AI in Education needs interpretable machine learning: Lessons from Open Learner Modelling

Interpretability of the underlying AI representations is a key raison d'\^{e}tre for Open Learner Modelling (OLM) -- a branch of Intelligent Tutoring Systems (ITS) research. OLMs provide tools for 'opening' up the AI models of learners' cognition and emotions for the purpose of supporting human learning and teaching. Over thirty years of research in ITS (also known as AI in Education) produced important work, which informs about how AI can be used in Education to best effects and, through the OLM research, what are the necessary considerations to make it interpretable and explainable for the benefit of learning. We argue that this work can provide a valuable starting point for a framework of interpretable AI, and as such is of relevance to the application of both knowledge-based and machine learning systems in other high-stakes contexts, beyond education.

[1]  Gautam Biswas,et al.  LEARNING BY TEACHING: A NEW AGENT PARADIGM FOR EDUCATIONAL SOFTWARE , 2005, Appl. Artif. Intell..

[2]  Rafael A. Calvo,et al.  Automated Detection of Engagement Using Video-Based Estimation of Facial Expressions and Heart Rate , 2017, IEEE Transactions on Affective Computing.

[3]  Beverley Park Woolf,et al.  Building Intelligent Interactive Tutors , 2008 .

[4]  Judy Kay,et al.  SMILI☺: a Framework for Interfaces to Learning Data in Open Learner Models, Learning Analytics and Related Fields , 2016, International Journal of Artificial Intelligence in Education.

[5]  Tobias Baur,et al.  Who's Afraid of Job Interviews? Definitely a Question for User Modelling , 2014, UMAP.

[6]  Sara Bernardini,et al.  Building an Intelligent, Authorable Serious Game for Autistic Children and Their Carers , 2013, Advances in Computer Entertainment.

[7]  Antonija Mitrovic,et al.  Intelligent Tutors for All: The Constraint-Based Approach , 2007, IEEE Intelligent Systems.

[8]  Adrian Weller,et al.  Challenges for Transparency , 2017, ArXiv.

[9]  Cristina Conati,et al.  Empirically building and evaluating a probabilistic model of user affect , 2009, User Modeling and User-Adapted Interaction.

[10]  Michael Eagle,et al.  Experimental Evaluation of Automatic Hint Generation for a Logic Tutor , 2011, Int. J. Artif. Intell. Educ..

[11]  Cristina Conati,et al.  Applying a Framework for Student Modeling in Exploratory Learning Environments: Comparing Data Representation Granularity to Handle Environment Complexity , 2017, International Journal of Artificial Intelligence in Education.

[12]  Cristina Conati,et al.  Student Modeling: Supporting Personalized Instruction, from Problem Solving to Exploratory Open Ended Activities , 2013, AI Mag..

[13]  Manolis Mavrikis,et al.  Affective learning: improving engagement and enhancing learning with affect-aware feedback , 2017, User Modeling and User-Adapted Interaction.

[14]  Vassilis Kostakos,et al.  Avoiding pitfalls when using machine learning in HCI studies , 2017, Interactions.

[15]  Qing Liu,et al.  How Effective are Intelligent Tutoring Systems in Computer Science Education? , 2014, 2014 IEEE 14th International Conference on Advanced Learning Technologies.

[16]  Vincent Aleven,et al.  Example-Tracing Tutors: Intelligent Tutor Development for Non-programmers , 2016, International Journal of Artificial Intelligence in Education.

[17]  Kaska Porayska-Pomsta,et al.  Adolescents' Self-regulation During Job Interviews Through an AI Coaching Environment , 2018, AIED.

[18]  John Benedict du Boulay,et al.  Artificial Intelligence as an Effective Classroom Assistant , 2016, IEEE Intelligent Systems.

[19]  H. Pain,et al.  ' Did I say what I think I said , and do you agree with me ? ' : Inspecting and Questioning the Student Model , 1995 .

[20]  Noah L. Schroeder,et al.  How Effective are Pedagogical Agents for Learning? A Meta-Analytic Review , 2013 .

[21]  Vincent Aleven,et al.  Intelligent Tutoring Goes To School in the Big City , 1997 .

[22]  Susan Bull,et al.  Student Preferences for Editing, Persuading, and Negotiating the Open Learner Model , 2006, Intelligent Tutoring Systems.

[23]  Jody Clarke,et al.  Towards general models of effective science inquiry in virtual performance assessments , 2016, J. Comput. Assist. Learn..

[24]  Manolis Mavrikis.  Modelling Student Interactions in Intelligent Learning Environments: Constructing Bayesian Networks from Data , 2010, Int. J. Artif. Intell. Tools.

[25]  Vincent Aleven,et al.  Enhancing learning outcomes through self-regulated learning support with an Open Learner Model , 2017, User Modeling and User-Adapted Interaction.