Evaluating Consideration Level of Responses For Mental Health Chatbots

作     者：Xu, Bei Zhuang, Ziyuan Wang, Yue 

作者机构：Jiangsu Key Laboratory of Big Data Security and Intelligent Processing China School of Computer Science Nanjing University of Posts and Telecommunications China 

出 版 物：《SSRN》 

年 卷 期：2023年

核心收录：

主　　题：Computational electromagnetics 

摘      要：Mental health chatbots are widely used and proven useful in the conversation of psychological treatments. The users of mental health chatbots require considerate responses because they are relatively sensitive or vulnerable. However, current mental health chatbots do not evaluate the consideration level of the responses. Current mental health chatbots generally use the categories of positive and negative to reflect consideration and sharp. This paper proposes a consideration evaluation model (CEM) to evaluate the consideration level of the responses from mental health chatbots. The experiments first prove that positive and negative cannot precisely reflect considerate and sharp, and then prove that CEM can effectively evaluate the consideration level of responses. We further use CEM to test five typical chatbots and the results indicates that some mental health chatbots may give sharp responses. © 2023, The Authors. All rights reserved.