{"id":1947,"date":"2026-06-14T03:18:35","date_gmt":"2026-06-13T19:18:35","guid":{"rendered":"https:\/\/aifed.now\/conference\/?page_id=1947"},"modified":"2026-06-14T03:18:35","modified_gmt":"2026-06-13T19:18:35","slug":"%e4%b8%bb%e9%a1%8c%e5%9b%9b%ef%bc%9a%e8%a9%95%e9%87%8f%e5%9b%9e%e9%a5%8b-%e5%bc%b5%e6%96%87%e8%89%af%ef%bc%8c%e9%9c%8d%e5%bb%ba%e8%b1%aa%ef%bc%8c%e9%84%ad%e9%b4%bb%e5%93%b2-%e8%87%aa%e7%84%b6","status":"publish","type":"page","link":"https:\/\/aifed.now\/conference\/?page_id=1947","title":{"rendered":"\u4e3b\u984c\u56db\uff1a\u8a55\u91cf\u56de\u994b \/ \u5f35\u6587\u826f\uff0c\u970d\u5efa\u8c6a\uff0c\u912d\u9d3b\u54f2 \/ \u81ea\u7136\u79d1\u5354\u4f5c\u6982\u5ff5\u5716\u8a55\u6539\u56de\u994b\u7cfb\u7d71"},"content":{"rendered":"<\/p>\n

\u81ea\u7136\u79d1\u5354\u4f5c\u6982\u5ff5\u5716\u8a55\u6539\u56de\u994b\u7cfb\u7d71<\/h3>\n<\/p>\n
\n

\"\u5f35\u6587\u826f\uff0c\u970d\u5efa\u8c6a\uff0c\u912d\u9d3b\u54f2\"<\/p>\n

\u8b1b\u8005\/Speaker\uff1a<\/strong> \u5f35\u6587\u826f\uff0c\u970d\u5efa\u8c6a\uff0c\u912d\u9d3b\u54f2, Chang Wen-Liang \u3001Huo Chien-hao\u3001Cheng Hung-che <\/span> <\/p>\n<\/div>\n

