Publications-Theses
Article View/Open
Publication Export
-
題名 應用Embedding於音樂播放推薦
Application of embedding in music recommendation作者 賴東昇
Lai, Tung-Sheng貢獻者 翁久幸
Weng, Chiu-Hsing
賴東昇
Lai, Tung-Sheng關鍵詞 推薦系統
音樂推薦
Embedding
Recommendation日期 2019 上傳時間 1-Jul-2019 10:43:21 (UTC+8) 摘要 Embedding為一種學習出目標之向量表示的方法。透過類神經網路或其他模型架構，Embedding能學習出優良的向量表示，並被廣泛用於文字分析、社群網路、推薦系統等領域。本論文使用Word2vec與LINE兩種embedding方法，透過序列化之音樂播放紀錄學習出使用者與音樂之向量表示，並檢視其性質。接著，我們結合兩者，同時考慮使用者之長期偏好與當下播放歌曲之性質，將其用於使用者之下一首歌曲、演唱者預測，並取得了不錯的準確率。研究顯示embedding方法可用於學習序列化資料之資訊，除了能呈現音樂之間的相似關係外，亦可用於音樂推薦之任務中。
Embedding is a method used for learning vector representation of target objects. With neural network or other model structure, embedding is able to learn well vector representation and is used in text analysis, social network, recommendation system and other fields. In this paper, we use two embedding method, Word2vec and LINE, along with music listening log data to learn the embedding of users and songs. We first show that the music embedding is able to preserve the genre similarity. Further, we combine user’s long term preference and current listening-session preference learned by embedding to conduct next n song and next n artist prediction. Result shows that embedding methods can be used in music recommendations.參考文獻 [1] http://www.cp.jku.at/datasets/LFM-1b/[2] M. Schedl. The LFM-1b Dataset for Music Retrieval and Recommendation. In Proceedings of the ICMR. 2016.[3] A. Poddar, E. Zangerle, and Y. Yang. #nowplaying-RS: A New Benchmark Dataset for Building Context-Aware Music Recommender Systems. In Proceedings of the Sound and Music Computing Conf. 2018.[4] T. Mikolov, K. Chen, G.Corrado, and J. Dean. Efficient Estimation of Word Representations in Vector Space. ICLR Workshop. 2013.[5] Q. Le, T. Mikolov. Distributed Representations of Sentences and Documents. In Proceedings of the ICML. 2014.[6] J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, and Q. Mei. Line: Large-scale Information Network Embedding. In Proceedings of the 24th International Conference on World Wide Web. 2015.[7] D. Wang, S. Deng, X. Zhang, and G. Xu. Learning Music Embedding with Metadata for Context Aware Recommendation. In Proceedings of the ICMR. 2016.[8] J. Tang and K. Wang. Personalized Top-n Sequential Recommendation Via Convolutional Sequence Embedding. In Proceedings of the WSDM. 2018.[9] H. Chen, B. Perozzi, R. Al-Rfou, and S. Skiena. A Tutorial on Network Embeddings. arXiv preprint arXiv:1808.02590. 2018.[10] B. Perozzi, R. Al-Rfou, and S. Skiena. Deepwalk: Online Learning of Social Representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014.[11] R. Salakhutdinov and A. Mnih. Probabilistic Matrix Factorization. In Advances in Neural Information Processing Systems, volume 20. 2008.[12] Y. Koren, R. Bell, and C. Volinsky. Matrix Factorization Techniques for Recommender Systems. IEEE Computer, 42(8):30–37, 2009.[13] Y. Hu, Y. Koren, and C. Volinsky. Collaborative Filtering for Implicit Feedback Datasets. In IEEE International Conference on Data Mining. 2008.[14] O. Barkan and N. Koenigstein. Item2vec: Neural Item Embedding for Collaborative Filtering. arXiv preprint arXiv:1603.04259. 2016.[15] M. Grbovic and H. Cheng. Real-time Personalization Using Embeddings for Search Ranking at Airbnb. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2018.[16] H. Zamani, M. Schedl, P. Lamere, and C. Chen. An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation. arXiv preprint arXiv:1810.01520. 2018.[17] https://www.spotify.com/us/discoverweekly/[18] L. van der Maaten and G. Hinton. Visualizing High-Dimensional Data Using t-SNE. Journal of Machine Learning Research 9:2579-2605. 2008.[19] L. van der Maaten. Accelerating t-SNE Using Tree-based Algorithms. Journal of machine learning research. 2014.[20] O. Levy, Y. Goldberg, and I. RamatGan. Linguistic Regularities in Sparse and Explicit Word Representations. CoNLL-2014.[21] T. Bolukbasi, K. Chang, J. Zou, V. Saligrama, and A. Kalai. