在线开放课程中教师教学行为研究——结合自然语言处理观点挖掘的方法
|
摘要
在线学习中教师教学行为影响到在线学习者课程评价和学习体验。本文提出研究假设:教师主教行为与学习者课程评价正相关;教师助教行为与学习者课程评价正相关;教师管理行为与学习者课程评价正相关。主要运用自然语言处理(NLP)和内容分析的方法,从学习者评论中挖掘在线学习者观点。研究设计了学习者观点抽象模型和教师教学行为编码表,运用语言技术平台(LTP)依存句法分析识别观点句,并基于规则压缩抽取观点句中属性和观点词语,编码分析教师教学行为相关观点。分析教师教学行为与学习者课程评价的相关性发现:教师主教行为(讲授、指示、演示)与学习者课程评价正相关;教师助教行为(评价反馈、技术指导)和教师管理行为(组织讨论、课程管理、辅助学习资源管理)与学习者课程评价的相关关系未达到统计检验的显著水平。基于研究结果提出在线学习中教师教学行为发展建议。
Teachers' online teaching behaviors affect learners' course evaluation and learning experience. This study set out with the following hypotheses:(a) teachers' dominant behaviors are positively correlated with learners' course evaluation;(b) teachers' support behaviors are positively correlated with learners' course evaluation;(c) teachers' managerial behaviors are positively correlated with learners' course evaluation. Using the methods of natural language processing and content analysis to mine learners' opinions from their online comments, the study designed an abstract model of learners' opinions and a code table of teaching behaviors. It then used LTP interdependence syntactic analysis to identify opinion sentences,extract attribution and opinion words based on rules and code relevant ideas of teaching behaviors.Analysis of the correlations between teachers' teaching behaviors and learners, course evaluation shows that teachers' dominant behaviors(lecturing, instruction and demonstration) are positively correlated with learners' course evaluation, teachers' support behaviors(evaluation, feedback and technical guidance) are weakly correlated with learners' course evaluation, and teachers' managerial behaviors(group discussion,course management and supplementary learning resource management) are positively correlated with learners' course evaluation. Suggestions are also discussed on teachers' online teaching behaviors.
Teachers' online teaching behaviors affect learners' course evaluation and learning experience. This study set out with the following hypotheses:(a) teachers' dominant behaviors are positively correlated with learners' course evaluation;(b) teachers' support behaviors are positively correlated with learners' course evaluation;(c) teachers' managerial behaviors are positively correlated with learners' course evaluation. Using the methods of natural language processing and content analysis to mine learners' opinions from their online comments, the study designed an abstract model of learners' opinions and a code table of teaching behaviors. It then used LTP interdependence syntactic analysis to identify opinion sentences,extract attribution and opinion words based on rules and code relevant ideas of teaching behaviors.Analysis of the correlations between teachers' teaching behaviors and learners, course evaluation shows that teachers' dominant behaviors(lecturing, instruction and demonstration) are positively correlated with learners' course evaluation, teachers' support behaviors(evaluation, feedback and technical guidance) are weakly correlated with learners' course evaluation, and teachers' managerial behaviors(group discussion,course management and supplementary learning resource management) are positively correlated with learners' course evaluation. Suggestions are also discussed on teachers' online teaching behaviors.
引文
丹尼尔·里夫,斯蒂文·赖斯,弗雷德里克·G.菲克.2010.内容分析法:媒介信息量化技巧(第二版)[M].嵇美云,译.北京:清华大学出版社:154-157.
傅德荣,章慧敏.2001.教育信息处理[M].北京:北京师范大学出版社:94-96.
高巍.2012.教师行为与学生行为的关系解析[J].教育研究,33(3):100-106.
顾小清,王炜.2004.支持教师专业发展的课堂分析技术新探索[J].中国电化教育(7):18-21.
韩后,王冬青,曹畅.2015.1∶1数字化环境下课堂教学互动行为的分析研究[J].电化教育研究,36(5):89-95.
李松林.2005.课堂教学行为分析引论[J].教育理论与实践(7):48-51.
刘繁华.2004.网络教学中教师的教学行为研究[J].电化教育研究(4):38-40,44.
施良方,崔允漷.1999.教学理论:课堂教学的原理、策略与研究[M].上海:华东师范大学出版社.
张屹,祝园,白清玉,等.2016.智慧教室环境下小学数学课堂教学互动行为特征研究[J].中国电化教育(6):43-48.
朱厚玉.2013.教师教学行为设计的原理与技术[M].昆明:云南大学出版社:9.
CNNIC中国互联网数据平台.2017.第40次《中国互联网络发展状况统计报告》[DB/OL].http://www.cnnic.cn/hlwfzyj/hlwxzbg/hlwtjbg/201708/P020170803598956435591.pdf
Cambria,E.,Schuller,B.,Xia,Y.,et al.(2013).New avenues in opinion mining and sentiment analysis.IEEE Intelligent Systems,28(2),15-21.
Chen,X.,Vorvoreanu,M.,&Madhavan,K.(2014).Mining social media data for understanding students.learning experiences.IEEE Transactions on Learning Technologies,7(3),246-259.
Dave,K.,Lawrence,S.,&Pennock,D.M.(2003).Mining the peanut gallery:Opinion extraction and semantic classification of product reviews.Proceedings of the 12th International Conference on World Wide Web.ACM,519-528.
Flanders,N.A.(1974).Interaction analysis:A technique for quantifying teacher influence.Behavior Change,1-16.
Kim,S.M.,&Hovy,E.(2004).Determining the sentiment of opinions International Conference on Computational Linguistics.Association for Computational Linguistics,1367.
Liu,B.,&Zhang,L.(2012).A survey of opinion mining and sentiment analysis.Chicago:Springer US.
