Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form
D-Scholarship @ Pitt Banner and Links to Homepage

USING EXTERNAL SOURCES TO IMPROVE RESEARCH TALK RECOMMENDATION IN SMALL COMMUNITIES

Wongchokprasitti, Chirayu (2015) USING EXTERNAL SOURCES TO IMPROVE RESEARCH TALK RECOMMENDATION IN SMALL COMMUNITIES. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img]
Preview
 PDF (Version 0.8.2)
Submitted Version
Download (7MB)

Abstract

In academic research communities, a typical way to spread ideas or seek for collaboration is through research talks, which might be presented at departmental colloquia or might be in given at conferences. Given a large number of research talks, with some of them happening in parallel, it becomes increasingly harder to focus on those of that are of most interest. To solve this problem, talk recommendation systems can help academics identify the most useful talks among many. This dissertation investigates methods to improve research talk recommendations, both for conference attendees and for faculty and students at a research university. More specifically, the focus of this thesis is the use of external information about user interests as a way to address the challenges of having limited data about target users. The thesis examines several kinds of external sources such as user home page, bibliography, external bookmarks, and user profiles from external information systems and explores impact of this information on the quality of talk recommendation in a general situation and in a cold-start context. For this study, the dissertation uses data from two existing talk recommendation systems, CoMeT and Conference Navigator 3, and an academic paper search system, SciNet.

Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Wongchokprasitti, Chirayuchw202pitt.edu0000-0001-8160-6976
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Thesis AdvisorBrusilovsky, Peterpeterb@pitt.eduPETERB
Committee MemberHirtle, Stephen C.hirtle@pitt.eduHIRTLE
Committee MemberHe, Daqingdah44@pitt.eduDAH44
Committee MemberWang, Jingtaojingtaow@cs.pitt.eduJINGTAOW
Date: 1 September 2015
Date Type: Publication
Defense Date: 15 April 2015
Approval Date: 1 September 2015
Submission Date: 28 July 2015
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 323
Institution: University of Pittsburgh
Schools and Programs: School of Information Sciences > Information Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: recommender systems, research talks, small communities
Date Deposited: 01 Sep 2015 14:33
Last Modified: 15 Nov 2016 14:29
URI: http://d-scholarship.pitt.edu/id/eprint/25836

Metrics

Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item