Recognizing the detrimental impact of information overload on user participation, in this paper we design and evaluate several algorithms to filter and rank the information on Social Networking Sites (SNS). As a first step we identify the factors that impact user evaluations of information shared through these networks in a set of regression analyses. Second, we use a Neural Network algorithm to predict three dimensions of user evaluations: affective, cognitive and instrumental value of information shared. Moreover, we design algorithms that allow not only to filter out the irrelevant information, but also rank the information on SNS in order of its relevance. As a result, the filtering algorithm accurately predicts in 73% of the cases, whereas for more than 70% of the users the individual ranking accuracy lies over 70%. The designed algorithms can be implemented by SNS providers in order to present users with more relevant and better structured information.
Koroleva, Ksenia and Bolufé Röhler, Antonio José, "REDUCING INFORMATION OVERLOAD: DESIGN AND EVALUATION OF FILTERING & RANKING ALGORITHMS FOR SOCIAL NETWORKING SITES" (2012). ECIS 2012 Proceedings. Paper 12.