BeSocratic: An Intelligent Tutoring System for the Recognition, Evaluation, and Analysis of Free-Form Student Input

Autor/in	Bryfczynski, Samuel Paul
Titel	BeSocratic: An Intelligent Tutoring System for the Recognition, Evaluation, and Analysis of Free-Form Student Input
Quelle	(2012), (127 Seiten) PDF als Volltext Verfügbarkeit Ph.D. Dissertation, Clemson University
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
ISBN	978-1-2678-7148-0
Schlagwörter	Hochschulschrift; Dissertation; Intelligent Tutoring Systems; Multiple Choice Tests; Feedback (Response); Questioning Techniques; Markov Processes; STEM Education; Chemistry; Computer Science; Learning Modules; Universities; Student Evaluation + Suchen Sie Ihr Suchwort? Thesis; Dissertations; Academic thesis; Intelligentes Tutorsystem; Multiple choice examinations; Multiple-choice tests, Multiple-choice examinations; Multiple-Choice-Verfahren; Befragungstechnik; Fragetechnik; Markowscher Prozess; STEM; Chemie; Informatik; Learning module; Lernmodul; University; Universität; Schulnote; Studentische Bewertung
Abstract	This dissertation describes a novel intelligent tutoring system, BeSocratic, which aims to help fill the gap between simple multiple-choice systems and free-response systems. BeSocratic focuses on targeting questions that are free-form in nature yet defined to the point which allows for automatic evaluation and analysis. The system includes a set of modules which provide instructors with tools to assess student performance. Beyond text boxes and multiple-choice questions, BeSocratic contains several modules that recognize, evaluate, provide feedback, and analyze student-drawn structures, including Euclidean graphs, chemistry molecules, computer science graphs, and simple drawings. Our system uses a visual, rule-based authoring system which enables the creation of activities for use within science, technology, engineering, and mathematics classrooms. BeSocratic records each action that students make within the system. Using a set of post-analysis tools, teachers have the ability to examine both individual and group performances. We accomplish this using hidden Markov model-based clustering techniques and visualizations. These visualizations can help teachers quickly identify common strategies and errors for large groups of students. Furthermore, analysis results can be used directly to improve activities through advanced detection of student errors and refined feedback. BeSocratic activities have been created and tested at several universities. We report specific results from several activities, and discuss how BeSocratic's analysis tools are being used with data from other systems. We specifically detail two chemistry activities and one computer science activity: (1) an activity focused on improving mechanism use, (2) an activity which assesses student understanding of Gibbs energy, and (3) an activity which teaches students the fundamentals of splay trees. In addition to analyzing data collected from students within BeSocratic, we share our visualizations and results from analyzing data gathered with another educational system, PhET. [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