Why Do We Turn to Virtual Companions? A Text Mining Analysis of Replika Reviews

Siemon, Dominik; Strohmann, Timo; Khosrawi-Rad, Bijan; de Vreede, Triparna; Elshan, Edona; Meyer, Michael

Zusammenfassung

Many people globally experience the feeling of loneliness and struggle with its consequences. A modern way
to deal with this loneliness and lack of companionship is to use empathetic and emotional conversational
agents. Often referred to as virtual companions, these agents can engage in human-like conversations with
their users and build relationships with them through modern artificial intelligence technologies. One
established service of such virtual companions is Replika, which we investigate in this study to explore what
users expect to gain from long-term interactions with virtual companions and what they tend to talk about
with them. Using a text mining approach and 119,831 reviews of the Replika service, we analyze users'
sentiments, emotions, and topics. Our results show that users interact with virtual companions to cope with
their loneliness and, especially, to address their mental well-being. Furthermore, Replika users have a joyful
and beneficial experience during long-term interaction with such virtual companions.

Schlüsselwörter

Conversational Agent, Virtual Companion, Chatbot, Replika, Text Mining

Zitieren als

Siemon, D., Strohmann, T., Khosrawi-Rad, B., de Vreede, T., Elshan, E., & Meyer, . (2022). Why Do We Turn to Virtual Companions? A Text Mining Analysis of Replika Reviews. In Aguirre-Urreta, M. I., Wu, D., & Jenkins, J. (Eds.), AMCIS 2022 Proceedings (pp. 1288–1288). SIG HIC — Human Computer Interaction: Vol. 10. Minnesota: AIS eLibrary.

Details

Publikationstyp
Forschungsartikel in Sammelband (Konferenz)

Begutachtet
Ja

Publikationsstatus
Veröffentlicht

Jahr
2022

Konferenz
Twenty-eighth Americas Conference on Information Systems

Konferenzort
Minneapolis

Buchtitel
AMCIS 2022 Proceedings

Herausgeber
Aguirre-Urreta, Miguel I.; Wu, Dezhi; Jenkins, Jeff

Erste Seite
1288

Letzte Seite
1288

Band
10

Reihe
SIG HIC - Human Computer Interaction

Verlag
AIS eLibrary

Ort
Minnesota

Sprache
Englisch

ISBN
978-1-958200-00-1

Gesamter Text