整合社會網路中互動與信任關係之產品推薦

隨著網際網路與Web 2.0技術普及，促成社會網路的蓬勃發展，且人們逐漸頻繁地參與社會網路的活動，以進行互動交流與資訊分享，使得網路上的消費者於作購買決策時，往往會依賴網路資訊來進行之，而如此的購買決策常會受到具有關係的人而影響。此外，眾多消費者於購買產品前，會傾向參考其他消費者對於產品的評論、評價和使用體驗等來進行購買決策。然而，過多的資訊卻造成消費者面臨資訊過載的問題。因此本研究提出整合社會網路中互動與信任關係之產品推薦方法，考量使用者在社會網路中的互動關係與信任關係。其中主要著重於使用者互動的分析，進而推論使用者之間互動關係與互動程度。另一方面，根據使用者的互動，來推論使用者之間的信任關係與信任程度。最後，提出與眾不同之產品推薦方法，將互動關係與信任關係整合，並運用於社會網路中進行產品推薦。藉由本研究之方法能提升推薦的準確性，進而較為準確地預測使用者的喜好，來提供相關之產品推薦，以協助使用者做購買決策。

關鍵字

產品推薦；信任關係；互動關係；資訊過載；社會網路

並列摘要

Web 2.0 technology fosters the flourishing growth and development of social networks. More and more people participate the activities on social networks to interact and share information with others. Thus, consumers make the purchasing decisions based on the information from the Internet. Such decisions may be affected by the opinions of their friends or their trusted friends. On the other hand, consumers may refer to others’ reviews, ratings, and comments on products before making the buying decisions. However, a great amount of that information may cause the problem of information overload for consumers. Therefore, this project proposes a novel product recommendation methods based on the integration of interaction, trust relationships and product popularity to predict users’ preferences on a social networking website. The research method of this project mainly focuses on the analysis of users’ interaction behavior to infer users’ latent interaction relationships, and then build a social network. Additionally, users’ common items with co-ratings and the role importance of users are used to infer their trust relationships and degrees. The method also analyzes the popularity of products on the social network. Finally, the interaction, trust relationships and product popularity are combined to make recommendations for users on a social networking website. This project can accurately predict users’ preference and recommend relevant products to users for supporting their decision making.

並列關鍵字

Data Mining ； Social Network ； Trust Relationship ； Product Recommendation ； Collaborative Filtering ； Interaction

參考文獻

[42] B. Sarwar, G. Karypis, J. Konstan, and J. Riedl, “Item-based collaborative filtering recommendation algorithms,” in Proceedings of the 10th international conference on World Wide Web, Hong Kong, Hong Kong, pp. 285-295, 2001.

[31] B. N. Miller, I. Albert, S. K. Lam, J. A. Konstan, and J. Riedl, “MovieLens unplugged: experiences with an occasionally connected recommender system,” in Proceedings of the 8th international conference on Intelligent user interfaces, Miami, Florida, USA, pp. 263-266, 2003.

[2] D. Ariely, “Controlling the information flow: Effects on consumers’ decision making and preferences,” Journal of Consumer Research, vol. 27, no. 2, pp. 233-248, 2000.

[4] P. Borzymek, M. Sydow, and A. Wierzbicki, “Enriching Trust Prediction Model in Social Network with User Rating Similarity,” in International Conference on Computational Aspects of Social Networks (CASON '09), pp. 40-47, 2009.

[5] d. m. boyd, and N. B. Ellison, “Social Network Sites: Definition, History, and Scholarship,” Journal of Computer-Mediated Communication, vol. 13, no. 1, pp. 210-230, 2007.

國際替代計量

整合社會網路中互動與信任關係之產品推薦

全文下載

主題瀏覽