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. In Advances in Neural Information Processing Systems. 2016.[22] B. Hidasi, A. Karatzoglou, L. Baltrunas, and D. Tikk. Session-Based Recommendations with Recurrent Neural Networks. arXiv preprint arXiv:1511.06939. 2015.[23] Y. Kim. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882. 2014.[24] https://en.wikipedia.org/wiki/Shoegazing#History[25] S. Rendle, C. Freudenthaler, and L. Schmidt-Thieme. Factorizing Personalized Markov Chains for Next-Basket Recommendation. In International Conference on World Wide Web. ACM, 811–820. 2010.[26] S. Zhang, L. Yao, and A. Sun. Deep Learning Based Recommender System: A survey and New Perspectives. arXiv preprint arXiv:1707.07435, 2017.[27] Z. Cheng, J. Shen, L. Zhu, M. Kankanhalli, and L. Nie. Exploiting Music Play Sequence for Music Recommendation. In Proceedings of the 26th International Joint Conference on Artificial Intelligence. 2017.[28] https://github.com/tangjianpku/LINE[29] R. R ̌ehu ̇r ̌ek and P. Sojka. Software Framework for Topic Modelling with Large Corpora. In LREC, 2010.[30] C. Chen, M. Tsai, Y. Lin, and Y. Yang. Query-based music recommendations via preference embedding. In Proceedings of the 10th ACM Conference on Recommender Systems, pages 79–82. ACM, 2016. 描述 碩士
國立政治大學
統計學系
106354002資料來源 http://thesis.lib.nccu.edu.tw/record/#G0106354002 資料類型 thesis dc.contributor.advisor 翁久幸 zh_TW dc.contributor.advisor Weng, Chiu-Hsing en_US dc.contributor.author (Authors) 賴東昇 zh_TW dc.contributor.author (Authors) Lai, Tung-Sheng en_US dc.creator (作者) 賴東昇 zh_TW dc.creator (作者) Lai, Tung-Sheng en_US dc.date (日期) 2019 en_US dc.date.accessioned 1-Jul-2019 10:43:21 (UTC+8) - dc.date.available 1-Jul-2019 10:43:21 (UTC+8) - dc.date.issued (上傳時間) 1-Jul-2019 10:43:21 (UTC+8) - dc.identifier (Other Identifiers) G0106354002 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/124120 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 統計學系 zh_TW dc.description (描述) 106354002 zh_TW dc.description.abstract (摘要) Embedding為一種學習出目標之向量表示的方法。透過類神經網路或其他模型架構，Embedding能學習出優良的向量表示，並被廣泛用於文字分析、社群網路、推薦系統等領域。本論文使用Word2vec與LINE兩種embedding方法，透過序列化之音樂播放紀錄學習出使用者與音樂之向量表示，並檢視其性質。接著，我們結合兩者，同時考慮使用者之長期偏好與當下播放歌曲之性質，將其用於使用者之下一首歌曲、演唱者預測，並取得了不錯的準確率。研究顯示embedding方法可用於學習序列化資料之資訊，除了能呈現音樂之間的相似關係外，亦可用於音樂推薦之任務中。 zh_TW dc.description.abstract (摘要) Embedding is a method used for learning vector representation of target objects. With neural network or other model structure, embedding is able to learn well vector representation and is used in text analysis, social network, recommendation system and other fields. In this paper, we use two embedding method, Word2vec and LINE, along with music listening log data to learn the embedding of users and songs. We first show that the music embedding is able to preserve the genre similarity. Further, we combine user’s long term preference and current listening-session preference learned by embedding to conduct next n song and next n artist prediction. Result shows that embedding methods can be used in music recommendations. en_US dc.description.tableofcontents 摘要 iiAbstract iii目錄 iv表目錄 v圖目錄 vi第一章 緒論 1第二章 文獻回顧 3第三章 資料介紹 5第一節 資料簡介 5第二節 資料預處理與篩選 7第四章 研究方法 11第一節 Word2vec與Skip-Gram Negative Sampling 11第二節 Network Embedding與LINE 14第五章 研究設定與評估準則 17第一節 Embedding方法用於音樂推薦 17第二節 結合LINE與Word2vec之兩階段商品推薦 24第三節 實驗目標與評估準則 27第六章 實驗結果 29第一節 歌曲預測 29第二節 演唱者預測 34第三節 其他推薦方法 35第四節 Embedding之結果、與其意義 37第七章 結論與建議 39參考文獻 41 zh_TW dc.format.extent 1432902 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0106354002 en_US dc.subject (關鍵詞) 推薦系統 zh_TW dc.subject (關鍵詞) 音樂推薦 zh_TW dc.subject (關鍵詞) Embedding en_US dc.subject (關鍵詞) Recommendation en_US dc.title (題名) 應用Embedding於音樂播放推薦 zh_TW dc.title (題名) Application of embedding in music recommendation en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] http://www.cp.jku.at/datasets/LFM-1b/[2] M. Schedl. The LFM-1b Dataset for Music Retrieval and Recommendation. In Proceedings of the ICMR. 2016.