Providing awareness, explanation and control of personalized stream filtering in a P2P social network

In Online Social Networks (OSNs), users are often overwhelmed with a huge amount of social data, most of which are irrelevant to their interest. Filtering of the social data stream is the common way to deal with this problem, and it has already been applied by OSNs, such as Facebook and Google+. Unfortunately, personalized filtering leads to “the filter bubble” problem where the user is trapped inside a world within the limited boundaries of her interests and cannot be exposed to any surprising, desirable information. Moreover, these OSNs are black boxes, providing no transparency for the user about how the filtering mechanism decides what is to be shown in the activity stream. As a result, the user trust in the system can decline. This thesis presents an interactive method to visualize the personalized stream filtering in OSNs. The proposed visualization helps to create awareness, explanation, and control of personalized stream filtering to alleviate “the filter bubble” problem and increase the users’ trust in the system. The visualization is implemented in MADMICA – a new privacy-aware decentralized OSN, based on the Friendica P2P protocol, which filters the social updates stream of users based on their interests. The results of three user evaluations are presented in this thesis: small-scale pilot study, qualitative study and large-scale quantitative study with 326 participants. The results of the small-scale study show that the filter bubble visualization makes the users aware of the filtering mechanism, engages them in actions to correct and change it, and as a result, increases the users’ trust in the system. The qualitative study reveals a generally higher proportion of desirable user perceptions for the awareness, explanation and control of the filter bubble provided by the visualization. Moreover, the results of the quantitative study demonstrate that the visualization leads to increased users’ awareness of the filter bubble, understandability of the filtering mechanism and to a feeling of control over the data stream they are seeing