Customers are increasingly interacting with intelligent technologies such as conversational agents (CA). While the majority of CAs process natural language and react in a human way, they however, do not adapt or react to their users’ personalities. Responding appropriately to a user’s behavior forms an important aspect for the interaction quality. Since studies have identified personality markers in language, we use these findings to design a personality adaptive CA called “Raffi”. Following the Design Science Research approach, we prototyped Raffi, who automatically infers users’ personality traits and adapts accordingly to their personality by using language that is specific to a particular personality dimension. A first evaluation of the prototype showed that participants noticed personality differences manifested in language and perceived communicating with Raffi as positive. The concept of a personality adaptive CA is expected to contribute to HCI research by highlighting the role of personality for users’ interaction experience.
Ahmad, Rangina; Siemon, Dominik; Fernau, Daniel; and Robra-Bissantz, Susanne, "Introducing “Raffi”: A Personality Adaptive Conversational Agent" (2020). PACIS 2020 Proceedings. 28.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.