Open Collections

LePlaza : an event-centered social networking platform with location based personalized recommendation service

University of British Columbia

Web based social networking services have afforded opportunities for people to enrich their social lives by building new relationships and sharing various kinds of information. While many people are interested in questions such as “what interesting social events are happening nearby that I can join?”, few existing social networking sites have successfully provided easy solutions for people to explore and organize real social activities. This thesis represents an effort to offer an event-centered social networking platform through which the users can share real social events as well as scheduling their own events. To serve targeted events that are more likely to be of interest to a specific individual, a content-based user-interest model is proposed according to the assessment of the user’s historical activity records and the description of the events. An intelligent recommender system built upon the user-interest model is developed to make personalized recommendations on restaurants as a particular case study in which events are parameterized by user’s location, and the results are visualized in an interactive manner. Experiments and user studies show that the proposed model and algorithm effectively reflect the user’s personal preferences with satisfying recommendation accuracy for the case of dining events.

Text

2011-08-19

Attribution-NonCommercial-NoDerivatives 4.0 International

http://hdl.handle.net/2429/36796

Computer Science

University of British Columbia

UBCV

http://creativecommons.org/licenses/by-nc-nd/4.0/