{"pk":27788,"title":"Towards a Pedigogical Conversational Agent for Collaborative Learning: A Model Based on Gaze Recurrence and Information Overlap","subtitle":null,"abstract":"This study focuses on collaborative learning involving a\nknowledge integration activity, whereby learner dyads explain\neach other’s expert knowledge. It was hypothesized that learn-\ning gain can be determined by the degree to which learn-\ners synchronize their gaze (gaze recurrence) and use overlap-\nping language (information overlap) during their interaction.\nThirty-four learners participated in a laboratory-based eye-\ntracking experiment, wherein learners’ gazes and oral dialogs\nwere analyzed. Multiple regression analysis was conducted,\nwherein learning performance was regressed on the two inde-\npendent variables. Then, a simulation was conducted to view\nhow the model predicts performance based on the collabora-\ntive process. The results showed that both gaze recurrence and\nlexical overlap significantly predicted learning performance in\nthe current task. Furthermore, the suggested model success-\nfully predicted learning performance in the simulation. These\nresults indicate that the two variables might be useful for de-\nveloping detection modules that enable a better understanding\nof learner-learner collaborative learning.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"Collaborative learning"},{"word":"Pedagogical Conversational Agent"},{"word":"Information Overlap"},{"word":"Gaze recurrence"}],"section":"Publication-based-Talks","is_remote":true,"remote_url":"https://escholarship.org/uc/item/11p1p7ps","frozenauthors":[{"first_name":"Yugo","middle_name":"","last_name":"Hayashi","name_suffix":"","institution":"Ritsumeikan University; Carnegie Mellon","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2018-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/27788/galley/17428/download/"}]}