Using Social Information to Compose a Similarity Function Based on Friends Attendance at Events

Abstract

The analysis of affinity or similarity between people is an important task in the study of social dynamics. Traditional methods for determining similarity depends on considerable amount of data regarding people's preferences and features. Those methods present limitations when the data is scarce and/or changes constantly. This paper introduces a new method for determining people similarity that does not suffer from the same problems. The method can learn a customized similarity function based on social variables of friends that attend the same events (concerts, parties, conferences etc), collected from social networks. Two types of optimization algorithms for learning a similarity function are presented: The universal function approximator modelling, which relays on the relationship of social attributes and a friends' importance ranking; and the populational evolutionary modelling, which linearly combines social variables. Both models were tested in a generalist and in a specialist approach. The results show that the specialist approach exceeded in almost 38 % the generalist approach using populational evolutionary methods and in almost 69 % when using the universal function approximator methods. Among the implemented optimization algorithms employed inside the methods for learning similarity, Genetic Algorithm and Particle Swarm Optimization presented better performance for the populational evolutionary methods and the Artificial Neural Network presented the best performance overall using the universal function approximator modelling.