I am presenting a short talk at the 42nd Conference of Research and Development by Tecnologico de Monterrey (CIDTEC) in Monterrey, Nuevo Leon, Mexico. January 2012.
Meta-tutoring applies the basic policies of interactive tutoring to get students to adopt effective meta-cognitive strategies. Unfortunately, when the meta-tutor is removed, students often revert to using ineffective strategies. This paper is an early report on the progress of the Affective Meta-Tutoring (AMT) project, which will use an affective learning companion to motivate students to more permanently adopt effective meta-cognitive strategies. The first task of the project was to implement a modeling tool and instructions that were simple enough that high school students could become moderately proficient in a few hours. This proved to be quite challenging. We conducted four studies where all students gave verbal protocols as they worked. Analyses of the screen videos, audio and log data led to many changes. During the last study, most students were able to construct models of at least the complexity shown in Figure 1 within the first hour of instruction. This learning rate is considerably faster than other projects have been able to achieve. The second task of the project was to develop the meta-tutor described earlier and evaluate it. A random-assignment experiment in the 2011 summer camps tested two predictions: (1) Students who were meta-tutored during the first half of the experiment should learn faster than students instructed by the same system with the meta-tutor turned off. (2) When the meta-tutor was turned off during the second half of the experiment, the meta-tutored students should stop using the meta-strategy. Preliminary data analyses suggest small effects in the predicted directions but the analyses are not complete. The last task of the project is to develop an affective agent that increase students’ persistence in using the meta-cognitive strategy when the meta-tutoring is turned off. To this end, we collected physiological sensor data from our high school summer campers. The data will be used to calibrate affect detectors. The data were collected from a facial camera, a posture sensing chair, a skin galvanometer and a posture sensing chair.
Proceedings of the 19th International Conference on Computers in Education.
Asia-Pacific Society for Computers in Education.
VanLehn K., Burleson W., Chavez-Echeagaray M.E., Christopherson R., Gonzalez-Sanchez J., Hidalgo-Pontet Y., Zhang L.(2012). The Affective Meta-Tutoring Project: How to Motivate Students to Use Effective Meta-cognitive Strategies. Companion of the 42nd Conference of Research and Development by Tecnologico de Monterrey. Monterrey, Nuevo Leon, Mexico. January 2012. Page 232. ISBN: 978-607-501-073-1