<\/p>\n

\n

\u5354\u4f5c\u6982\u5ff5\u5716\u7684\u8a55\u4f30\u70ba\u6559\u80b2\u5de5\u4f5c\u8005\u5e36\u4f86\u91cd\u5927\u6311\u6230\uff0c\u7279\u5225\u662f\u5728\u8b58\u5225\u500b\u4eba\u8ca2\u737b\u6c34\u6e96\u548c\u63d0\u4f9b\u53ca\u6642\u3001\u500b\u4eba\u5316\u56de\u994b\u65b9\u9762\u3002\u50b3\u7d71\u7684\u5354\u4f5c\u5b78\u7fd2\u8a55\u4f30\u65b9\u6cd5\u5f80\u5f80\u7121\u6cd5\u6e96\u78ba\u5340\u5206\u500b\u5225\u5b78\u751f\u7684\u8ca2\u737b\uff0c\u5c0e\u81f4\u4e0d\u516c\u5e73\u7684\u8a55\u4f30\u7d50\u679c\u548c\u904e\u91cd\u7684\u6559\u5e2b\u5de5\u4f5c\u8ca0\u64d4\u3002\u96a8\u8457\u751f\u6210\u5f0f\u4eba\u5de5\u667a\u6167\u6280\u8853\u7684\u5feb\u901f\u767c\u5c55\uff0c\u7279\u5225\u662f\u5927\u578b\u8a9e\u8a00\u6a21\u578b\u5728\u6559\u80b2\u8a55\u4f30\u4e2d\u7684\u61c9\u7528\uff0c\u70ba\u89e3\u6c7a\u9019\u4e9b\u6311\u6230\u63d0\u4f9b\u4e86\u65b0\u7684\u6280\u8853\u8def\u5f91\u3002
\n\u672c\u7814\u7a76\u65e8\u5728\uff1a(1)\u900f\u904eAI\u63d0\u793a\u7cfb\u7d71\u69cb\u5efa\u4e26\u9a57\u8b49\u80fd\u5920\u6e96\u78ba\u5206\u6790\u5354\u4f5c\u6982\u5ff5\u5716\u4e26\u8b58\u5225\u500b\u5225\u5b78\u751f\u8ca2\u737b\u7684\u6846\u67b6\uff1b
\n(2)\u5efa\u7acb\u5ba2\u89c0\u7684\u8a08\u7b97\u6a5f\u5236\u4f86\u91cf\u5316\u5354\u4f5c\u6982\u5ff5\u5716\u6d3b\u52d5\u4e2d\u7684\u500b\u4eba\u8ca2\u737b\u503c\uff1b
\n(3)\u8a2d\u8a08\u4e26\u5be6\u65bd\u57fa\u65bc\u500b\u4eba\u8ca2\u737b\u5206\u6790\u7684\u500b\u4eba\u5316\u56de\u994b\u7cfb\u7d71\uff0c\u63d0\u4f9b\u5dee\u7570\u5316\u5b78\u7fd2\u5efa\u8b70\u3002
\n\u6211\u5011\u63a1\u7528\u8a2d\u8a08\u5c0e\u5411\u7814\u7a76\u65b9\u6cd5\uff0c\u5c0d\u8c61\u70ba\u53f0\u7063\u4e09\u500b\u73ed\u7d1a\u768490\u540d\u516b\u5e74\u7d1a\u5b78\u751f\uff0c\u69cb\u5efa\u4e86\u5c08\u9580\u91dd\u5c0d\u81ea\u7136\u79d1\u5b78\u6982\u5ff5\u5716\u8a55\u4f30\u7684\u300c\u89d2\u8272-\u4efb\u52d9-\u6b65\u9a5f-\u898f\u5247\u300d(RTSR)\u63d0\u793a\u512a\u5316\u6846\u67b6\u3002\u7814\u7a76\u4f7f\u7528NotebookLM\u4f5c\u70ba\u4e3b\u8981AI\u8a55\u4f30\u5e73\u53f0\uff0c\u56e0\u5176\u5728\u8655\u7406PDF\u683c\u5f0f\u5354\u4f5c\u6982\u5ff5\u5716\u7684\u6279\u6b21\u8655\u7406\u80fd\u529b\u65b9\u9762\u8868\u73fe\u512a\u7570\u3002\u7814\u7a76\u958b\u767c\u4e86\u4e94\u500b\u7248\u672c\u7684\u63d0\u793a\u512a\u5316\u6846\u67b6\uff0c\u5f9e\u57fa\u790e\u8a55\u4f30(V1.0)\u767c\u5c55\u5230\u500b\u4eba\u5316\u56de\u994b(V5.0)\uff0c\u7cfb\u7d71\u6027\u5730\u63d0\u5347\u4e86\u7cfb\u7d71\u7684\u8a55\u4f30\u6e96\u78ba\u6027\u548c\u56de\u994b\u54c1\u8cea\u3002
\n\u9a57\u8b49\u7d50\u679c\u986f\u793a\u7cfb\u7d71\u5177\u6709\u9ad8\u5ea6\u53ef\u9760\u6027\uff0c\u500b\u4eba\u8ca2\u737b\u5206\u6790\u5728\u8b58\u5225\u984f\u8272\u7de8\u78bc\u5b78\u751f\u8ca2\u737b\u65b9\u9762\u9054\u523094%\u7684\u6e96\u78ba\u7387\u3002\u8ca2\u737b\u503c\u8a08\u7b97\u6a21\u578b\u6709\u6548\u91cf\u5316\u4e86\u56db\u7a2e\u4e0d\u540c\u8ca2\u737b\u985e\u578b\u7684\u5354\u4f5c\u53c3\u8207\u91cf\u548c\u8cea\u3002\u500b\u4eba\u5316\u56de\u994b\u6a5f\u5236\u63d0\u4f9b\u4e86\u7b26\u5408\u5b78\u751f\u8a8d\u77e5\u767c\u5c55\u6c34\u6e96\u7684\u500b\u5225\u5316\u5b78\u7fd2\u5efa\u8b70\uff0c\u986f\u8457\u63d0\u5347\u4e86\u5354\u4f5c\u6982\u5ff5\u5716\u6d3b\u52d5\u7684\u6559\u80b2\u50f9\u503c\u3002\u672c\u7814\u7a76\u6210\u529f\u5efa\u7acb\u4e86\u4e00\u500b\u5168\u9762\u7684AI\u8f14\u52a9\u5354\u4f5c\u6982\u5ff5\u5716\u8a55\u4f30\u7cfb\u7d71\uff0c\u4e0d\u50c5\u89e3\u6c7a\u4e86\u50b3\u7d71\u8a55\u4f30\u65b9\u6cd5\u7684\u9650\u5236\uff0c\u4e5f\u70ba\u500b\u4eba\u5316\u6559\u80b2\u63d0\u4f9b\u4e86\u65b0\u7684\u6280\u8853\u8def\u5f91\u3002\u7814\u7a76\u767c\u73fe\u5c0d\u4fc3\u9032\u667a\u6167\u6559\u80b2\u767c\u5c55\u548c\u63d0\u5347\u5354\u4f5c\u5b78\u7fd2\u6548\u679c\u5177\u6709\u91cd\u8981\u7684\u7406\u8ad6\u548c\u5be6\u52d9\u50f9\u503c\u3002<\/p>\n

