Towards Automatic Hint Generation for a Data- Driven Novice Programming Tutor I. WEI JIN Shaw University, USA AND I.I. LORRIE LEHMANN University of North Carolina at Charlotte, USA AND I.I.I. MATTHEW JOHNSON University of North Carolina at Charlotte, USA AND I.V. MICHAEL EAGLE University of North Carolina at Charlotte, USA AND V. BEHROOZ MOSTAFAVI University of North Carolina at Charlotte, USA AND V.I. TIFFANY BARNES University of North Carolina at Charlotte, USA AND V.I.I. JOHN STAMPER Carnegie Mellon University, USA ________________________________________________________________________ Hint annotation is one of the most time consuming components of developing intelligent tutoring systems. One approach is to use educational data mining and machine learning techniques to automate the creation of hints from student problem-solving data. This paper describes a new technique to represent, classify, and use programs written by novices as a base for automatic hint generation for programming tutors. Our preliminary evaluation shows that this approach can effectively cluster programs and therefore has potential to be a source for automatically generated hints for novice programmers. Key Words and Phrases: Intelligent tutoring systems, automatic hint generation, programming tutors, educational data mining and data clustering _____________________________________________________________________ 1. INTRODUCTION Hint annotation is one of the most time consuming components of developing intelligent tutoring systems. Barnes and Stamper developed a data-driven educational data mining __________________________________________________________________________________________ Authors‟ addresses: Wei Jin, Department of Computer Information Sciences, Shaw University, Raleigh, NC, USA. E-mail: wjin@shawu.edu ; Lorrie Lehmann, Matthew Johnson, Michael Eagle, Behrooz Mostafavi, and Tiffany Barnes, Department of Computer Science, University of North Carolina at Charlotte, Charlotte, NC, USA. E-mails: ljlehman@uncc.edu ; matjohns@uncc.edu ; mjeagle@uncc.edu ; bzmostaf@uncc.edu ; tiffany.barnes@gmail.com ; John Stamper, Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, PA, USA. E-mail: jstamper@cs.cmu.edu .