Development of Social-Aware Recommendation System Using Public Preference Mining and Social Influence Analysis - A Case Study of Landscape Recommendation

Abstract

A novel social-aware recommendation system framework which employs public preference and social influence to classify user preference orientation is proposed in this thesis Unlike traditional content-based or collaborative filtering recommendation approaches we collected large scale information from heterogeneous data sources to construct the public preference model for user’s feature-based preference orientation classification Moreover the social relation graph of target user is constructed to analyze social influence of preference between users in it According to the different online social networks corresponding types of interaction are adopted to estimate the degree of social influence between users Then the social influence of preference is calculated by social influence and interest similarity between users In addition the preference guiding pair is constructed by real data to be the baseline of preference adjustment The purpose of this thesis is that using public preference to infer user preference and further adjusting user preference through social influence of preference from neighbors The proposed method deals with the cold-start issue in recommendation system There two main advantages of the proposed method are social relationship can be easily obtained from online social network and any type of recommendation system can be applied in the proposed method In our experiment blogs news and online social networks are the information sources to construct public preference model Moreover Facebook the most famous social media is the platform selected for social relationship analysis The experimental result shows our approach not only innovation but also practicable

Date of Award	2014 Aug 16
Original language	English
Supervisor	Yau-Hwang Kuo (Supervisor)