作者: Giuliano Arru , Davide Feltoni Gurini , Fabio Gasparetti , Alessandro Micarelli , Giuseppe Sansonetti
关键词:
摘要: In recent years, social networks have become one of the best ways to access information. The ease with which users connect each other and opportunity provided by Twitter tools in order follow person activities are increasing use such platforms for gathering amount available digital data is core new challenges we now face. Social recommender systems can suggest both relevant content common interests. Our approach relies on a signal-based model, explicitly includes time dimension representation user Specifically, this model takes advantage signal processing technique, namely, wavelet transform, defining an efficient pattern-based similarity function among users. Experimental comparisons approaches show benefits proposed approach.