ABSTRACT
Chatbots’ growing popularity has brought new challenges to HCI, having changed the patterns of human interactions with computers. The increasing need to approximate conversational interaction styles raises expectations for chatbots to present social behaviors that are habitual in human–human communication. In this survey, we argue that chatbots should be enriched with social characteristics that cohere with users’ expectations, ultimately avoiding frustration and dissatisfaction. We bring together the literature on disembodied, text-based chatbots to derive a conceptual model of social characteristics for chatbots. We analyzed 56 papers from various domains to understand how social characteristics can benefit human–chatbot interactions and identify the challenges and strategies to designing them. Additionally, we discussed how characteristics may influence one another. Our results provide relevant opportunities to both researchers and designers to advance human–chatbot interactions.
Disclosure of potential conflict of interest
No potential conflict of interest was reported by the authors.
Supplementary material
Supplemental data for this article can be accessed on the publisher’s website.
Notes
1. https://botlist.co/
2. see more details in the supplementary materials.
Additional information
Notes on contributors
Ana Paula Chaves
Ana Paula Chaves is a Ph.D. Candidate at the Northern Arizona University and a Faculty at the Federal University of Technology - Paraná, Campus Campo Mourão, Brazil. She researches social aspects of human-chatbot interactions as well as technologies for tourism. More information at http://anachaves.pro.br
Marco Aurelio Gerosa
Marco Aurelio Gerosa is an Associate Professor at the Northern Arizona University. He researches Software Engineering and CSCW, having served on the program committee of important conferences, such as FSE, CSCW, SANER, and MSR. He is an ACM and IEEE senior member. For more information, visit http://www.marcoagerosa.com