Analyzing Learner Affect in a Scenario-Based Intelligent Tutoring System

Nye, Benjamin
Karumbaiah, Shamya
Tokel, Saniye Tuğba
Core, Mark G.
Stratou, Giota
Auerbach, Daniel
Georgila, Kallirroi
Scenario-based tutoring systems influence affective states due to two distinct mechanisms during learning: (1) reactions to performance feedback and (2) responses to the scenario context or events. To explore the role of affect and engagement, a scenario-based ITS was instrumented to support unobtrusive facial affect detection. Results from a sample of university students showed relatively few traditional academic affective states such as confusion or frustration, even at decision points and after poor performance (e.g., incorrect responses). This may show evidence of "over-flow," with a high level of engagement and interest but insufficient confusion/disequilibrium for optimal learning.
18th International Conference on Artificial Intelligence in Education (AIED)


Prospective Middle School Mathematics Teachers' Covariational Reasoning for Interpreting Dynamic Events During Peer Interactions
Yemen-Karpuzcu, Secil; Ulusoy, Fadime; Işıksal Bostan, Mine (2017-01-01)
This study investigated the covariational reasoning abilities of prospective middle school mathematics teachers in a task about dynamic functional events involving two simultaneously changing quantities in an individual process and also in a peer interaction process. The focus was the ways in which prospective teachers' covariational reasoning abilities re-emerge in the peer interaction process in excess of their covariational reasoning. The data sources were taken from the individual written responses of p...
Measuring striving for understanding and learning value of geometry: a validity study
Ubuz, Behiye (Informa UK Limited, 2017-01-01)
The current study aimed to construct a questionnaire that measures students' personality traits related to striving for understanding and learning value of geometry and then examine its psychometric properties. Through the use of multiple methods on two independent samples of 402 and 521 middle school students, two studies were performed to address this issue to provide support for its validity. In Study 1, exploratory factor analysis indicated the two-factor model. In Study 2, confirmatory factor analysis ...
Concurrent validity and test-retest reliability of the information processing styles
Baloğlu, Mustafa; Zelhart, PF (2000-12-01)
To investigate concurrent validity and test-retest reliability of thr Information Processing Styles, 62 students majoring in social sciences evaluated the accuracy of the checklist in describing their dominant types. Each student had a friend who read the descriptions of thy dominant types(s) of the student and rated their perceived accuracy of that categorization. Analyses indicated the inventory is reliable and valid.
Assessment of web-based courses: a discussion and analysis of learners individual difference and teaching-learning process
Gülbahar, Yasemin; Yıldırım, İbrahim Soner; Department of Computer Education and Instructional Technology (2002)
This study examined the role of individual differences and the quality of the teaching-learning process on learning outcomes in a web-based instructional environment, and explored the implications of these variables on the design, delivery and evaluation stages of web-based instruction. The subjects of this study were the students of two web-supported traditional courses, being one undergraduate and the other graduate, offered by the Computer Education and Instructional Technologies Department of METU. Fort...
Positive impact of state similarity on reinforcement learning performance
Girgin, Sertan; Polat, Faruk; Alhaj, Reda (Institute of Electrical and Electronics Engineers (IEEE), 2007-10-01)
In this paper, we propose a novel approach to identify states with similar subpolicies and show how they can be integrated into the reinforcement learning framework to improve learning performance. The method utilizes a specialized tree structure to identify common action sequences of states, which are derived from possible optimal policies, and defines a similarity function between two states based on the number of such sequences. Using this similarity function, updates on the action-value function of a st...
Citation Formats
B. Nye et al., “Analyzing Learner Affect in a Scenario-Based Intelligent Tutoring System,” Cent China Normal Univ, Wuhan, PEOPLES R CHINA, 2017, vol. 10331, Accessed: 00, 2020. [Online]. Available: