Print Email Facebook Twitter Feature Engineering for Second Language Acquisition Modeling Title Feature Engineering for Second Language Acquisition Modeling Author Chen, G. (TU Delft Web Information Systems) Hauff, C. (TU Delft Web Information Systems) Houben, G.J.P.M. (TU Delft Web Information Systems) Contributor Tetreault, Joel (editor) Burstein, Jill (editor) Kochmar, Ekaterina (editor) Leacock, Claudia (editor) Yannakoudakis, Helen (editor) Date 2018 Abstract Knowledge tracing serves as a keystone in delivering personalized education. However, few works attempted to model students’ knowledge state in the setting of Second Language Acquisition. The Duolingo Shared Task on Second Language Acquisition Modeling (Settles et al., 2018) provides students’ trace data that we extensively analyze and engineer features from for the task of predicting whether a student will correctly solve a vocabulary exercise. Our analyses of students’ learning traces reveal that factors like exercise format and engagement impact their exercise performance to a large extent. Overall, we extracted 23 different features as input to a Gradient Tree Boosting framework, which resulted in an AUC score of between 0.80 and 0.82 on the official test set. To reference this document use: http://resolver.tudelft.nl/uuid:9258d413-129f-45e8-848c-2a9083d3bcc8 Source Proceedings of the 13th Workshop on Innovative Use of NLP for Building Educational Applications Part of collection Institutional Repository Document type conference paper Rights © 2018 G. Chen, C. Hauff, G.J.P.M. Houben Files PDF chen.slam18.pdf 418.07 KB Close viewer /islandora/object/uuid:9258d413-129f-45e8-848c-2a9083d3bcc8/datastream/OBJ/view