18 users conducting an exploratory search task for two sessions with two different topics in the experimental analysis. With this analysis we show that we can effectively model their behavior using implicit features to predict the user's future performance level with above 70{\%} accuracy in most cases. Further, using simulations we demonstrate that our search process based recommendations improve the search performance of low performing users over time and validate these findings using both qualitative and quantitative approaches.",
keywords = "Evaluation, Exploratory search, Implicit features, User behavior",
author = "Chathra Hendahewa and Chirag Shah",
year = "2015",
month = "6",
day = "20",
doi = "https://doi.org/10.1016/j.ipm.2015.06.004",
language = "English (US)",
volume = "51",
pages = "643--661",
journal = "Information Processing and Management",
issn = "0306-4573",
publisher = "Elsevier Limited",
number = "5",

}

Implicit search feature based approach to assist users in exploratory search tasks. / Hendahewa, Chathra; Shah, Chirag.

In: Information Processing and Management, Vol. 51, No. 5, 20.06.2015, p. 643-661.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Implicit search feature based approach to assist users in exploratory search tasks

AU - Hendahewa, Chathra

AU - Shah, Chirag

PY - 2015/6/20

Y1 - 2015/6/20

N2 - Analyzing and modeling users' online search behaviors when conducting exploratory search tasks could be instrumental in discovering search behavior patterns that can then be leveraged to assist users in reaching their search task goals. We propose a framework for evaluating exploratory search based on implicit features and user search action sequences extracted from the transactional log data to model different aspects of exploratory search namely uncertainty, creativity, exploration, and knowledge discovery. We show the effectiveness of the proposed framework by demonstrating how it can be used to understand and evaluate user search performance and thereby make meaningful recommendations to improve the overall search performance of users. We used data collected from a user study consisting of 18 users conducting an exploratory search task for two sessions with two different topics in the experimental analysis. With this analysis we show that we can effectively model their behavior using implicit features to predict the user's future performance level with above 70% accuracy in most cases. Further, using simulations we demonstrate that our search process based recommendations improve the search performance of low performing users over time and validate these findings using both qualitative and quantitative approaches.

AB - Analyzing and modeling users' online search behaviors when conducting exploratory search tasks could be instrumental in discovering search behavior patterns that can then be leveraged to assist users in reaching their search task goals. We propose a framework for evaluating exploratory search based on implicit features and user search action sequences extracted from the transactional log data to model different aspects of exploratory search namely uncertainty, creativity, exploration, and knowledge discovery. We show the effectiveness of the proposed framework by demonstrating how it can be used to understand and evaluate user search performance and thereby make meaningful recommendations to improve the overall search performance of users. We used data collected from a user study consisting of 18 users conducting an exploratory search task for two sessions with two different topics in the experimental analysis. With this analysis we show that we can effectively model their behavior using implicit features to predict the user's future performance level with above 70% accuracy in most cases. Further, using simulations we demonstrate that our search process based recommendations improve the search performance of low performing users over time and validate these findings using both qualitative and quantitative approaches.

KW - Evaluation

KW - Exploratory search

KW - Implicit features

KW - User behavior

UR - http://www.scopus.com/inward/record.url?scp=84934928862&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84934928862&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.ipm.2015.06.004

DO - https://doi.org/10.1016/j.ipm.2015.06.004

M3 - Article

VL - 51

SP - 643

EP - 661

JO - Information Processing and Management

JF - Information Processing and Management

SN - 0306-4573

IS - 5

ER -