Communicating with Machines: Conversational Agents with Personality and the Role of Extraversion

Abstract

Communication with conversational agents (CA) has become increasingly important. It therefore is crucial to understand how individuals perceive interaction with CAs and how the personality of both the CA and the human can affect the interaction experience. As personality differences are manifested in language cues, we investigate whether different language style manifestations of extraversion lead to a more anthropomorphized perception (specifically perceived humanness and social presence) of the personality bots. We examine, whether individuals rate communication satisfaction of a CA similar to their own personality as higher (law of attraction). The results of our experiment indicate that highly extraverted CAs are generally better received in terms of social presence and communication satisfaction. Further, incorporating personality into CAs increases perceived humanness. Although no significant effects could be found in regard to the law of attraction, interesting findings about ambiverts could be made. The outcomes of the experiment contribute towards designing personality-adaptive CAs.

Segmentation of the Young Elderly Based on Technology Readiness

“…In further research, the concrete influencing components of an interaction are also to be identified in order to develop concrete guidelines and design patterns for the active design of interactions on this basis. In addition, the technologies currently discussed in IS and their applications such as emotion recognition , personality mining (Ahmad et al, 2021)…”

Data Management Platforms: An Empirical Taxonomy

“…In further research, the concrete influencing components of an interaction are also to be identified in order to develop concrete guidelines and design patterns for the active design of interactions on this basis. In addition, the technologies currently discussed in IS and their applications such as emotion recognition (Meyer et al, 2019), personality mining (Ahmad et al, 2021), AI or chatbots are to be examined in relation to the Value in Interaction Model. The aim is to find out how these technologies have to be integrated into the interactions between retailers and customers in order to generate value and what contribution they make to the PRQ in comparison to each other.…”

A Framework of Personality Cues for Conversational Agents

“…For example, in paraverbal language, cues such as speech rate range, loudness or fundamental frequency distinguish submissive from dominant individuals [35]. On all three communication levels, such language cues can be used to help imbue CAs with personalities, in order to sustain more human-like interactions with people [13,14,15]. A combination of these linguistic cues can further help portray a specific CA personality: as some contexts, for example in mental health care, require CAs to have a more emphatic and agreeable personality rather than a neurotic personality.…”

“…In recent years, researchers have specifically focused on designing human-like CAs by giving them a personality: first, to propose more complete cognitive models of CAs, and second, to propose CAs capable of sustaining more human-like interactions with people [13,14,15]. The Big Five model of personality has emerged as a standard in psychology, with research over the last fifty years systematically documenting correlations between personality traits and a wide range of behaviors [16,17,18].…”