Toward Intelligent Animated Tutoring Systems: Monitoring of Student Comprehension through Facial Expression Classification

Literaturnachweis - Detailanzeige

Trefferliste

Autor/in	Agada, Ruth O.
Titel	Toward Intelligent Animated Tutoring Systems: Monitoring of Student Comprehension through Facial Expression Classification
Quelle	(2016), (144 Seiten) PDF als Volltext Verfügbarkeit D.C.S. Dissertation, Bowie State University
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
ISBN	978-1-3922-4135-6
Schlagwörter	Hochschulschrift; Dissertation; Intelligent Tutoring Systems; Comprehension; Nonverbal Communication; Identification; Computer Simulation; Computer Science Education; Programming; Psychological Patterns; Retention (Psychology); Learning Experience; Visualization + Suchen Sie Ihr Suchwort? Thesis; Dissertations; Academic thesis; Intelligentes Tutorsystem; Verstehen; Verständnis; Non-verbal communication; Nonverbale Kommunikation; Identifikation; Identifizierung; Computergrafik; Computersimulation; Computer science lessons; Informatikunterricht; Programmierung; Merkfähigkeit; Lernerfahrung; Visualisation; Visualisierung
Abstract	Recognition of spontaneous emotion would influence human-computer interaction and emotion-related studies in many related fields. In any given environment, the spontaneous generation of expression are more often observed than their prototypic counterparts.This thesis explores methods for detecting emotional facial expressions occurring in a tutor-tutee setting -- the expressions made by the tutee to non verbally communicate understanding. Given the importance of non-verbal communication in human dialog, the information gathered will in turn be used to inform the agent on user understanding of material and be able to provide a more realistic relationship between a tutor and the tutee. Considering that in-class teaching time is very limited, it can be very challenging for an educator to instruct the student, while keeping the student's interest in the course high throughout the semester. This requires innovation in teaching, especially when the class is large. The affect sensitive animated tutoring system is designed to simulate the process of one-to-one tutoring of small class teaching and helping educators to further supplement the contents to suit the needs of the students. The intelligence of the embodied agent system comes from information related to the student knowledge, the specific domain knowledge, and the teaching strategies, but also the affective state of the student and the role it plays in helping the student progress through the curriculum. In this research, we put forth an affect sensitive emotionally capable animated tutoring system for introduction to programing courses, providing the student the opportunity to learn about certain aspects of the course. Key instruction modules based on core concepts in programing will be created in which the student is presented with a lecture specified by the instructor, as well topics to be covered in that lecture. Based on the subtopic selected by the student, only information pertinent to that subtopic is displayed. As the session proceeds the system will monitor the student for affective feedback via any spontaneous facial expression generation. Once a negative affect is detected the embodied agent will then assess the student to determine the root of the affect ad devise a strategy to help the student progress from the negative affect to a positive one. Also, following each lecture, quizzes will be made available to test the students' comprehension and retention of the lecture. The quiz modules test students on information covered in each lecture module.Three issues were evaluated in the analyses: the comprehension level of the user after interacting with the system, the user's perception of their learning experiences as a result of the embedded animated agent and the affective visualization of the different learning states. Preliminary results show that the condition in which the agent is fully expressive shows a marked increase in the level of comprehension because as we speculated the user is more invested in the software when the agent fully articulates emotion through head movement and facial expression. In addition, the condition in which the agent is partially animated illustrates that the comprehension level is the average of both the fully animated and non-animated agent. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.] (As Provided).
Anmerkungen	ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01