Home
Resource
Implicit search feature based approach to assist users in exploratory search tasks
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(5.30 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Hendahewa, Chathra Hasini. Implicit search feature based approach to assist users in exploratory search tasks. Retrieved from https://doi.org/doi:10.7282/T39S1T21

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleImplicit search feature based approach to assist users in exploratory search tasks
NameHendahewa, Chathra Hasini (author); Shah, Chirag (chair); Imielinksi, Tomasz (internal member); Gerasoulis, Apostolos (internal member); Russell, Daniel (outside member); Rutgers University; Graduate School - New Brunswick
Date Created2016
Other Date2016-01 (degree)
SubjectComputer Science, Human-computer interaction, Information behavior
Extent1 online resource (xiv, 105 p. : ill.)
DescriptionAnalyzing 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. In this dissertation, 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 e ectiveness of the proposed framework by demonstrating how it can be used to understand and evaluate user search performance to identify struggling and non-struggling users. Major contributions of this dissertation are three-fold. We show that we can e ectively model user search behavior using implicit features to predict the user's future performance level with high accuracy when conducting exploratory search tasks. We also provide a recommendation approach to assist struggling users by recommending them better search paths in order to improve their search performance and reach the task goal. Further, using simulations we demonstrate that our search process based recommendations improve the search performance of struggling users over time and validate these ndings using both qualitative and quantitative approaches. We also exhibit that the recommended search trail order matters and it outperforms the random order of search trails and would bene t the struggling users using search trail order evaluation metrics.
NotePh.D.
NoteIncludes bibliographical references
Noteby Chathra Hasini Hendahewa
Genretheses, ETD doctoral
Persistent URLhttps://doi.org/doi:10.7282/T39S1T21
Languageeng
CollectionGraduate School - New Brunswick Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024