56 International Journal of People-Oriented Programming, 3(2), 56-74, July-December 2014 Copyright © 2014, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. ABSTRACT Two major goals in Educational Data Mining are determining students’state of knowledge and determining their affective state as students progress through the learning session. While many models and solutions have been explored for each of these problems, relatively little work has been done on examining these states in parallel, even though the psychology literature suggests that it is an interplay of both of these states that infuences how a student performs and behaves. This work proposes a model that takes into account the performance and behavior of students when working with an Intelligent Tutoring System in order to track both knowledge and engagement and tests it on data from two different systems and explores the usefulness of such models. Modeling the Interplay Between Knowledge and Affective Engagement in Students Sarah E. Schultz, Department of Computer Science, Worcester Polytechnic Institute, Worcester, MA, USA Ivon Arroyo, Department of Social Sciences and Policy Studies, Worcester Polytechnic Institute, Worcester, MA, USA Keywords: Affect Detection, Behavior, Engagement, Knowledge Tracing, Performance INTRODUCTION Intelligent Tutoring Systems (Cognitive Tutors, or adaptive interactive learning environments) are meant to personalize learning by simulating the behaviors of a human tutor, adapting to students’ needs in order to better teach the student. In order to do this, they must have an estima- tion of each student’s knowledge as they progress through the tutoring session. Such systems might use these estimations of a student’s mastery of the subject to decide whether to adjust the difficulty of problems given (the level of challenge) or progress to a new unit (move on, as the previous unit is mastered). These models may also be used by teachers and researchers, instead of the software itself, to estimate students’ mastery of individual skills or whole knowledge units. In the field of Educational Data Mining, the standard way to model and trace student knowl- edge is via knowledge tracing (Corbett & Anderson, 1995). However, students often become disengaged as they use the software, confounding models that rely solely on performance data on individual questions to estimate students’ changing knowledge. To these models that estimate DOI: 10.4018/IJPOP.2014070103