Journal of Computer Assisted Learning最新文献

{"title":"The Impact of AI-Supported Think-Pair-Share Instruction on Students' Problem-Solving Skills and Motivation in Learning Quadratic Equations: A Social Constructivist Perspective","authors":"Belaynesh Kassanew, Cathy Weng, Melese Astatke, Yamral Kassanew","doi":"10.1002/jcal.70271","DOIUrl":"https://doi.org/10.1002/jcal.70271","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Quadratic equations are a cornerstone of algebra and serve as a gateway to advanced mathematical concepts. Despite their importance, students frequently struggle with conceptual understanding, procedural accuracy, and sustained motivation when learning mathematics, particularly quadratic equations. Traditional instruction often fails to address these difficulties, leading to persistent misconceptions and disengagement. Artificial intelligence (AI) shows promise in offering adaptive feedback and customised support, but research mainly focuses on its role in helping individual learners. On the other hand, the Think-Pair-Share (TPS) model, grounded in Vygotsky's social constructivist theory, has been proven effective in fostering collaboration, critical thinking, and communication. However, limited studies have explored how AI can be systematically integrated into structured collaborative learning approaches such as TPS to enhance both problem-solving and motivation.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Rationale and Objectives</h3>\u0000 \u0000 <p>This study introduces a novel instructional model that embeds AI scaffolding into each phase of the TPS process. Rather than replacing teacher facilitation, AI functions as a supportive scaffold that delivers individualised prompts during the <i>Think</i> stage, facilitates peer negotiation in the <i>Pair</i> stage, and provides clarification or reinforcement in the <i>Share</i> stage. This integration ensures consistent, contextualised guidance while maintaining the collaborative essence of TPS. The study therefore, aims to examine the effectiveness of AI-supported TPS instruction in enhancing junior high school students' problem-solving skills and motivation in learning quadratic equations.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>This study employed a quasi-experimental design with a non-equivalent control group. A total of 43 junior high school students participated, with the experimental group receiving AI-enhanced TPS instruction and the control group following traditional TPS instruction with online Google searches. Data were collected using two instruments: a problem-solving test to measure students' learning outcomes and a mathematics motivation questionnaire to assess intrinsic motivation, interest, and self-efficacy. The data were analysed using analysis of covariance (ANCOVA) to control for pre-test differences and determine the impact of the intervention.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results and Conclusions</h3>\u0000 \u0000 <p>The findings indicate significant improvements in both problem-solving skills and motivation for the experimental group compared to the co","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148174176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging Multimodal Large Language Models to Analyse Student Exploration Behaviours in Educational Game Environments","authors":"Yiqiu Zhou,&nbsp;Xiner Liu,&nbsp;Andres Felipe Zambrano,&nbsp;Luc Paquette,&nbsp;Amanda Barany,&nbsp;Jaclyn Ocumpaugh,&nbsp;Ryan S. Baker,&nbsp;Jeff Ginger","doi":"10.1002/jcal.70269","DOIUrl":"https://doi.org/10.1002/jcal.70269","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Video data provides rich opportunities to examine student behaviour in game-based learning environments, capturing not only observable actions but also subtle indicators of cognitive engagement. However, traditional video analysis is labor-intensive, and current applications of AI to this task are limited by models trained on general-purpose datasets, which often fail to capture the pedagogical meaning of student actions in authentic educational contexts.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Objectives</h3>\u0000 \u0000 <p>This study explores how multimodal large language models (MLLMs), specifically LLaVA-Video-7B-Qwen2, can support qualitative video analysis of student exploration behaviours in a Minecraft-based STEM learning environment.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We conducted an exploratory case study using screen recordings from a Minecraft-based STEM learning environment. We tested multiple prompt strategies for guiding MLLM-generated video descriptions and found that role-assignment prompting performed most effectively. We evaluated model outputs using a mixed-method framework that included quantitative scoring, GPT-based judgement, and researcher validation.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results and Conclusions</h3>\u0000 \u0000 <p>Our findings show that MLLMs can reliably identify surface-level behaviours, such as navigation patterns and object interactions, but struggle to infer the intent or goals behind student actions, leading to a significant rate of over-interpretation (26.5% when explaining student strategies). The model's outputs are sensitive to prompt phrasing, underscoring the importance of prompt engineering. While current MLLMs show promise for streamlining parts of the video analysis workflow, their use in educational contexts requires structured oversight and careful interpretation to ensure reliability and relevance.</p>\u0000 </section>\u0000 </div>","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/jcal.70269","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148174174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging Multimodal Large Language Models to Analyse Student Exploration Behaviours in Educational Game Environments","authors":"Yiqiu Zhou,&nbsp;Xiner Liu,&nbsp;Andres Felipe Zambrano,&nbsp;Luc Paquette,&nbsp;Amanda Barany,&nbsp;Jaclyn Ocumpaugh,&nbsp;Ryan S. Baker,&nbsp;Jeff Ginger","doi":"10.1002/jcal.70269","DOIUrl":"https://doi.org/10.1002/jcal.70269","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Video data provides rich opportunities to examine student behaviour in game-based learning environments, capturing not only observable actions but also subtle indicators of cognitive engagement. However, traditional video analysis is labor-intensive, and current applications of AI to this task are limited by models trained on general-purpose datasets, which often fail to capture the pedagogical meaning of student actions in authentic educational contexts.