How Community Feedback Shapes User Behavior

By Justin Cheng, Cristian Danescu-Niculescu-Mizil, Jure Leskovec. 2014

145 citations recorded by the source corpus.

Social media systems rely on user feedback and rating mechanisms for personalization, ranking, and content filtering. However, when users evaluate content contributed by fellow users (e.g., by liking a post or voting on a comment), these evaluations create complex social feedback effects. This paper investigates how ratings on a piece of content affect its author's future behavior. By studying four large comment-based news communities, we find that negative feedback leads to significant behavioral changes that are detrimental to the community. Not only do authors of negatively-evaluated content contribute more, but also their future posts are of lower quality, and are perceived by the community as such. Moreover, these authors are more likely to subsequently evaluate their fellow users negatively, percolating these effects through the community. In contrast, positive feedback does not carry similar effects, and neither encourages rewarded authors to write more, nor improves the quality of their posts. Interestingly, the authors that receive no feedback are most likely to leave a community. Furthermore, a structural analysis of the voter network reveals that evaluations polarize the community the most when positive and negative votes are equally split.

Subfields: Communication, Information Systems, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Communication

In Information Systems

In Statistical and Nonlinear Physics

Citations in the corpus

You Can't Stay Here (2017, background): “While some kinds of moderation can be effective [41], moderation can also make things worse [7, 9].”
Fine-Grained Car Detection for Visual Census Estimation (2017, background): “However, the emergence of large, diverse sets of data generated by people has enabled computer scientists and computational sociologists to gain interesting insights by analyzing massive user texts and social networks (West et al. 2014; Cheng, Danescu-Niculescu-Mizil, and Leskovec 2014).”
Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions (2017, background): “More relevant is work showing that getting downvoted leads people to downvote others more and post content that gets further downvoted in the future [17].”
Antisocial Behavior in Online Discussion Communities (2015, background): “For instance, a low proportion of up-votes received has been shown to be perceived negatively by users (Cheng, Danescu-Niculescu-Mizil, and Leskovec 2014).”
Distilling the Outcomes of Personal Experiences: A Propensity-scored Analysis of Social Media (2017, background): “Recent studies looking at migration patterns [99], shifts in suicidal ideation [28], at the effect of exercise on mental health [31], or of community feedback on individual user behavior [21] try to improve on correlational analyses by applying causal inference techniques that have come into extensi”