Customizability in conversational agents and their impact on health engagement

Abstract

Conversational agents (CAs) are effective tools for health behavior change, yet little research investigates the mechanisms through which they work. In accordance with the Computer as Social Actors (CASA) paradigm, we suggest that agents are perceived as human-like actors and hence influence behavior much as human coaches might. As such, agents should be designed to resemble ideal interaction patterns-for example, by resembling their users. Our study will test this paradigm by testing the impact of customization on similarity and reciprocity, which in turn are hypothesized to improve perceptions of the agent and compliance with the agent's recommendations.

Patterns of Sociotechnical Design Preferences of Chatbots for Intergenerational Collaborative Innovation: A Q Methodology Study

“…Moreover, as a practical contribution, we demonstrated how the Q methodology represents an alternative systemdesign tool [53]. This methodology can be used for user experience designers [83] to find pattern similarities in different sociotechnical viewpoints used in social inclusion design [52,53,55,84], and also, this study demonstrates the potential of the Q method to identify preferred interaction patterns that can be used to improve personalization and customization of chatbots [22]. Based on our findings, we introduce the idea of using chatbots focused on subjective preferences independently of age and social differences.…”

“…This ongoing evolution of chatbots creates more opportunities for their use as companions in various settings, including a potential technology for intergenerational collaboration [3,64]. The various functions and applications of chatbots that can support intergenerational innovation processes include the following: (1) reducing communicative ambiguity in workplace contexts [18], which can aid in the removal of perceptual barriers by restricting broad topic interpretation and selection options, (2) supporting problem-based learning individuali-zation [23] and collaborative distance learning [65], which can help overcome emotional, cultural, and institutional barriers to learning more about a topic together, and through artificial intelligence and machine learning in a more personal setting [22,23], focusing on identifying common problems and raising awareness of intergenerational differences, and (3) facilitation of debate and consensus building [65], presentation of documents and results, management and administrative support in the cocreation process, and the ability to guide group collaboration in the context of professional work through the aesthetic design and various group work features [66]. These features and functions can help solve technical and operational challenges and promote and support critical issues such as privacy and information credential in the context of institutional barriers.…”

“…However, the study shows that chatbots can assist with such technical and managerial tasks [20]. Likewise, in creative activities such as ideation and cocreation, where divergent perceptions or ways of thinking can hinder creativity, chatbots can assist through social facilitation or inhibition [21] and system customization [22,23].…”

“…Therefore, chatbots should be developed by identifying interaction patterns and involving users in cocreating products and services. This can increase the subjectivity of products and services, allowing for better customization [22].…”

Emotionally Intelligent Chatbots: A Systematic Literature Review

“…Users get frustrated when chatbot responses are irrelevant [13], while a chatbot that verbalizes emotions can enhance the user's mood [14]. Moreover, users often anthropomorphize chatbots, which in turn influences their interaction and behavior [15]. Chatbots that mimic human behavior and emotions lead to increased rapport, higher motivation, and better engagement [16].…”