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Objectives</h3>\u0000 \u0000 <p>This study explores how multimodal large language models (MLLMs), specifically LLaVA-Video-7B-Qwen2, can support qualitative video analysis of student exploration behaviours in a Minecraft-based STEM learning environment.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We conducted an exploratory case study using screen recordings from a Minecraft-based STEM learning environment. We tested multiple prompt strategies for guiding MLLM-generated video descriptions and found that role-assignment prompting performed most effectively. We evaluated model outputs using a mixed-method framework that included quantitative scoring, GPT-based judgement, and researcher validation.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results and Conclusions</h3>\u0000 \u0000 <p>Our findings show that MLLMs can reliably identify surface-level behaviours, such as navigation patterns and object interactions, but struggle to infer the intent or goals behind student actions, leading to a significant rate of over-interpretation (26.5% when explaining student strategies). The model's outputs are sensitive to prompt phrasing, underscoring the importance of prompt engineering. While current MLLMs show promise for streamlining parts of the video analysis workflow, their use in educational contexts requires structured oversight and careful interpretation to ensure reliability and relevance.</p>\u0000 </section>\u0000 </div>","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/jcal.70269","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148173835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Impact of AI-Supported Think-Pair-Share Instruction on Students' Problem-Solving Skills and Motivation in Learning Quadratic Equations: A Social Constructivist Perspective","authors":"Belaynesh Kassanew,&nbsp;Cathy Weng,&nbsp;Melese Astatke,&nbsp;Yamral Kassanew","doi":"10.1002/jcal.70271","DOIUrl":"https://doi.org/10.1002/jcal.70271","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Background&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;Quadratic equations are a cornerstone of algebra and serve as a gateway to advanced mathematical concepts. Despite their importance, students frequently struggle with conceptual understanding, procedural accuracy, and sustained motivation when learning mathematics, particularly quadratic equations. Traditional instruction often fails to address these difficulties, leading to persistent misconceptions and disengagement. Artificial intelligence (AI) shows promise in offering adaptive feedback and customised support, but research mainly focuses on its role in helping individual learners. On the other hand, the Think-Pair-Share (TPS) model, grounded in Vygotsky's social constructivist theory, has been proven effective in fostering collaboration, critical thinking, and communication. However, limited studies have explored how AI can be systematically integrated into structured collaborative learning approaches such as TPS to enhance both problem-solving and motivation.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Rationale and Objectives&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;This study introduces a novel instructional model that embeds AI scaffolding into each phase of the TPS process. Rather than replacing teacher facilitation, AI functions as a supportive scaffold that delivers individualised prompts during the &lt;i&gt;Think&lt;/i&gt; stage, facilitates peer negotiation in the &lt;i&gt;Pair&lt;/i&gt; stage, and provides clarification or reinforcement in the &lt;i&gt;Share&lt;/i&gt; stage. This integration ensures consistent, contextualised guidance while maintaining the collaborative essence of TPS. The study therefore, aims to examine the effectiveness of AI-supported TPS instruction in enhancing junior high school students' problem-solving skills and motivation in learning quadratic equations.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Methods&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;This study employed a quasi-experimental design with a non-equivalent control group. A total of 43 junior high school students participated, with the experimental group receiving AI-enhanced TPS instruction and the control group following traditional TPS instruction with online Google searches. Data were collected using two instruments: a problem-solving test to measure students' learning outcomes and a mathematics motivation questionnaire to assess intrinsic motivation, interest, and self-efficacy. The data were analysed using analysis of covariance (ANCOVA) to control for pre-test differences and determine the impact of the intervention.&lt;/p&gt;\u0000 &lt;/section&gt;\u0000 \u0000 &lt;section&gt;\u0000 \u0000 &lt;h3&gt; Results and Conclusions&lt;/h3&gt;\u0000 \u0000 &lt;p&gt;The findings indicate significant improvements in both problem-solving skills and motivation for the experimental group compared to the co","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148174175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"","authors":"","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148095663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"","authors":"","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148096655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"","authors":"","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148093386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"","authors":"","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148090033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"","authors":"","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148090031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"","authors":"","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":48071,"journal":{"name":"Journal of Computer Assisted Learning","volume":"42 4","pages":""},"PeriodicalIF":4.6,"publicationDate":"2026-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148090032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}