Background: Conversational agents cannot yet express empathy in nuanced ways that account for the unique circumstances of the user. Agents that possess this faculty could be used to enhance digital mental health interventions. Objective: We sought to design a conversational agent that could express empathic support in ways that might approach, or even match, human capabilities. Another aim was to assess how users might appraise such a system. Methods: Our system used a corpus-based approach to simulate expressed empathy. Responses from an existing pool of online peer support data were repurposed by the agent and presented to the user. Information retrieval techniques and word embeddings were used to select historical responses that best matched a user’s concerns. We collected ratings from 37,169 users to evaluate the system. Additionally, we conducted a controlled experiment (N=1284) to test whether the alleged source of a response (human or machine) might change user perceptions. Results: The majority of responses created by the agent (2986/3770, 79.20%) were deemed acceptable by users. However, users significantly preferred the efforts of their peers (P<.001). This effect was maintained in a controlled study (P=.02), even when the only difference in responses was whether they were framed as coming from a human or a machine. Conclusions: Our system illustrates a novel way for machines to construct nuanced and personalized empathic utterances. However, the design had significant limitations and further research is needed to make this approach viable. Our controlled study suggests that even in ideal conditions, nonhuman agents may struggle to express empathy as well as humans. The ethical implications of empathic agents, as well as their potential iatrogenic effects, are also discussed.

/pdf/towards-an-artificially-empathic-conversational-agent-for-37su8gllqa.pdf

A Way of Being

Towards an Artificially Empathic Conversational Agent for Mental Health Applications: System Design and User Perceptions.

The Balance of Personality

Reflective practice is widely adopted across the field of experience-based learning subjects in higher education, including practicums, work-integrated learning, internships, service learning and community participation. This adoption of reflective practice implies that it supports student learning through experience. When reviewing the evidence for the role of reflection for learning, it became evident that not only was there no clear agreement about the definition of reflection, there has been little theoretical development in this area. An integrated participatory action research and ecological approach was adopted to build a theory about the ecology of reflection for learning through experience. Through this process the assumptions, or truths that are taken for granted, that underpin the new theory were declared and substantiated. Key concepts and the principle tenets of the theory were then identified and defined, leading to an overview of the ecologies of the learner, the learning context and the experiential learning context.

background

/pdf/towards-a-theory-of-the-ecology-of-reflection-reflective-3swnk0kr5c.pdf

Towards a theory of the ecology of reflection: reflective practice for experiential learning in higher education

/pdf/the-core-conditions-of-peer-mentoring-fa4s6o15cx.pdf

The core conditions of peer mentoring

We examined how merely sharing attitudes with a good listener shapes speakers' attitudes. We predicted that high-quality (i.e., empathic, attentive, and nonjudgmental) listening reduces speakers' social anxiety and leads them to delve deeper into their attitude-relevant knowledge (greater self-awareness). This, subsequently, differentially affects two components of speaker's attitude certainty by increasing attitude clarity, but not attitude correctness. In addition, we predicted that this increased clarity is followed by increased attitude- expression intentions, but not attitude- persuasion intentions. We obtained consistent support for our hypotheses across five experiments (including one preregistered study), manipulating listening behavior in a variety of ways. This is the first evidence that an interpersonal variable, unrelated to the attitude itself, can affect attitude clarity and its consequences.

A Way of Being

Citations

Towards an Artificially Empathic Conversational Agent for Mental Health Applications: System Design and User Perceptions.

The Balance of Personality

Towards a theory of the ecology of reflection: reflective practice for experiential learning in higher education

The core conditions of peer mentoring

The Listener Sets the Tone: High-Quality Listening Increases Attitude Clarity and Behavior-Intention Consequences.

Related Papers (2)

A Way In

In a way和In the way的辨析