%0 Conference Paper %1 Jiang:2019:TSI:3298689.3347030 %A Jiang, Weijie %A Pardos, Zachary A. %B Proceedings of the 13th ACM Conference on Recommender Systems %C New York, NY, USA %D 2019 %I ACM %K course-recommender mooc recommender sequencing %P 506--510 %R 10.1145/3298689.3347030 %T Time Slice Imputation for Personalized Goal-based Recommendation in Higher Education %U http://doi.acm.org/10.1145/3298689.3347030 %X Learners are often faced with the following scenario: given a goal for the future, and what they have learned in the past, what should they do now to best achieve their goal? We build on work utilizing deep learning to make inferences about how past actions correspond to future outcomes and enhance this work with a novel application of backpropagation to learn per-user optimized next actions. We apply this technique to two datasets, one from a university setting in which courses can be recommended towards preparation for a target course, and one from a massive open online course (MOOC) in which course pages can be recommended towards quiz preparation. In both cases, our algorithm is applied to recommend actions the learner can take to maximize a desired future achievement objective, given their past actions and performance. %@ 978-1-4503-6243-6

@inproceedings{Jiang:2019:TSI:3298689.3347030, abstract = {Learners are often faced with the following scenario: given a goal for the future, and what they have learned in the past, what should they do now to best achieve their goal? We build on work utilizing deep learning to make inferences about how past actions correspond to future outcomes and enhance this work with a novel application of backpropagation to learn per-user optimized next actions. We apply this technique to two datasets, one from a university setting in which courses can be recommended towards preparation for a target course, and one from a massive open online course (MOOC) in which course pages can be recommended towards quiz preparation. In both cases, our algorithm is applied to recommend actions the learner can take to maximize a desired future achievement objective, given their past actions and performance.}, acmid = {3347030}, added-at = {2019-09-18T17:00:08.000+0200}, address = {New York, NY, USA}, author = {Jiang, Weijie and Pardos, Zachary A.}, biburl = {https://www.bibsonomy.org/bibtex/28d37809980d238968c2b66b616df7d30/brusilovsky}, booktitle = {Proceedings of the 13th ACM Conference on Recommender Systems}, description = {Time slice imputation for personalized goal-based recommendation in higher education}, doi = {10.1145/3298689.3347030}, interhash = {0a0f629c04c03e06aab19c8caddcc106}, intrahash = {8d37809980d238968c2b66b616df7d30}, isbn = {978-1-4503-6243-6}, keywords = {course-recommender mooc recommender sequencing}, location = {Copenhagen, Denmark}, numpages = {5}, pages = {506--510}, publisher = {ACM}, series = {RecSys '19}, timestamp = {2019-09-18T17:00:08.000+0200}, title = {Time Slice Imputation for Personalized Goal-based Recommendation in Higher Education}, url = {http://doi.acm.org/10.1145/3298689.3347030}, year = 2019 }