Educational Question Mining At Scale: Prediction, Analysis and Personalization

Online education platforms enable teachers to share a large number of educational resources such as questions to form exercises and quizzes for students. With large volumes of available questions, it is important to have an automated way to quantify their properties and intelligently select them for students, enabling effective and personalized learning experiences. In this work, we propose a framework for mining insights from educational questions at scale. We utilize the state-of-the-art Bayesian deep learning method, in particular partial variational auto-encoders (p-VAE), to analyze real students' answers to a large collection of questions. Based on p-VAE, we propose two novel metrics that quantify question quality and difficulty, respectively, and a personalized strategy to adaptively select questions for students. We apply our proposed framework to a real-world dataset with tens of thousands of questions and tens of millions of answers from an online education platform. Our framework not only demonstrates promising results in terms of statistical metrics but also obtains highly consistent results with domain experts' evaluation.

[1]  Georg Rasch,et al.  Probabilistic Models for Some Intelligence and Attainment Tests , 1981, The SAGE Encyclopedia of Research Design.

[2]  Zichao Wang,et al.  Diagnostic Questions: The NeurIPS 2020 Education Challenge , 2020, ArXiv.

[3]  J. Sandars,et al.  Twelve tips for rapidly migrating to online learning during the COVID-19 pandemic , 2020, MedEdPublish.

[4]  Resmi Darni,et al.  Reviewing Online Learning Facing the Covid-19 Outbreak , 2020 .

[5]  Wei Bao,et al.  COVID‐19 and online teaching in higher education: A case study of Peking University , 2020, Human behavior and emerging technologies.

[6]  Pablo M. Olmos,et al.  Handling Incomplete Heterogeneous Data using VAEs , 2018, Pattern Recognit..

[7]  Sebastian Nowozin,et al.  Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model , 2019, ArXiv.

[8]  Hisashi Kashima,et al.  Knowledge Tracing Machines: Factorization Machines for Knowledge Tracing , 2018, AAAI.

[9]  Sebastian Nowozin,et al.  EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE , 2018, ICML.

[10]  Mike Wu,et al.  Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference , 2018, AAAI.

[11]  Hedvig Kjellström,et al.  Advances in Variational Inference , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Ming-Jen Lin,et al.  Catching Cheating Students , 2015, Economica.

[13]  Jes Frellsen,et al.  missIWAE: Deep Generative Modelling and Imputation of Incomplete Data , 2018, ArXiv.

[14]  Jie Yuan,et al.  Item Recommendation with Variational Autoencoders and Heterogeneous Priors , 2018, DLRS@RecSys.

[15]  M. de Rijke,et al.  A Collective Variational Autoencoder for Top-N Recommendation with Side Information , 2018, DLRS@RecSys.

[16]  Richard G. Baraniuk,et al.  QG-net: a data-driven question generation model for educational content , 2018, L@S.

[17]  Hisashi Kashima,et al.  Predictive Modeling of Learning Continuation in Preschool Education Using Temporal Patterns of Development Tests , 2018, AAAI.

[18]  Matthew D. Hoffman,et al.  Variational Autoencoders for Collaborative Filtering , 2018, WWW.

[19]  José Miguel Hernández-Lobato,et al.  Partial VAE for Hybrid Recommender System , 2018 .

[20]  Boris Ginsburg,et al.  Training Deep AutoEncoders for Collaborative Filtering , 2017, ArXiv.

[21]  James She,et al.  Collaborative Variational Autoencoder for Recommender Systems , 2017, KDD.

[22]  Alexander J. Smola,et al.  Deep Sets , 2017, 1703.06114.

[23]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Manuj Aggarwal,et al.  A survey of methods of collaborative filtering techniques , 2017, 2017 International Conference on Inventive Systems and Control (ICISC).

[25]  Geza Kovacs,et al.  Effects of In-Video Quizzes on MOOC Lecture Viewing , 2016, L@S.

[26]  Julia Eichmann Studies In Mathematical Psychology , 2016 .

[27]  Leonidas J. Guibas,et al.  Deep Knowledge Tracing , 2015, NIPS.

[28]  Scott Sanner,et al.  AutoRec: Autoencoders Meet Collaborative Filtering , 2015, WWW.

[29]  Richard G. Baraniuk,et al.  BayesRank: A Bayesian Approach to Ranked Peer Grading , 2015, L@S.

[30]  Kenneth R. Koedinger,et al.  Learning is Not a Spectator Sport: Doing is Better than Watching for Learning from a MOOC , 2015, L@S.

[31]  Dit-Yan Yeung,et al.  Relational Stacked Denoising Autoencoder for Tag Recommendation , 2015, AAAI.

[32]  Richard G. Baraniuk,et al.  Mathematical Language Processing: Automatic Grading and Feedback for Open Response Mathematical Questions , 2015, L@S.

[33]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[34]  Neil T. Heffernan,et al.  The ASSISTments Ecosystem: Building a Platform that Brings Scientists and Teachers Together for Minimally Invasive Research on Human Learning and Teaching , 2014, International Journal of Artificial Intelligence in Education.

[35]  Richard G. Baraniuk,et al.  Collaboration-Type Identification in Educational Datasets. , 2014, EDM 2014.

[36]  MengChu Zhou,et al.  An Efficient Non-Negative Matrix-Factorization-Based Approach to Collaborative Filtering for Recommender Systems , 2014, IEEE Transactions on Industrial Informatics.

[37]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[38]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[39]  Richard G. Baraniuk,et al.  Time-varying learning and content analytics via sparse factor analysis , 2013, KDD.

[40]  Duanli Yan,et al.  Computerized multistage testing : theory and applications , 2014 .

[41]  Konstantina Chrysafiadi,et al.  Student modeling approaches: A literature review for the last decade , 2013, Expert Syst. Appl..

[42]  Richard G. Baraniuk,et al.  Tag-Aware Ordinal Sparse Factor Analysis for Learning and Content Analytics , 2014, EDM.

[43]  R. Philip Chalmers,et al.  mirt: A Multidimensional Item Response Theory Package for the R Environment , 2012 .

[44]  Beverly Park Woolf,et al.  Student Modeling , 2010, Advances in Intelligent Tutoring Systems.

[45]  Z. Ying,et al.  Nonlinear sequential designs for logistic item response theory models with applications to computerized adaptive tests , 2009, 0906.1859.

[46]  Thore Graepel,et al.  Matchbox: large scale online bayesian recommendations , 2009, WWW '09.

[47]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[48]  Jeffrey D. Karpicke,et al.  The Critical Importance of Retrieval for Learning , 2008, Science.

[49]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[50]  Judith Blanchette Questions in the Online Learning Environment , 2007 .

[51]  Srujana Merugu,et al.  A scalable collaborative filtering framework based on co-clustering , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[52]  C. Twigg Improving Learning and Reducing Costs: New Models for Online Learning , 2003 .

[53]  P. Connor-Greene,et al.  Assessing and Promoting Student Learning: Blurring the Line between Teaching and Testing , 2000 .

[54]  H. Swaminathan,et al.  Bayesian Estimation in the Rasch Model , 1982 .