基于在线学习行为分析的个性化学习推荐
|
摘要
随着在线课程和线上学习的普及,大量的在线学习行为数据被积累。如何利用数据挖掘技术分析积累的大数据,从而为教学决策和学习优化提供服务,已经成为新的研究重点。文中分析了在线学习的行为特征,挖掘学习者的性格特征与学习效率的关系,实现个性化学习方法推荐。首先,提取在线学习行为特征,并提出了一种基于BP神经网络的学习成绩预测方法,通过分析在线学习行为特征,预测其相应的线下学习成绩;其次,为了进一步分析学习者的在线学习行为与成绩的关系,提出了基于实际熵的在线学习行为规律性分析,通过分析学习者的在线学习行为,定义并计算相应的实际熵值来评估个体的学习行为规律性,从而分析规律性与最终成绩的关系;再次,基于Felder-Silverman性格分类法获得学习者的性格特征,对学习者实现基于K-means的聚类分析获得相似学习者的类别,将学习成绩较优的学习者的在线学习习惯推荐给同一类别的其他学习者,从而提高学习者的在线学习效率;最终,以某在线课程平台的实际数据为实验对象,分别实现在线学习行为特征提取、线下成绩预测、学习规律性分析和个性化学习推荐,从而验证了所提方法的有效性和应用价值。
With the wide use of online courses and the population of online learning,massive data of online learning behaviors have been collected.How to take advantages of those accumulated data through novel data mining technology for improving teaching decision and learning efficiency is becoming the research focus.In this paper,online learning behavior features are extracted,relationship between online learner's personality and learning efficiency is modeled and analyzed,and personal learning recommendation is designed as well.First,online learner behavior features were extracted,and BP neural network based academic performance prediction algorithm was put forward,in which offline score was predicted based on accordingly online learning behavior features.Second,in order to further analyze the relationship of online learning behavior and offline practical score,a novel actual entropy based online learning behavior orderness evaluation model was proposed.Each learner's offline academic performance can be predicted on basis of online learning orderness.Third,learners' personalities were estimated through Felder-Silverman method.K-means algorithm was carried out on those personality vectors to achieve clusters of learners with the similar personality.Among those learners clustered into the same class,the top scored learner's learning behavior will be recommended to the rest learners.Finally,tackingapractical online courses platform's data as our experimental subject,plenty of experiments were carried out including online learning behavior feature extraction,offline academic performance evaluation and orderness analysis,perso-nal learning behavior recommendation,and the efficiency and application value of proposed method was proved.
With the wide use of online courses and the population of online learning,massive data of online learning behaviors have been collected.How to take advantages of those accumulated data through novel data mining technology for improving teaching decision and learning efficiency is becoming the research focus.In this paper,online learning behavior features are extracted,relationship between online learner's personality and learning efficiency is modeled and analyzed,and personal learning recommendation is designed as well.First,online learner behavior features were extracted,and BP neural network based academic performance prediction algorithm was put forward,in which offline score was predicted based on accordingly online learning behavior features.Second,in order to further analyze the relationship of online learning behavior and offline practical score,a novel actual entropy based online learning behavior orderness evaluation model was proposed.Each learner's offline academic performance can be predicted on basis of online learning orderness.Third,learners' personalities were estimated through Felder-Silverman method.K-means algorithm was carried out on those personality vectors to achieve clusters of learners with the similar personality.Among those learners clustered into the same class,the top scored learner's learning behavior will be recommended to the rest learners.Finally,tackingapractical online courses platform's data as our experimental subject,plenty of experiments were carried out including online learning behavior feature extraction,offline academic performance evaluation and orderness analysis,perso-nal learning behavior recommendation,and the efficiency and application value of proposed method was proved.
引文
[1] COATES H.Student engagement in campus-based and online education:University connections[OL].http://www.bokus.com/cgi-bin/product_search.cgi?authors=Hamish%20Coates.
[2] STRANG K.How student behavior and reflective learning impact grades in online business courses[J].Journal of Applied Research in Higher Education,2016,8(3):390-410.
[3] PRIOR D D,MAZANOV J,MEACHEAM D,et al.Attitude,digital literacy and self efficacy:Flow-on effects for online learning behavior[J].Internet&Higher Education,2016,29:91-97.
[4] BUTCHER K R,SUMNER T.How Does Prior Knowledge Impact Students’Online Learning Behaviors?[J].International Journal of Cyber Behavior Psychology&Learning,2011,1(4):1-18.
[5] YANG C,HSIEH T.Regional differences of online learning behavior patterns[J].Electronic Library,2013,31(2):167-187.
