Jelle Boers , Terra Etty , Martine Baars , Kim van Boekhoven
{"title":"Exploring cognitive strategies in human-AI interaction: ChatGPT's role in creative tasks","authors":"Jelle Boers , Terra Etty , Martine Baars , Kim van Boekhoven","doi":"10.1016/j.yjoc.2025.100095","DOIUrl":null,"url":null,"abstract":"<div><div>This study investigated the cognitive strategies employed by dyads when utilizing ChatGPT's examples to generate ideas in creative tasks. Fourteen university students generated ideas for both function-first and form-first creative tasks in interaction with ChatGPT. Their 591 turns were analyzed using both self-reports and coded transcripts to categorize cognitive strategies such as conceptual combination, inspiration, improvement, and repetition. The results indicated that students less frequently employ cognitive strategies focusing on human-AI interaction (e.g., inspiration, improve, combine), but that most of the ideas were produced by repeating ChatGPT's idea. This tendency suggests that, when given freedom, students may rely heavily on AI-generated suggestions rather than actively engaging in more complex cognitive processes. A key practical implication of these findings is the importance of educating students on different cognitive strategies they can adopt in collaboration with AI tools. By guiding students to employ more diverse and active cognitive strategies, ChatGPT has the potential to become a more effective tool for enhancing creative thinking in higher education.</div></div>","PeriodicalId":100769,"journal":{"name":"Journal of Creativity","volume":"35 1","pages":"Article 100095"},"PeriodicalIF":0.0000,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Creativity","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2713374525000020","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This study investigated the cognitive strategies employed by dyads when utilizing ChatGPT's examples to generate ideas in creative tasks. Fourteen university students generated ideas for both function-first and form-first creative tasks in interaction with ChatGPT. Their 591 turns were analyzed using both self-reports and coded transcripts to categorize cognitive strategies such as conceptual combination, inspiration, improvement, and repetition. The results indicated that students less frequently employ cognitive strategies focusing on human-AI interaction (e.g., inspiration, improve, combine), but that most of the ideas were produced by repeating ChatGPT's idea. This tendency suggests that, when given freedom, students may rely heavily on AI-generated suggestions rather than actively engaging in more complex cognitive processes. A key practical implication of these findings is the importance of educating students on different cognitive strategies they can adopt in collaboration with AI tools. By guiding students to employ more diverse and active cognitive strategies, ChatGPT has the potential to become a more effective tool for enhancing creative thinking in higher education.