\u95dc\u9375\u5b57\uff1a AI\u8f14\u52a9\u8a55\u91cf\u3001\u5354\u4f5c\u6982\u5ff5\u5716\u3001\u63d0\u793a\u8a5e\u512a\u5316\u3001\u500b\u4eba\u8ca2\u737b\u503c\u3001\u5dee\u7570\u5316\u56de\u994b<\/p>\n

\u00a0<\/p>\n\n

Assessment of collaborative concept mapping poses significant challenges for educators, particularly in identifying individual contribution levels and providing timely, personalized feedback. Traditional collaborative learning assessment methods often fail to accurately distinguish individual student contributions, leading to unfair assessment outcomes and excessive teacher workload. With the rapid development of generative artificial intelligence technology, particularly the application of large language models in educational assessment, new technical pathways have emerged to address these challenges.
\nThis study aims to: (1) construct and validate a framework capable of accurately analyzing collaborative concept maps and identifying individual student contributions through AI prompt systems; (2) establish objective computational mechanisms to quantify personal contribution values in collaborative concept mapping activities; (3) design and implement personalized feedback systems based on individual contribution analysis, providing differentiated learning recommendations.
\nWe adopted a design-based research approach involving 90 eighth-grade students from three classes in Taiwan, constructing a \"Role-Task-Step-Rule\" (RTSR) prompt optimization framework specifically for natural science concept map assessment. The study used NotebookLM as the primary AI assessment platform due to its excellent batch processing capabilities for PDF-format collaborative concept maps. Five versions of the prompt optimization framework were developed, evolving from basic assessment (V1.0) to personalized feedback (V5.0), systematically enhancing the system's assessment accuracy and feedback quality.
\nValidation results demonstrate high system reliability, with individual contribution analysis achieving 94% accuracy in identifying color-coded student contributions. The contribution value calculation model effectively quantified collaborative participation quantity and quality across four different contribution types. The personalized feedback mechanism provided individualized learning recommendations aligned with students' cognitive developmental levels, significantly enhancing the educational value of collaborative concept mapping activities.This study successfully established a comprehensive AI-assisted collaborative concept map assessment system that not only addresses limitations of traditional assessment methods but also provides new technical pathways for personalized education. The research findings hold significant theoretical and practical value for promoting intelligent education development and enhancing collaborative learning effectiveness.<\/p>\n

Keywords: AI-assisted assessment, collaborative concept mapping, prompt optimization, individual contribution value, differentiated feedback<\/p>\n

\u00a0<\/p>\n<\/div>\n

\u00a0<\/p>\n

\n