[6] PARK Y,YU J H,JO I H.Clustering blended learning courses by online behavior data:A case study in a Korean higher education institute[J].Internet&Higher Education,2016,29:1-11.
[7] SHIMADA A,OKUBO F,YIN C,et al.Informal Learning Behavior Analysis Using Action Logs and Slide Features in ETextbooks[C]∥International Conference on Advanced Learning Technologies.IEEE,2015:116-117.
[8] HWANG W Y,SHADIEV R,WANG C Y,et al.A pilot study of cooperative programming learning behavior and its relationship with students’learning performance[J].Computers&Education,2012,58(4):1267-1281.
[9] TOUYA K,FAKIR M.Mining Students’Learning Behavior in Moodle System[J].Journal of Information Technology Research(JITR),2014,7(4):12-26.
[10]YE C,KINNEBREW J S,SEGEDY J R,et al.Learning Behavior Characterization with Multi-Feature,Hierarchical Activity Sequences[C]∥Proceedings of the 8th International Conference on Educational Data Mining.2015:380-383.
[11]LINAN L C,ANGEL ALEJANDRO JUAN PEREZ.Educational data mining and learning analytics:differences,similarities and time evolution[J].Ruse Revista De Universidad Y Sociedad Del Conocimiento,2015,12(3):98-112.
[12]DURKSEN T L,CHU M W,AHMAD Z F,et al.Motivation in a MOOC:aprobabilistic analysis of online learners’basic psychological needs[J].Social Psychology of Education,2016,19(2):241-260.
[13]FITOUSSI J P,VELUPILLAI K.Technology for Mining the Big Data of MOOCs[J].Research&Practice in Assessment,2014,9:29-37.
[14]MAC CALLUM K,JEFFREY L.Factors Impacting Teachers’Adoption of Mobile Learning[J].Journal of Information Technology Education Research,2014,13(13):141-162.
[15]樊超,宗利永.MOOC在线学习行为的人类动力学分析[J].开放教育研究,2016,22(2):53-58.
[16]宗阳,孙洪涛,张享国,等.MOOCs学习行为与学习效果的逻辑回归分析[J].中国远程教育,2016,36(5):14-22.
[17]肖建忠,陈小娟,贾秀险.高等教育评估多元化研究[J].高教探索,2013(1):13-15.
[18]O’CONNOR M C,PAUNONEN S V.Big Five personality predictors of post-secondary academic performance[J].Personality&Individual Differences,2007,43(5):971-990.
[19]POROPAT A E.A meta-analysis of the five-factor model of personality and academic performance[J].Psychological Bulletin,2009,135(2):322-328.
[20]VEDEL A.The Big Five and tertiary academic performance:A systematic review and metaanal-ysis[J].Personality&Individual Differences,2014,71(2):66-76.
[21]KONTOYIANNIS I,ALGOET P H,SUHOV Y M,et al.Nonparametric entropy estimation for stationary processes and random fields,with applications to English text[J].IEEE Transactions on Information Theory,1998,44(3):1319-1327.
[22]CAO Y,GAO J,LIAN D,et al.Orderness Predicts Academic Performance:Behavioral Analysis on Campus Lifestyle[J].eprint arXiv:1704.04013.
[23]TOKTAROVA V I,PANTUROVA A A.Learning and Teaching Style Models in Pedagogical Design of Electronic Educational Environment of the University[OL].http://www.mcser.org/journal/index.php/mjss/article/view/6874.
[24]倍智人才研究院.大五人格心理学:The big five[M].北京:企业管理出版社,2015.
[25]PERRY T W.16-Cattle Finishing Systems[OL].http://doi.org/10.1016/B978-012552052-2150019-6.
[26]王晨煜,管明辉,殷传涛,等.基于FelderS-ilverman学习风格模型的网络学习风格研究[J].重庆理工大学学报,2017,31(2):102-109.
[27]FREUND Y,MASON L.The Alternating Decision Tree Learning Algorithm[C]∥Machine Learning:Sixteenth International Conference.1999:124-133.
[28]MOZINA M,DEMSAR J,KATTAN M,et al.Nomograms for Visualization of Bayesian Classifier[C]∥European Conference on Principles of Data Mining&Knowledge Discovery.2004:337-348.
[2] STRANG K.How student behavior and reflective learning impact grades in online business courses[J].Journal of Applied Research in Higher Education,2016,8(3):390-410.
[3] PRIOR D D,MAZANOV J,MEACHEAM D,et al.Attitude,digital literacy and self efficacy:Flow-on effects for online learning behavior[J].Internet&Higher Education,2016,29:91-97.
