Newsfeed Screening for Behavioral Therapy to Social Network Mental Disorders

While the popularity of social network applications continues to grow, increasing cases of social networkmental disorders (SNMDs) are also noted. For behavioral therapy of SNMDs, an idea, similar to providing electronic cigareŠes to addictive smokers, is to substitute highly-addictive newsfeeds with safer, less-addictive ones to those users. Nevertheless, this idea faces two major challenges: 1) how to measure the addictive degree of a newsfeed to an SNMD user, and 2) how to exploit the theories in Psychology to determine appropriate substitution of newsfeeds for the therapy. To address these issues, in this paper, we propose a learning framework, namely, SNMD-Aware Personalized nEwsfeed Ranking (SAPER), that exploits features extracted from social network data to measure the addictive degree of a newsfeed. With the quanti€ed addictive degrees of newsfeeds, we formulate a new optimization problem, namely, Multi-Ecacy Maximization with Interest Constraint (MEMIC), to maximize the ecacy of the behavioral therapy, without sacri€cing the interests of users. Accordingly, we propose a randomized algorithm called Computing Budget Optimization for MEMIC with Newsfeed Di‚erentiation (CBOM-ND). To validate our idea, we conduct a user study on 517 online social network users to evaluate the proposed SAPER framework. Moreover, we conduct experiments on large-scale datasets to evaluate the proposed CBOM-ND. Œe results show that our approach is promising for alleviating the symptoms of online social network users with potential SNMDs.