Differences in Knowledge Adoption Among Task Types in Human-AI Collaboration Under the Chronic Disease Prevention Scenario

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 experts scored the objective effectiveness. 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.