Authors:
Ema Kušen
1
and
Mark Strembeck
2
Affiliations:
1
Vienna University of Economics and Business (WU Vienna), Austria
;
2
Vienna University of Economics and Business (WU Vienna), Secure Business Austria (SBA) and Complexity Science Hub (CSH), Austria
Keyword(s):
Bot Behavior, Emotion Analysis, Emotional Conformity, Temporal Patterns, Twitter.
Related
Ontology
Subjects/Areas/Topics:
Cloud Computing
;
Collaboration and e-Services
;
Data Communication Networking
;
e-Business
;
Enterprise Information Systems
;
Information Systems
;
Methodologies and Technologies
;
Operational Research
;
Platforms and Applications
;
Social Networks
;
Telecommunications
Abstract:
In this paper, we present a study on the emotions conveyed in bot-generated Twitter messages as compared to emotions conveyed in human-generated messages. Social bots are software programs that automatically produce messages and interact with human users on social media platforms. In recent years, bots have become quite complex and may mimic the behavior of human users. Prior studies have shown that emotional messages may significantly influence their readers. Therefore, it is important to study the effects that emotional bot-generated content has on the reactions of human users and on information diffusion over online social networks (OSNs). For the purposes of this paper, we analyzed 1.3 million Twitter accounts that generated 4.4 million tweets related to 24 systematically chosen real-world events. Our findings show that: 1) bots emotionally polarize during controversial events and even inject polarizing emotions into the Twitter discourse on harmless events such as Thanksgiving,
2) humans generally tend to conform to the base emotion of the respective event, while bots contribute to the higher intensity of shifted emotions (i.e. emotions that do not conform to the base emotion of the respective event), 3) bots tend to shift emotions to receive more attention (in terms of likes and retweets).
(More)