| 3 | 0 | 5 |
| 下载次数 | 被引频次 | 阅读次数 |
在知识建构教学中,观点的持续改进过程很大程度上揭示了学生知识的进化轨迹,因此观点质量的评估成为判断学习效果的重要依据。研究采用文本挖掘技术,对知识建构社区中学生生成的观点进行质量评价。首先,基于知识建构教学原则和深度学习模型,构建了包含相关度、专业度、内聚度、纵深度、探究度和创新性六个维度的观点质量评价指标体系。其次,对教材文本进行分词处理、关键词提取,并建立学科词向量,以此为基础构建学科语义词库;同时,对知识论坛上学习者发布的文本数据进行分词和关键词提取,进而提取表征观点质量的关键特征。然后,通过模型训练迭代优化,最终确定梯度提升树模型为拟合效果最佳的评估模型。最后,应用该模型实现了知识论坛上观点的大规模自动量化评价。基于量化结果,研究通过时间序列分析发现,观点质量在波动中呈现逐步提升的趋势,学科词汇的重组与优化是推动观点改进与升华的关键动力。研究成果不仅为计算机自动评价观点质量提供方法依据,也为优化学习路径和推送个性化学习资源提供参考。
Abstract：In the Knowledge Building teaching, the process of continuous idea improvement reveals the evolution trajectory of students' knowledge to a large extent. So the evaluation of idea quality becomes an important basis for judging the learning effect. This paper applies text mining technology to evaluate the quality of the ideas generated by students in the Knowledge Building community. Firstly, the evaluation index system of idea quality is constructed, which includes six dimensions of relevance, specialization, cohesion, depth, exploration and innovation on the basis of the principles of Knowledge Building and the model of deep level processing. Secondly, the textbook text is processed by word segmentation, keyword extraction, and the subject word vector is established to build the subject semantic vocabulary on this basis; At the same time, the text data published by students on the Knowledge Forum platform is segmented and keywords are extracted, and then key features representing idea quality are extracted. Thirdly, through iterative optimization of model training, the Gradient Boosting Regressor is finally determined as the best evaluation model for fitting effect. Finally, the model is applied to realize the large-scale automatic quantitative evaluation of ideas on the Knowledge Forum. Based on the quantitative results, through time series analysis, the research finds that the quality of ideas has gradually improved in the fluctuation, and the reorganization and optimization of subject vocabulary is the key driving force to idea improvement and sublimation. The research results not only provide a method for computer to automatically evaluate idea quality, but also provide a reference for optimizing the learning path and pushing personalized learning resources.
[1]Scardamalia M,Bereiter C.Knowledge Building:Theory,pedagogy,and technology[A].Sawyer R K.Cambridge Handbook of the Learning Sciences[C].New York:Cambridge University Press,2006.97-118.
[2]Scardamalia M.Collective Cognitive Responsibility for the Advancement of Knowledge[A].Smith B.Liberal Education in a Knowledge Society[C].Chicago,IL:Open Court,2002.67-98.
[3]Bereiter C.Education and mind in the knowledge age[M].New Jersey:Lawrence Erlbaum Associates,2002.84-89.
[4]刘清堂,尹兴翰等.基于学习者评论数据挖掘的MOOC课程质量影响因素研究[J].远程教育杂志,2023,41(1):80-90.
[5]贾积有,乐惠骁等.基于大数据挖掘的智能评测和辅导系统设计[J].中国电化教育,2023,(3):112-119.
[6]胡金艳,杨霞等.知识建构社区中多主体模拟支持的观点涌现模型构建:复杂性科学的视角[J].电化教育研究,2024,45(1):100-107.
[7]Nadia S,Salwa H.Effective creative crowdsourcing:A multi-dimensional evaluation framework[J].Creativity and Innovation Management,2022,31(2):223-235.
[8]Gunawardena C N,Lowe C A,et al.Analysis of A Global Online Debate and The Development of an Interaction Analysis Model for Examining Social Construction of Knowledge in Computer Conferencing[J].Journal of Educational Computing Research,1997,17(4):397-431.
[9][36] Zhang J,Scardamalia M,et al.Socio-cognitive dynamics of knowledge building in the work of 9-and 10-year-olds[J].Educational Technology Research and Development,2007,55(2):117-145.
[10]Hakkarainen.Progressive inquiry in a computer-supported biology class[J].Journal of Research in Science Teaching,2003,(40):1072-1088.
[11]Galili I,Hazan A.Learners’ knowledge in optics:interpretation,structure and analysis[J].International Journal of Science Education,2000,(1):57-88.
