%0 Conference Paper %1 citeulike:14346943 %A Zhang, Liang %A Xiong, Xiaolu %A Zhao, Siyuan %A Botelho, Anthony %A Heffernan, Neil T. %B Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale %C New York, NY, USA %D 2017 %I ACM %K deep-learning knowledge-tracing las2017 %P 169--172 %R 10.1145/3051457.3053976 %T Incorporating Rich Features into Deep Knowledge Tracing %U http://dx.doi.org/10.1145/3051457.3053976 %X Knowledge Tracing aims to model student knowledge by predicting the correctness of each next item as students work through an assignment. Through recent developments in deep learning, Deep Knowledge Tracing (DKT) was explored as a method to improve upon traditional methods. Thus far, the DKT model has only considered the knowledge components and correctness as input, neglecting the other important features collected by computer-based learning platforms. This paper seeks to further improve upon DKT by incorporating more problem-level features. With this higher dimensional input, an adaption to the original DKT model structure is also proposed to convert the input into a low dimensional feature vector. Our results show that this adapted DKT model can effectively improve accuracy. %@ 978-1-4503-4450-0

@inproceedings{citeulike:14346943, abstract = {{Knowledge Tracing aims to model student knowledge by predicting the correctness of each next item as students work through an assignment. Through recent developments in deep learning, Deep Knowledge Tracing (DKT) was explored as a method to improve upon traditional methods. Thus far, the DKT model has only considered the knowledge components and correctness as input, neglecting the other important features collected by computer-based learning platforms. This paper seeks to further improve upon DKT by incorporating more problem-level features. With this higher dimensional input, an adaption to the original DKT model structure is also proposed to convert the input into a low dimensional feature vector. Our results show that this adapted DKT model can effectively improve accuracy.}}, added-at = {2018-03-19T12:24:51.000+0100}, address = {New York, NY, USA}, author = {Zhang, Liang and Xiong, Xiaolu and Zhao, Siyuan and Botelho, Anthony and Heffernan, Neil T.}, biburl = {https://www.bibsonomy.org/bibtex/21c87b0fc4335dfcd05e031763dfce1f7/aho}, booktitle = {Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale}, citeulike-article-id = {14346943}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=3053976}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/3051457.3053976}, doi = {10.1145/3051457.3053976}, interhash = {7eb3f915674e8c49b690942e7179befb}, intrahash = {1c87b0fc4335dfcd05e031763dfce1f7}, isbn = {978-1-4503-4450-0}, keywords = {deep-learning knowledge-tracing las2017}, location = {Cambridge, Massachusetts, USA}, pages = {169--172}, posted-at = {2017-04-29 19:02:33}, priority = {2}, publisher = {ACM}, series = {L@S '17}, timestamp = {2018-03-19T12:24:51.000+0100}, title = {{Incorporating Rich Features into Deep Knowledge Tracing}}, url = {http://dx.doi.org/10.1145/3051457.3053976}, year = 2017 }