Title page for etd-0729112-222447


[Back to Results | New Search]

URN etd-0729112-222447
Author Po-ling Chen
Author's Email Address No Public.
Statistics This thesis had been viewed 5350 times. Download 945 times.
Department Information Management
Year 2011
Semester 2
Degree Master
Type of Document
Language English
Title Recommending Travel Threads Based on Information Need
Model
Date of Defense 2012-07-02
Page Count 54
Keyword
  • Text classification
  • Travel threads recommendation
  • Travel threads classification
  • Question recommendation
  • Information need model
  • Abstract Recommendation techniques are developed to discover user’s real information
    need among large amounts of information. Recommendation systems help users filter
    out information and attempt to present those similar items according to user’s tastes. In
    our work, we focus on discussion threads recommendation in the tourism domain. We
    assume that when users have traveling information need, they will try to search related
    information on the websites. In addition to browsing others suggestions and opinions,
    users  are  allowed  to  express  their  need  as  a  question.  Hence,  we  focus  on
    recommending users previous discussion threads that may provide good answers to the
    users’ questions by considering the question input as well as their browsing records. We
    propose a model, which consists of four perspectives: goal similarity, content similarity,
    freshness  and  quality.  To  validate  and  the  effectiveness  of  our  model  on
    recommendation performance, we collected 14348 threads from TripAdvisor.com, the
    largest travel website, and recruited ten volunteers, who have interests in the tourism, to
    verify our approach. The four perspectives are utilized by two methods. The first is
    Question-based method, which makes use of content similarity, freshness and quality
    and the second is Session-based method, which involves goal similarity. We also
    integrate the two methods into a hybrid method.
    The  experiment  results  show  that  the  hybrid  method  generally  has  better
    performance than the other two methods.
    Advisory Committee
  • Hsiang-Li Chiang - chair
  • Chun-I Fan - co-chair
  • San-Yih Hwang - advisor
  • Files
  • etd-0729112-222447.pdf
  • Indicate in-campus at 2 year and off-campus access at 2 year.
    Date of Submission 2012-07-29

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys