Host: The Japanese Society for Artificial Intelligence
Name : The 100th SIG-SLUD
Number : 100
Location : [in Japanese]
Date : February 29, 2024 - March 01, 2024
Pages 74-78
In face-to-face situations, the expression someone gives off is mainly produced through the body, but this is not true in SNS. Nevertheless, information that influences one's impressions is likely conveyed by not only verbal descriptions but also some means equivalent to bodily expression in SNS. In this research, we analyzed the ways of impression management in different accounts of an ekaki on Twitter by extracting some pairs of daily tweets, in both of which the same event is described. The results showed that in the "front" account, the granularity of sentences was lower by using peculiar onomatopoeia or illustrations to express situations, and the seriousness was lower by using pictograms or jokes. On the other hand, in the "back" account, the granularity of sentences was higher by describing changes over time or the detailed situation, and the seriousness was higher by using periods or appropriate verbs or verbalizing embodiment.