If computers are to interact naturally with humans, they should recognize students’ affect and express social competencies. Research has shown that learning is enhanced when empathy or support is provided and that improved personal relationships between teachers and students leads to increased student motivation.1-4 Therefore, if tutoring systems can embed affective support for students, they should be more effective. However, previous research has tended to privilege the cognitive over the affective and to view learning as information processing, marginalizing, or ignoring affect.5 This chapter describes two data-driven approaches toward the automatic prediction of affective variables by creating models from students’ past behavior (log-data). The first case study shows the methodology and accuracy of an empirical model that helps predict students’ general attitudes, goals, and perceptions of the software, and the second develops empirical models for predicting students’ fluctuating emotions while using the system. The vision is to use these models to predict students’ learning and positive attitudes in real time. Special emphasis is placed in this chapter on understanding and inspecting these models, to understand how students express their emotions, attitudes, goals, and perceptions while using a tutoring system.
ASJC Scopus subject areas
- Economics, Econometrics and Finance(all)
- Business, Management and Accounting(all)
- Computer Science(all)