Something draws near, I can feel it: An analysis of human and bot emotion-exchange motifs on Twitter - CSH

Something draws near, I can feel it: An analysis of human and bot emotion-exchange motifs on Twitter


Details


Social bots are software programs that automatically produce messages and interact with human users on social media platforms. In this paper, we provide an analysis of the emotion-exchange patterns that arise from bot- and human-generated Twitter messages.

In particular, we analyzed 1.3 million Twitter accounts that generated 4.4 million tweets related to 24 systematically chosen real-world events. To this end, we first identified the intensities of the eight basic emotions (according to Plutchik’s wheel of emotions) that are conveyed in bot- and human-generated messages. We then performed a temporal analysis of the emotions that have been sent during positive, negative, and polarizing events. Furthermore, we investigated the effects on user reactions as well as on the message exchange behavior between bots and humans. In addition, we performed an analysis of the emotion-exchange motifs that occur when bots communicate with humans. For this purpose, we performed a systematic structural analysis of the multiplex communication network that we derived from the 4.4 million tweets in our data-set.

Among other things, we found that 1) in contrast to humans, bots do not conform to the base mood of an event, 2) bots often emotionally polarize during controversial events and even inject polarizing emotions into the Twitter discourse on harmless events such as Thanksgiving, 3) when bots directly exchange messages with human accounts they are, however, indistinguishable from humans with respect to the emotions they send, 4) direct message exchanges between bots and humans result in characteristic and statistically significant emotion-exchange motifs.

 

E. Kušena, M. Strembeck, Something draws near, I can feel it: An analysis of human and bot emotion-exchange motifs on Twitter, Online Social Networks and Media, Vols. 10–11 (2019) 1–17

Linked Reseachers