Preliminary Conference Agenda

Chronic disease prevention is crucial for maintaining national health and reducing medical burden. Transmission of disease prevention knowledge to people through human-AI collaboration is an emerging disruptive and revolutionary approach. Nonetheless, little research has been aimed at the knowledge adoption in different tasks under this scenario. This study explored the differences in knowledge adoption among task types in human-AI collaboration under the chronic disease prevention scenario. Twelve participants were recruited to complete the factual, interpretive, and exploratory tasks in human-AI collaboration. The subjective efficiency and effectiveness of knowledge adoption were obtained by questionnaires. The objective efficiency, including search time, switch frequency, and number of queries, was counted by Screen Recorder, while the objective effectiveness was scored by experts. Furthermore, non-parametric tests were used to compare the differences. The results showed that objective efficiency varied among different task types. Participants spent more time in the interpretive task and switched more pages in the exploratory task. Then, perceived effectiveness was the worst in the interpretive task. Finally, the participants got lower scores in the factual task and higher scores in the interpretive task. Therefore, suggestions for the means of human-AI collaboration have been proposed under the chronic disease scenario, including identifying scenarios to enhance user adaptation and immersion in completing different health tasks, enhancing the transparency and explainability of AI, especially in interpretive tasks, and adding references in the process of acquiring and understanding knowledge.

Improving the Q&A ability of government affairs dialogue robots (GDRs) has become an important issue. In practice, a large number of users with poor information literacy often pose vague questions, which makes it challenging for GDRs to comprehend their inquiries within a specific context. In order to enhance contextualization, this study has constructed a multi-turn dialogue model that incorporates R-GCN and fuzzy logic to base on the "question-answer-context" matching process. To obtain more accurate context, we propose a re-question mechanism to further press for contextual details. Additionally, we introduce the sub-graph matching mechanism of fuzzy logic and R-GCN to improve the accuracy of implicitly representation of Chinese logic in the contextualized matching process. This mechanism allows us to prune the context-irrelevant parts in the "answer", and obtain more complete context information. We collected over 300,000 words of real cases as the test-set. The results of the experiments show that this model can significantly improve the contextualized reasoning ability of GDRs in a more humanized way. The innovative response generation method in this research, which utilizes "question-answer-context" matching, is more suitable for complex scenarios where the user may not be articulate. It helps to lower the barrier for accessing government services and provides more user-friendly assistance to individuals with limited information literacy.

With the rapid advancement of artificial intelligence and natural language processing technologies, AI voice assistants are gaining attention for their potential to enable voice shopping. Based on cognitive appraisal theory, this study constructs a theoretical model of AI voice assistant user experience with emotional experience as a mediating variable, and examines the antecedent variables of emotional experience and the mechanism of its effect on users' willingness to adopt AI voice assistant in the context of voice shopping. The study used data collected from 318 users of AI voice assistants. Findings of Partial Least Squares (PLS-SEM) suggest that perceived service quality, and perceived entertainment significantly influence emotional state and emotional attachment towards the users' adoption intention. Perceived anthropomorphism significant influence the emotional attachment but not emotional state. By exploring the role of emotional experience in the user experience of AI voice assistants, this paper proposes suggestions to enhance user experience and promote voice shopping.