Abstract Maryam Fatemi 8th November

From IMC wiki
Jump to: navigation, search

Maryam will be talking about some of her data and findings, and developments on the Social Recommender System for movies based on the network of co-reviewers.

The traditional recommender systems (collaborative-filtering, content- based recommender systems or combination of them) all have one or more weaknesses such as cold start, sparsity of data, scalability problems and overspecialised recommendation. Social networks and other similar websites have new types of data which can be used in recommender systems to potentially overcome these shortcomings. For this purpose, this research examines an on-line movie database (IMDb), and the interactions between reviewers, and attempts to construct a social network graph based on the network of reviewers. The resulting network is confirmed as the power-law, small-world and scale free. It identifies the highly connected clusters and shows that the content of these subgroups are diversified and not limited to similar tags or genres. The Social Network with its communities is used in the proposed Social Recommender System in order to enhance recommendations; and provides diverse results while overcoming the known shortcomings.


Back to IMC Seminar Series