Applying the Deep Learning Method for Simulating Outcomes of Educational Interventions

Predicting outcomes of educational interventions before investing in large-scale implementation efforts in school settings is essential for educational policy-making. However, due to time and resource limitations, conducting longitudinal, large-scale experiments testing outcomes of interventions in authentic settings is difficult. Here, we introduce the deep learning method as a way to address this issue and illustrate the use of the deep learning method for the prediction of intervention outcomes through a MATLAB implementation. The presented deep learning method extracts predictable patterns from an empirical dataset to simulate large-scale intervention outcomes. Findings from our simulations suggest that the deep learning applied simulation model can predict intervention outcomes significantly more accurately compared to the traditional regression analysis methods.

[1]  Yueh-Min Huang,et al.  The use of data science for education: The case of social-emotional learning , 2016, Smart Learning Environments.

[2]  Chris S. Hulleman,et al.  Using Design Thinking to Improve Psychological Interventions: The Case of the Growth Mindset During the Transition to High School. , 2016, Journal of educational psychology.

[3]  Hyemin Han,et al.  Connecting levels of analysis in educational neuroscience: A review of multi-level structure of educational neuroscience with concrete examples , 2019, Trends in Neuroscience and Education.

[4]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[5]  Hae Yeon Lee,et al.  Declines in efficacy of anti-bullying programs among older adolescents: Theory and a three-level meta-analysis , 2015 .

[6]  Christopher D. Chambers,et al.  Redefine statistical significance , 2017, Nature Human Behaviour.

[7]  Edward Y. Chang,et al.  Representation Learning on Large and Small Data , 2017, Big Data Analytics for Large-Scale Multimedia Search.

[8]  K. Squire,et al.  Design-Based Research: Putting a Stake in the Ground , 2004 .

[9]  E. Crocetti,et al.  Identity and civic engagement in adolescence. , 2012, Journal of adolescence.

[10]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[11]  Valerie Purdie-Vaughns,et al.  Recursive Processes in Self-Affirmation: Intervening to Close the Minority Achievement Gap , 2009, Science.

[12]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[13]  Tenelle Porter.  Moral and political identity and civic involvement in adolescents , 2013 .

[14]  Ning Qian,et al.  On the momentum term in gradient descent learning algorithms , 1999, Neural Networks.

[15]  Leif D. Nelson,et al.  False-Positive Psychology , 2011, Psychological science.

[16]  C. Dweck,et al.  Adolescents' implicit theories predict desire for vengeance after peer conflicts: correlational and experimental evidence. , 2011, Developmental psychology.

[17]  Natalie M. Golaszewski,et al.  Why we need a small data paradigm , 2019, BMC Medicine.

[18]  Yves Rosseel,et al.  lavaan: An R Package for Structural Equation Modeling , 2012 .

[19]  Geoffrey L. Cohen,et al.  Mere belonging: the power of social connections. , 2012, Journal of personality and social psychology.

[20]  G. Walton,et al.  Social-Psychological Interventions in Education , 2011 .

[22]  T. Yarkoni,et al.  Choosing Prediction Over Explanation in Psychology: Lessons From Machine Learning , 2017, Perspectives on psychological science : a journal of the Association for Psychological Science.

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

[24]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[25]  Guocai He.  Lung CT Imaging Sign Classification through Deep Learning on Small Data , 2019, ArXiv.

[26]  H. Han,et al.  Civic Purpose in Late Adolescence: Factors That Prevent Decline in Civic Engagement After High School , 2017, Developmental psychology.

[27]  D. Bates,et al.  Fitting Linear Mixed-Effects Models Using lme4 , 2014, 1406.5823.

[28]  G. Walton,et al.  Enacting Cultural Interests , 2013, Psychological science.

[29]  Abbie Brown,et al.  Design experiments: Theoretical and methodological challenges in creating complex interventions in c , 1992 .

[30]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[31]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[32]  C. Dweck,et al.  An Implicit Theories of Personality Intervention Reduces Adolescent Aggression in Response to Victimization and Exclusion , 2012, Child development.

[33]  Hyemin Han,et al.  Attainable and Relevant Moral Exemplars Are More Effective than Extraordinary Exemplars in Promoting Voluntary Service Engagement , 2017, Front. Psychol..

[34]  Hyemin Han,et al.  Why do we need to employ Bayesian statistics and how can we employ it in studies of moral education?: With practical guidelines to use JASP for educators and researchers , 2018, Journal of Moral Education.

[35]  Martin J. Wainwright,et al.  Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions , 2011, ICML.

[36]  Yichuan Tang,et al.  Deep Learning using Linear Support Vector Machines , 2013, 1306.0239.

[37]  E. Wagenmakers.  A practical solution to the pervasive problems ofp values , 2007, Psychonomic bulletin & review.

[38]  Lawrence O. Hall,et al.  Neuroimaging Based Survival Time Prediction of GBM Patients Using CNNs from Small Data , 2019, 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC).

[39]  Jessica E. Black,et al.  Development, reliability, and validity of the Moral Identity Questionnaire , 2016 .

[40]  Galit Shmueli,et al.  To Explain or To Predict? , 2010 .

[41]  Kangwook Lee,et al.  Simulating outcomes of interventions using a multipurpose simulation program based on the evolutionary causal matrices and Markov chain , 2017, Knowledge and Information Systems.

[42]  Hyemin Han,et al.  Moral growth mindset is associated with change in voluntary service engagement , 2018, PloS one.

[43]  Kangwook Lee,et al.  Predicting long-term outcomes of educational interventions using the evolutionary causal matrices and Markov chain based on educational neuroscience , 2016, Trends in Neuroscience and Education.

[44]  Jacob Cohen,et al.  A power primer. , 1992, Psychological bulletin.

[45]  Larry P. Heck,et al.  Learning deep structured semantic models for web search using clickthrough data , 2013, CIKM.

[46]  Andrew Gelman,et al.  Measurement error and the replication crisis , 2017, Science.

[47]  Gholamreza Haffari,et al.  Medical Multimodal Classifiers Under Scarce Data Condition , 2019, 1902.08888.