[4] BUTCHER K R,SUMNER T.How Does Prior Knowledge Impact Students’Online Learning Behaviors?[J].International Journal of Cyber Behavior Psychology&Learning,2011,1(4):1-18.
[5] YANG C,HSIEH T.Regional differences of online learning behavior patterns[J].Electronic Library,2013,31(2):167-187.
[6] PARK Y,YU J H,JO I H.Clustering blended learning courses by online behavior data:A case study in a Korean higher education institute[J].Internet&Higher Education,2016,29:1-11.
[7] SHIMADA A,OKUBO F,YIN C,et al.Informal Learning Behavior Analysis Using Action Logs and Slide Features in ETextbooks[C]∥International Conference on Advanced Learning Technologies.IEEE,2015:116-117.
[8] HWANG W Y,SHADIEV R,WANG C Y,et al.A pilot study of cooperative programming learning behavior and its relationship with students’learning performance[J].Computers&Education,2012,58(4):1267-1281.
[9] TOUYA K,FAKIR M.Mining Students’Learning Behavior in Moodle System[J].Journal of Information Technology Research(JITR),2014,7(4):12-26.
[10]YE C,KINNEBREW J S,SEGEDY J R,et al.Learning Behavior Characterization with Multi-Feature,Hierarchical Activity Sequences[C]∥Proceedings of the 8th International Conference on Educational Data Mining.2015:380-383.
[11]LINAN L C,ANGEL ALEJANDRO JUAN PEREZ.Educational data mining and learning analytics:differences,similarities and time evolution[J].Ruse Revista De Universidad Y Sociedad Del Conocimiento,2015,12(3):98-112.
[12]DURKSEN T L,CHU M W,AHMAD Z F,et al.Motivation in a MOOC:aprobabilistic analysis of online learners’basic psychological needs[J].Social Psychology of Education,2016,19(2):241-260.
[13]FITOUSSI J P,VELUPILLAI K.Technology for Mining the Big Data of MOOCs[J].Research&Practice in Assessment,2014,9:29-37.
[14]MAC CALLUM K,JEFFREY L.Factors Impacting Teachers’Adoption of Mobile Learning[J].Journal of Information Technology Education Research,2014,13(13):141-162.
[15]樊超,宗利永.MOOC在线学习行为的人类动力学分析[J].开放教育研究,2016,22(2):53-58.
[16]宗阳,孙洪涛,张享国,等.MOOCs学习行为与学习效果的逻辑回归分析[J].中国远程教育,2016,36(5):14-22.
[17]肖建忠,陈小娟,贾秀险.高等教育评估多元化研究[J].高教探索,2013(1):13-15.
[18]O’CONNOR M C,PAUNONEN S V.Big Five personality predictors of post-secondary academic performance[J].Personality&Individual Differences,2007,43(5):971-990.
[19]POROPAT A E.A meta-analysis of the five-factor model of personality and academic performance[J].Psychological Bulletin,2009,135(2):322-328.
[20]VEDEL A.The Big Five and tertiary academic performance:A systematic review and metaanal-ysis[J].Personality&Individual Differences,2014,71(2):66-76.
[21]KONTOYIANNIS I,ALGOET P H,SUHOV Y M,et al.Nonparametric entropy estimation for stationary processes and random fields,with applications to English text[J].IEEE Transactions on Information Theory,1998,44(3):1319-1327.
[22]CAO Y,GAO J,LIAN D,et al.Orderness Predicts Academic Performance:Behavioral Analysis on Campus Lifestyle[J].eprint arXiv:1704.04013.
[23]TOKTAROVA V I,PANTUROVA A A.Learning and Teaching Style Models in Pedagogical Design of Electronic Educational Environment of the University[OL].http://www.mcser.org/journal/index.php/mjss/article/view/6874.
[24]倍智人才研究院.大五人格心理学:The big five[M].北京:企业管理出版社,2015.
[25]PERRY T W.16-Cattle Finishing Systems[OL].http://doi.org/10.1016/B978-012552052-2150019-6.
[26]王晨煜,管明辉,殷传涛,等.基于FelderS-ilverman学习风格模型的网络学习风格研究[J].重庆理工大学学报,2017,31(2):102-109.
[27]FREUND Y,MASON L.The Alternating Decision Tree Learning Algorithm[C]∥Machine Learning:Sixteenth International Conference.1999:124-133.
[28]MOZINA M,DEMSAR J,KATTAN M,et al.Nomograms for Visualization of Bayesian Classifier[C]∥European Conference on Principles of Data Mining&Knowledge Discovery.2004:337-348.