| ||||
Nirmalie Wiratunga: AbstractSocial recommender systems harness knowledge from social media to guide recommendations. Typically these systems make use of social knowledge such as reviews, social tags, social relationship (social network) and microblogs. In this talk, I will focus on two knowledge sources for product recommendation: product reviews and user purchase trails. In particular, I will present how we exploit the sentiment expressed in product reviews and user preferences which are implicitly contained in user purchase trails as the basis to guide recommendations. In particular I will discuss how and why aspect guided sentiment analysis is useful for recommender systems.
|