Co-constructing intersubjectivity with artificial conversational agents: People are more likely to initiate repairs of misunderstandings with agents represented as human

How Do You Want Your Chatbot? An Exploratory Wizard-of-Oz Study with Young, Urban Indians

“…There is also work in sociable robots that are able to communicate and interact with users, understand and relate to them in social or human terms, and learn and adapt throughout their lifetimes [9]. Recent work has shown that people more frequently attempt to repair misunderstandings when speaking to an artificial conversational agent if it is represented as a human body interface (agent's responses vocalized by a human speech shadower), compared to when the agent's responses were shown as a text screen [14]. Then there is work in embodied conversational agents that take on a physical form with the intent of eliciting more natural communication with users.…”

Untitled

“…Somewhat contrary to the above studies on the benefits of transparency, Murgia, Janssens, Demeyer, and Vasilescu (2016) found that, when deploying a bot that answered users' questions in the Stack Overflow community, the bot was regarded more positively when posing as a human than when revealing its bot identity. In a similar vein, Corti and Gillespie (2016) found users more likely to expend effort in making themselves understood when the agent's chat content was conveyed through a human (the so-called echoborg method) than through a text-based interface. Hence, transparency in the machine identity and capabilities of a chatbot may work counter to its intention.…”

Where is the Bot in our Team? Toward a Taxonomy of Design Option Combinations for Conversational Agents in Collaborative Work

“…Open domain CAs often have chitchat purposes and lack boundaries of a specified task or context information of a closed knowledge field, e.g. [8,16,27].…”

“…[11,15,20] and such that are non goal-oriented (CGN), e.g. [8,41,45], whose value lies in the interaction itself.…”