%0 Conference Paper %1 Ajalloeian_2022 %A Ajalloeian, Ahmad %A Vlachos, Michalis %A Schneider, Johannes %A Steinmann, Alexis %B Proceedings of the 31st ACM International Conference on Information &amp$\mathsemicolon$ Knowledge Management %D 2022 %I ACM %K cikm2022 e-learning music-recommendation recommender %P 2853-2862 %R 10.1145/3511808.3557111 %T A Case Study in Educational Recommenders: Recommending Music Partitures at Tomplay %U https://doi.org/10.1145%2F3511808.3557111 %X Recommendation technologies have been playing an instrumental role for promoting both physical and digital content across several global platforms (Amazon, Apple, Netflix). Here we provide a study on the benefits of recommendation technologies in an educational platform with a focus on music learning. There are several characteristics present in this educational platform that make this recommendation problem particularly interesting, namely: a) the few but highly repetitive interactions, b) the existence of multiple versions of the same content across many difficulty levels, orchestrations, and musical instruments, and c) the user's expertise in a musical instrument which is essential for making appropriate recommendations. We highlight the unique dataset characteristics and compare them to those of other widely-used recommendation datasets. To alleviate the very high data sparsity due to the multi-instantiation of songs, we use entity resolution principles to embed songs in a new space. Using this lightweight entity resolution step on song data, in combination with neural recommendation architectures, we can double the predictive accuracy compared to techniques based on matrix factorization.

@inproceedings{Ajalloeian_2022, abstract = {Recommendation technologies have been playing an instrumental role for promoting both physical and digital content across several global platforms (Amazon, Apple, Netflix). Here we provide a study on the benefits of recommendation technologies in an educational platform with a focus on music learning. There are several characteristics present in this educational platform that make this recommendation problem particularly interesting, namely: a) the few but highly repetitive interactions, b) the existence of multiple versions of the same content across many difficulty levels, orchestrations, and musical instruments, and c) the user's expertise in a musical instrument which is essential for making appropriate recommendations. We highlight the unique dataset characteristics and compare them to those of other widely-used recommendation datasets. To alleviate the very high data sparsity due to the multi-instantiation of songs, we use entity resolution principles to embed songs in a new space. Using this lightweight entity resolution step on song data, in combination with neural recommendation architectures, we can double the predictive accuracy compared to techniques based on matrix factorization. }, added-at = {2022-10-19T22:27:19.000+0200}, author = {Ajalloeian, Ahmad and Vlachos, Michalis and Schneider, Johannes and Steinmann, Alexis}, biburl = {https://www.bibsonomy.org/bibtex/258948c04980202886cb969413bd98dfe/brusilovsky}, booktitle = {Proceedings of the 31st {ACM} International Conference on Information {\&}amp$\mathsemicolon$ Knowledge Management}, description = {A Case Study in Educational Recommenders: Recommending Music Partitures at Tomplay | Proceedings of the 31st ACM International Conference on Information & Knowledge Management}, doi = {10.1145/3511808.3557111}, interhash = {6d77fc27571af3a8ee881141222fb65f}, intrahash = {58948c04980202886cb969413bd98dfe}, keywords = {cikm2022 e-learning music-recommendation recommender}, month = oct, note = {Very interesting case of recommendations. Music to play... Need to have skill level and also same music could be recommended many times...}, pages = {2853-2862}, publisher = {{ACM}}, timestamp = {2022-10-19T22:27:19.000+0200}, title = {A Case Study in Educational Recommenders: Recommending Music Partitures at Tomplay}, url = {https://doi.org/10.1145%2F3511808.3557111}, year = 2022 }