A social-evolutionary approach to compose a similarity function used on event recommendation

摘要: With the development of web 2.0, social networks have achieved great space on internet, with that many users provide information and interests about themselves. There are expert systems use user's to recommend different products, these known as Recommender Systems. One main techniques a Systems is Collaborative Filtering (User based) which recommends products based what other similar people liked in past. However, methods determine similarity between presented some problems. Therefore, this work presents proposal using variables composition function applied user recommendation events. To test proposal, details friends events two target-users network Facebook been extracted. The results were compared deterministic heuristics, Euclidean Distance aleatory method. proposed model showed promising potential expand contexts.