Literaturnachweis - Detailanzeige
Autor/inn/en | Rajendran, Ramkumar; Kumar, Anurag; Carter, Kelly E.; Levin, Daniel T.; Biswas, Gautam |
---|---|
Titel | Predicting Learning by Analyzing Eye-Gaze Data of Reading Behavior [Konferenzbericht] Paper presented at the International Conference on Educational Data Mining (EDM) (11th, Raleigh, NC, Jul 16-20, 2018). |
Quelle | (2018), (7 Seiten)
PDF als Volltext |
Sprache | englisch |
Dokumenttyp | gedruckt; online; Monographie |
Schlagwörter | Eye Movements; Reading Processes; Reading Strategies; Middle School Students; Educational Technology; Technology Uses in Education; Artificial Intelligence; Science Instruction; Teaching Methods; Hypermedia; Classification; Causal Models; Maps; Predictor Variables Augenbewegung; Leseprozess; Reading strategy; Leselernstufe; Lesetechnik; Middle school; Middle schools; Student; Students; Mittelschule; Mittelstufenschule; Schüler; Schülerin; Unterrichtsmedien; Technology enhanced learning; Technology aided learning; Technologieunterstütztes Lernen; Künstliche Intelligenz; Teaching of science; Science education; Natural sciences Lessons; Naturwissenschaftlicher Unterricht; Teaching method; Lehrmethode; Unterrichtsmethode; Classification system; Klassifikation; Klassifikationssystem; Kausalanalyse; Map; Karte; Prädiktor |
Abstract | Researchers have highlighted how tracking learners' eye-gaze can reveal their reading behaviors and strategies, and this provides a framework for developing personalized feedback to improve learning and problem solving skills. In this paper, we describe analyses of eye-gaze data collected from 16 middle school students who worked with Betty's Brain, an open-ended learning environment, where students learn science by building causal models to teach a virtual agent. Our goal was to test whether newly available consumer-level eye trackers could provide the data that would allow us to probe further into the relations between students' reading of hypertext resources and building of graphical causal maps. We collected substantial amounts of gaze data and then constructed classifier models to predict whether students would be successful in constructing correct causal links. These models predicted correct map-building actions with an accuracy of 80% (F1 = 0.82; Cohen's kappa K = 0.62). The proportions of correct link additions are in turn directly related to learners' performance in Betty's Brain. Therefore, students' gaze patterns when reading the resources may be good indicators of their overall performance. These findings can be used to support the development of a real-time eye gaze analysis system, which can detect students reading patterns, and when necessary provide support to help them become better readers. [For the full proceedings, see ED593090.] (As Provided). |
Anmerkungen | International Educational Data Mining Society. e-mail: admin@educationaldatamining.org; Web site: http://www.educationaldatamining.org |
Erfasst von | ERIC (Education Resources Information Center), Washington, DC |
Update | 2020/1/01 |