How exposure to different opinions impacts the life cycle of social media

As a lot of communication and media consumption moves online, people may be exposed to a wider population and more diverse opinions. However, individuals may act differently when faced with opinions far removed from their own. Moreover, changes in the frequency of visits, posting, and other forms of expression could lead to narrowing of the opinions that each person observes, as well as changes in the customer base for online platforms. Despite increasing research on the rise and fall of online social media outlets, user activity in response to exposure to others’ opinions has received little attention. In this study, we first introduce a method that maps opinions of individuals and their generated content on a multi-dimensional space by factorizing an individual–object interaction (e.g., user-news rating) matrix. Using data on 6151 users interacting with 287,327 pieces of content over 21 months on a social media platform we estimate changes in individuals’ activities in response to interaction with content expressing a variety of opinions. We find that individuals increase their online activities when interacting with content close to their own opinions, and interacting with extreme opinions may decrease their activities. Finally, developing an agent-based simulation model, we study the effect of the estimated mechanisms on the future success of a simulated platform.

Total weekly posts, and b total weekly comments; for communities with wider bias levels over 1000 days. Red lines represent less biased communities and blue lines representmore extremely biased communities

Besides exploring the impact of consumed opinions on user activities, some practical implications follow from our results. First, it seems that keeping users entails engaging them with content that is closely aligned to their opinions (i.e., by creating clusters of likeminded users and feeding them with content generated among themselves). Most of the social network platforms today use recommendations and ranking algorithms that work based on the proximity of opinions. Some extract users’ opinions directly (using methods such as collaborative filtering) and feed the users content that has proven interesting to other likeminded people (e.g., Netflix and Pandora recommend movies and songs to users based on the taste of other users), while others use different proxies to feed users content closely aligned to their own opinions (e.g., Facebook feeds its users content shared by their friends or pages in which they are interested). Both cases create plurality in communities, which, based on our results, increases the life cycle of outlets. Yet, ranking algorithms in both cases treat all of the opinion groups the same, which may not be optimal. There is no difference in the ranking of opponents’ stories for supporters and supporters’ stories for opponents, although they may react differently to opposing opinions. Our study, however, shows that different opinion groups could be treated according to their overall reactions, in order to maximize user activity rates.

Distribution of users opinion on the understudy social media

You can find this paper here.