Multimodal Data Analytics

JavaTutor Data Collection Setup

The JavaTutor project produced one of the largest multimodal datasets of tutorial dialogue ever collected. Itincludes measures of effectiveness through learning gains and a suite of affective outcomes. The data consists of computer-mediated textual dialogue for introductory computer science and is accompanied by logs of fine-grained problem solving, facial expression videos and and Kinect depth videos capturing posture and gesture, as well as skin conductance traces. The corpus also includes pre-measures including demographics, self-efficacy, and attitudes toward learning, post-measures including engagement and frustration, as well as pre and post learning outcomes.

JavaTutor MultiModal Data Collection

Comments are closed