[12]Dean D L,Hender J M,et al.Identifying quality, novel, and creative ideas:Constructs and scales for idea evaluation[J].Journal of the Association for Information Systems,2006,7(1):646-698.
[13][29]殷常鸿,张义兵等.“皮亚杰—比格斯”深度学习评价模型构建[J].电化教育研究,2019,40(7):13-20.
[14]王丽英,张义兵.融合知识建构和机器学习的观点质量评价[J].现代教育技术,2020,30(11):62-69.
[15]Christensen K,Norskov S,et al.In search of new product ideas:Identifying ideas in online communities by machine learning and text mining[J].Creativity and Innovation Management,2017,26(1):17-30.
[16]Tao D,Zhang J W.Forming Shared Inquiry Structures to Support Knowledge Building in a Grade 5 Community[J].Instructional Science,2018,46(4):563-592.
[17]Kota V R,Munisamy S D.High accuracy offering attention mechanisms based deep learning approach using CNN/bi-LSTM for sentiment analysis[J].International Journal of Intelligent Computing and Cybernetics,2022,15(1):61-74.
[18]Gunawardena C N,Chen Y,et al.Deep Learning Models for Analyzing Social Construction of Knowledge Online[J].Online Learning,2023,27(4):69-92.
[19]Li K,Qian C,et al.Evaluating the quality of Student-generated content in learnersourcing:A large language model based Approach[J].Education and Information Technologies,2024,30(2):2331-2360.
[20]Jong Y J,Kim Y J,et al.Improving Performance of Automated Essay Scoring by Using Back-Translation Essays and Adjusted Scores[J]. Mathematical Problems in Engineering,2022:1-10.
[21]Scardamalia M,Bereier C.Computer support for knowledge-building communities[J].The Journal of the Learning Sciences,1994,3(3):265-283.
[22]Hong H Y,Chen F C,et al.Teacher-education students’views about knowledge building theory and practice[J].Instructional Science,2011,39(4):467-482.
[23]TSoukas H.A Dialogical Approach to the Creation of New Knowledge in Organizations[J].Organization Science,2009,20(6):941-957.
[24][37]蒋纪平,胡金艳等.促进社区知识形成的知识建构对话发展研究——基于社会网络和时序分析的方法[J].远程教育杂志,2021,39(4):94-103.
[25]Marton F,SäljöR.On qualitative differences in learning:i-outcome and process[J].British journal of educational psychology,1976,46(1):4-11.
[26][瑞士]皮亚杰.王宪钿译.发生认识论原理[M].北京:商务印书馆,1981.
[27]Biggs J,Kevin F,et al.Evaluating the quality of learning:The SOLO taxonomy(structure of the observed learning outcome)[M].New York:Academic Press,1982.
[28]张建伟.概念转变模型及其发展[J].心理学动态,1998,6(3):33-37.
[30]Chai S,Zhu G.The relationship between group adoption of Knowledge Building Principles and performance in creating Artifacts[J].Educational Technology Research and Development,2021,69(2):787-808.
[31]Ben Yaakov Y,Denisova M,et al.Normative or Confirmative:Effects of Information Quality and Redundancy in Decision Support Systems[J].Hum Factors.2025,67(6):546-559.
[32]蒋纪平,田晟瑶等.知识建构社区中观点种群能量流动机制研究[J].电化教育研究,2025,46(8):73-80.
[33]Yang Y,Chan C K K,et al.Reflective assessment using analytics and artifacts for scaffolding knowledge building competencies among undergraduate Students[J].International Journal of Computer-Supported Collaborative Learning,2024,19(2):231-272.
[34]张义兵.知识建构:新教育公平视野下教与学的变革[M].南京:南京师范大学出版社,2018.90-91.
[35]Sawyer R K.The Cambridge handbook of the learning sciences[M].Cambridge:Cambridge University Press,2014.
[38][英]波普尔.舒炜光,卓如飞等译.客观知识——一个进化论的研究[M].上海:上海译文出版社,1987.
[39]蒋纪平,满其峰等.在线协作知识建构的知识进化:内涵、本质与模型[J].开放教育研究,2022,28(6):52-59.
[40]陈向东,周春红等.知识冲突:大语言模型教育应用的挑战与应对[J].中国电化教育,2025,(3):1-10.
基本信息:
中图分类号:G434
引用信息:
[1]蒋纪平,田晟瑶,张义兵,等.知识建构社区中观点质量自动评价研究——基于数据驱动的文本挖掘[J].中国电化教育,2026,No.472(05):76-84+94.
基金信息:
全国教育科学规划一般项目“促进人机协同创造力提升的循证教学设计模式构建”(项目编号:BCA250069)研究成果
2026-05-10
2026-05-10