Publication: Twitter session analytics: profiling susers' short-term behavioral changes
Loading...
Identifiers
Publication date
2016-10-19
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Impact
Export
Abstract
Human behavior shows strong daily, weekly, and monthlypatterns. In this work, we demonstrate online behavioral changes thatoccur on a much smaller time scale: minutes, rather than days or weeks.Specifically, we study how people distribute their effort over differenttasks during periods of activity on the Twitter social platform. Wedemonstrate that later in a session on Twitter, people prefer to perform simpler tasks, such as replying and retweeting others' posts, ratherthan composing original messages, and they also tend to post shortermessages. We measure the strength of this effect empirically and statistically using mixed-effects models, and find that the first post of a sessionis up to 25 % more likely to be a composed message, and 10-20 % lesslikely to be a reply or retweet. Qualitatively, our results hold for differentpopulations of Twitter users segmented by how active and well-connectedthey are. Although our work does not resolve the mechanisms responsible for these behavioral changes, our results offer insights for improvinguser experience and engagement on online social platforms.
Description
[Proceeding of]: 8th International Conference (SocInfo 2016), Bellevue, WA, USA, November 11-14, 2016.
Keywords
Online Social Network, Twitter user, Activity session, Social platform, Index coefficient
Bibliographic citation
Spiro, Emma; Ahn, Yong-Yeol, (eds.) Social Informatics: SocInfo 2016, Bellevue, WA, USA, November 11–14, 2016 Proceedings, Part II. New York: Springer. Pp.: 71-86. (Lecture notes in computer science; 10047).