Liu,B.(2012).Sentiment analysis and opinion mining.Chicago:Morgan&Claypool Publishers.
Liu,Q.,Zhang,S.,Wang,Q.,et al.(2017).Mining online discussion data for understanding teachers.reflective thinking.IEEE Transactions on Learning Technologies,pp(99),1-9.
Pang,B.,&Lee,L.(2008).Opinion mining and sentiment analysis California:Information Retrieval.
Reich,J.,Tingley,D.H.,Leder-Luis,J.,et al.(2015).Computer-assisted reading and discovery for student generated text in massive open online courses.Journal of Learning Analytics,2(1),156-184.
Romero,C.,López,M.I.,Luna,J.M.,et al.(2013).Predicting students final performance from participation in on-line discussion forums Computers&Education,68,458-472.
Stigler,J.W.,Gonzales,P.,Kawanaka,T.,Knoll,S.,&Serrano,A(1999).The TIMSS videotape classroom study:Methods and findings from an exploratory research project on eighth-grade mathematics instruction in Germany,Japan,and the United States.Washington,DCEducation Statistics Quarterly.
Takehisa Kumakawa.(2017).A text mining examination of university students.learning program posters.Open Access Library Journal,DOI:10.4236/oalib.1103639,pp.1-6
Che,W.,Zhao,Y.,Guo,H.,Su,Z.,Liu,T.(2015).Sentence compression for aspect-based sentiment analysis.IEEE/ACM Transactions on Audio,Speech,and Language Processing.23(12),2111-2124.
Yang,D.,Wen,M.,Kumar,A.,et al.(2014).Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs.International Review of Research in Open&Distance Learning,15(5),214-234.
傅德荣,章慧敏.2001.教育信息处理[M].北京:北京师范大学出版社:94-96.
高巍.2012.教师行为与学生行为的关系解析[J].教育研究,33(3):100-106.
顾小清,王炜.2004.支持教师专业发展的课堂分析技术新探索[J].中国电化教育(7):18-21.
韩后,王冬青,曹畅.2015.1∶1数字化环境下课堂教学互动行为的分析研究[J].电化教育研究,36(5):89-95.
李松林.2005.课堂教学行为分析引论[J].教育理论与实践(7):48-51.
刘繁华.2004.网络教学中教师的教学行为研究[J].电化教育研究(4):38-40,44.
施良方,崔允漷.1999.教学理论:课堂教学的原理、策略与研究[M].上海:华东师范大学出版社.
张屹,祝园,白清玉,等.2016.智慧教室环境下小学数学课堂教学互动行为特征研究[J].中国电化教育(6):43-48.
朱厚玉.2013.教师教学行为设计的原理与技术[M].昆明:云南大学出版社:9.
CNNIC中国互联网数据平台.2017.第40次《中国互联网络发展状况统计报告》[DB/OL].http://www.cnnic.cn/hlwfzyj/hlwxzbg/hlwtjbg/201708/P020170803598956435591.pdf
Cambria,E.,Schuller,B.,Xia,Y.,et al.(2013).New avenues in opinion mining and sentiment analysis.IEEE Intelligent Systems,28(2),15-21.
Chen,X.,Vorvoreanu,M.,&Madhavan,K.(2014).Mining social media data for understanding students.learning experiences.IEEE Transactions on Learning Technologies,7(3),246-259.
Dave,K.,Lawrence,S.,&Pennock,D.M.(2003).Mining the peanut gallery:Opinion extraction and semantic classification of product reviews.Proceedings of the 12th International Conference on World Wide Web.ACM,519-528.
Flanders,N.A.(1974).Interaction analysis:A technique for quantifying teacher influence.Behavior Change,1-16.
Kim,S.M.,&Hovy,E.(2004).Determining the sentiment of opinions International Conference on Computational Linguistics.Association for Computational Linguistics,1367.
Liu,B.,&Zhang,L.(2012).A survey of opinion mining and sentiment analysis.Chicago:Springer US.
Liu,B.(2012).Sentiment analysis and opinion mining.Chicago:Morgan&Claypool Publishers.
Liu,Q.,Zhang,S.,Wang,Q.,et al.(2017).Mining online discussion data for understanding teachers.reflective thinking.IEEE Transactions on Learning Technologies,pp(99),1-9.
Pang,B.,&Lee,L.(2008).Opinion mining and sentiment analysis California:Information Retrieval.
Reich,J.,Tingley,D.H.,Leder-Luis,J.,et al.(2015).Computer-assisted reading and discovery for student generated text in massive open online courses.Journal of Learning Analytics,2(1),156-184.
Romero,C.,López,M.I.,Luna,J.M.,et al.(2013).Predicting students final performance from participation in on-line discussion forums Computers&Education,68,458-472.
Stigler,J.W.,Gonzales,P.,Kawanaka,T.,Knoll,S.,&Serrano,A(1999).The TIMSS videotape classroom study:Methods and findings from an exploratory research project on eighth-grade mathematics instruction in Germany,Japan,and the United States.Washington,DCEducation Statistics Quarterly.
Takehisa Kumakawa.(2017).A text mining examination of university students.learning program posters.Open Access Library Journal,DOI:10.4236/oalib.1103639,pp.1-6
Che,W.,Zhao,Y.,Guo,H.,Su,Z.,Liu,T.(2015).Sentence compression for aspect-based sentiment analysis.IEEE/ACM Transactions on Audio,Speech,and Language Processing.23(12),2111-2124.
Yang,D.,Wen,M.,Kumar,A.,et al.(2014).Towards an integration of text and graph clustering methods as a lens for studying social interaction in MOOCs.International Review of Research in Open&Distance Learning,15(5),214-234.