[3] A. Poddar, E. Zangerle, and Y. Yang. #nowplaying-RS: A New Benchmark Dataset for Building Context-Aware Music Recommender Systems. In Proceedings of the Sound and Music Computing Conf. 2018.[4] T. Mikolov, K. Chen, G.Corrado, and J. Dean. Efficient Estimation of Word Representations in Vector Space. ICLR Workshop. 2013.[5] Q. Le, T. Mikolov. Distributed Representations of Sentences and Documents. In Proceedings of the ICML. 2014.[6] J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, and Q. Mei. Line: Large-scale Information Network Embedding. In Proceedings of the 24th International Conference on World Wide Web. 2015.[7] D. Wang, S. Deng, X. Zhang, and G. Xu. Learning Music Embedding with Metadata for Context Aware Recommendation. In Proceedings of the ICMR. 2016.[8] J. Tang and K. Wang. Personalized Top-n Sequential Recommendation Via Convolutional Sequence Embedding. In Proceedings of the WSDM. 2018.[9] H. Chen, B. Perozzi, R. Al-Rfou, and S. Skiena. A Tutorial on Network Embeddings. arXiv preprint arXiv:1808.02590. 2018.[10] B. Perozzi, R. Al-Rfou, and S. Skiena. Deepwalk: Online Learning of Social Representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014.[11] R. Salakhutdinov and A. Mnih. Probabilistic Matrix Factorization. In Advances in Neural Information Processing Systems, volume 20. 2008.[12] Y. Koren, R. Bell, and C. Volinsky. Matrix Factorization Techniques for Recommender Systems. IEEE Computer, 42(8):30–37, 2009.[13] Y. Hu, Y. Koren, and C. Volinsky. Collaborative Filtering for Implicit Feedback Datasets. In IEEE International Conference on Data Mining. 2008.[14] O. Barkan and N. Koenigstein. Item2vec: Neural Item Embedding for Collaborative Filtering. arXiv preprint arXiv:1603.04259. 2016.[15] M. Grbovic and H. Cheng. Real-time Personalization Using Embeddings for Search Ranking at Airbnb. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2018.[16] H. Zamani, M. Schedl, P. Lamere, and C. Chen. An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation. arXiv preprint arXiv:1810.01520. 2018.[17] https://www.spotify.com/us/discoverweekly/[18] L. van der Maaten and G. Hinton. Visualizing High-Dimensional Data Using t-SNE. Journal of Machine Learning Research 9:2579-2605. 2008.[19] L. van der Maaten. Accelerating t-SNE Using Tree-based Algorithms. Journal of machine learning research. 2014.[20] O. Levy, Y. Goldberg, and I. RamatGan. Linguistic Regularities in Sparse and Explicit Word Representations. CoNLL-2014.[21] T. Bolukbasi, K. Chang, J. Zou, V. Saligrama, and A. Kalai. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings. In Advances in Neural Information Processing Systems. 2016.[22] B. Hidasi, A. Karatzoglou, L. Baltrunas, and D. Tikk. Session-Based Recommendations with Recurrent Neural Networks. arXiv preprint arXiv:1511.06939. 2015.[23] Y. Kim. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882. 2014.[24] https://en.wikipedia.org/wiki/Shoegazing#History[25] S. Rendle, C. Freudenthaler, and L. Schmidt-Thieme. Factorizing Personalized Markov Chains for Next-Basket Recommendation. In International Conference on World Wide Web. ACM, 811–820. 2010.[26] S. Zhang, L. Yao, and A. Sun. Deep Learning Based Recommender System: A survey and New Perspectives. arXiv preprint arXiv:1707.07435, 2017.[27] Z. Cheng, J. Shen, L. Zhu, M. Kankanhalli, and L. Nie. Exploiting Music Play Sequence for Music Recommendation. In Proceedings of the 26th International Joint Conference on Artificial Intelligence. 2017.[28] https://github.com/tangjianpku/LINE[29] R. R ̌ehu ̇r ̌ek and P. Sojka. Software Framework for Topic Modelling with Large Corpora. In LREC, 2010.[30] C. Chen, M. Tsai, Y. Lin, and Y. Yang. Query-based music recommendations via preference embedding. In Proceedings of the 10th ACM Conference on Recommender Systems, pages 79–82. ACM, 2016. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU201900087 en_US
