Research Article
Student Action Prediction for Automatic Tutoring for Procedural Training in 3D Virtual Environments
361 downloads
@INPROCEEDINGS{10.1007/978-3-319-28883-3_25, author={Diego Riofr\^{\i}o-Luzcando and Jaime Ram\^{\i}rez}, title={Student Action Prediction for Automatic Tutoring for Procedural Training in 3D Virtual Environments}, proceedings={E-Learning, E-Education, and Online Training. Second International Conference, eLEOT 2015, Novedrate, Italy, September 16-18, 2015, Revised Selected Papers}, proceedings_a={ELEOT}, year={2016}, month={1}, keywords={Intelligent Tutoring Systems Educational Data Mining e-learning Procedural training Virtual environments}, doi={10.1007/978-3-319-28883-3_25} }- Diego Riofrío-Luzcando
Jaime Ramírez
Year: 2016
Student Action Prediction for Automatic Tutoring for Procedural Training in 3D Virtual Environments
ELEOT
Springer
DOI: 10.1007/978-3-319-28883-3_25
Abstract
This paper presents a way to predict student actions, by using student logs generated by a 3D virtual environment for procedural training. Each student log is categorized in a cluster based on the number of errors and the total time spent to complete the entire practice. For each cluster an extended automata is created, which allows us to generate more reliable predictions according to each student type. States of this extended automata represent the effect of a student correct or failed action. The most common behaviors can be predicted considering the sequences of more frequent actions. This is useful to anticipate common student errors, and this can help an Intelligent Tutoring System to generate feedback proactively.
Copyright © 2015–2024 ICST