=Paper=
{{Paper
|id=Vol-1622/SocInf2016_InvitedTalk2
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-1622/SocInf2016_InvitedTalk2.pdf
|volume=Vol-1622
}}
==None==
<pdf width="1500px">https://ceur-ws.org/Vol-1622/SocInf2016_InvitedTalk2.pdf</pdf>
<pre>
Proceedings of the 2nd International Workshop on Social Influence Analysis (SocInf 2016)
July 9th, 2016 - New York, USA




   Invited Talk

   Negative Social Influence in Online Discussions
   Justin Cheng
   Computer Science Department at Stanford University

   Abstract
   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. First, by studying four large comment-based news communities, we
   investigate the influence of such feedback on future user behavior. How may positive or
   negative feedback percolate through a community? Next, we focus on the impact of negative
   behavior (i.e., trolling) on a community - quantifying the effects of both trolls and trolling on the
   community at large through a combination of experimentation and large-scale longitudinal
   analysis.

   Biographical Sketch
                                            Justin Cheng is a PhD candidate in the Computer Science
                                            Department at Stanford University, where he is advised by
                                            Jure Leskovec and Michael Bernstein. His research lies at the
                                            intersection of data mining and crowdsourcing, and focuses on
                                            cascading behavior in social networks. This work has received
                                            several best paper nominations at CHI, CSCW, and ICWSM.
                                            He is also a recipient of an MSR PhD Fellowship.




                                                               2

</pre>