1. NCCU Academic Hub
  2. Publications
  3. College of Commerce
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 於直播電商環境下結合時間因素基於圖卷積網絡的推薦系統
Leveraging the Tripartite Relationships with Livestreaming E-Commerce Graphical Time-aware Recommender System
作者 廖偉丞
Liao, Wei-Cheng
貢獻者 林怡伶<br>蕭舜文
Lin, Yi-Ling<br>Hsiao, Shun-Weng
廖偉丞
Liao, Wei-Cheng
關鍵詞 直播電商
圖神經網絡
時間感知
推薦系統
Live Commerce
GNN
Time-aware
Recommender System
日期 2024
上傳時間 4-Sep-2024 14:05:20 (UTC+8)
摘要 直播電子商務 (live commerce) 的快速發展，對推薦系統 (RSs) 帶來了新的挑戰，需要建模用戶、商品和主播之間複雜的三方關係，並適當捕捉用戶偏好的變化。本研究提出了一種新的直播電子商務圖形時間感知推薦系統 (LGT-RS) 來應對這些挑戰。LGT-RS 利用圖卷積網絡 (GCNs) 來建模用戶、商品和主播之間的複雜關係，並結合了時間編碼方法來捕捉用戶偏好隨時間的動態演變。此外，為豐富數據並提升模型性能，LGT-RS 融合了一個針對商品、用戶和主播的統一詞嵌入空間。LGT-RS 的有效性通過在台灣直播電商平台真實世界數據集上的大量實驗得到了驗證。結果表明，LGT-RS 在 topK 推薦和鏈接預測任務上的性能優於其他幾個基準模型。本研究通過解決複雜三方關係、快速變化的用戶偏好以及數據集中有限的特徵等挑戰，推進了直播電商推薦系統的發展。
The rapid growth of livestreaming e-commerce (live commerce) poses new challenges for recommender systems (RSs), necessitating the modeling of complex tripartite relationships among users, items, and streamers and capturing user preferences change properly. This study introduces a novel Live commerce Graphical Time-aware Recommender System (LGT-RS) to address these challenges. LGT-RS leverages Graph Convolutional Networks (GCNs) to model the complex relationships between users, items, and streamers, and incorporates a time encoding method to capture the dynamic evolution of user preferences over time. Furthermore, to enhance data richness and improve model performance, LGT-RS integrates a unified word embedding space for items, users, and streamers. The effectiveness of LGT-RS is validated through extensive experiments on a real-world dataset from a Taiwanese live commerce platform. The results demonstrate LGT-RS's superior performance compared to several baseline models in topK recommendation and link prediction tasks.
參考文獻 Chang, J., Gao, C., He, X., Jin, D., & Li, Y. (2021). Bundle recommendation and generation with graph neural networks. IEEE Transactions on Knowledge and Data Engineering, 35(3), 2326–2340. Fan, W., Ma, Y., Li, Q., He, Y., Zhao, E., Tang, J., & Yin, D. (2019). Graph neural networks for social recommendation. The world wide web conference, 417–426. Favale, T., Soro, F., Trevisan, M., Drago, I., & Mellia, M. (2020). Campus traffic and e-learning during covid-19 pandemic. Computer networks, 176, 107290. Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in neural information processing systems, 30. He, X., Liao, L., Zhang, H., Nie, L., Hu, X., & Chua, T.-S. (2017). Neural collaborative filtering. Proceedings of the 26th international conference on world wide web, 173–182. Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. Kotnis, B., & Nastase, V. (2017). Analysis of the impact of negative sampling on link prediction in knowledge graphs. arXiv preprint arXiv:1708.06816. Liben-Nowell, D., & Kleinberg, J. (2003). The link prediction problem for social networks. Proceedings of the twelfth international conference on Information and knowledge management, 556–559. Lin, C.-Y., & Chen, H.-S. (2019). Personalized channel recommendation on live streaming platforms. Multimedia Tools and Applications, 78, 1999–2015. Liu, F., Cheng, Z., Zhu, L., Gao, Z., & Nie, L. (2021). Interest-aware message-passing gcn for recommendation. Proceedings of the Web Conference 2021, 1296–1305. Liu, Y.-W., Lin, C.-Y., & Huang, J.-L. (2015). Live streaming channel recommendation using hits algorithm. 2015 IEEE International Conference on Consumer Electronics- Taiwan, 118–119. Lu, Z., Annett, M., & Wigdor, D. (2019). Vicariously experiencing it all without going outside: A study of outdoor livestreaming in china. Proceedings of the ACM on Human-Computer Interaction, 3(CSCW), 1–28. Lu, Z., Xia, H., Heo, S., & Wigdor, D. (2018). You watch, you give, and you engage: A study of live streaming practices in china. Proceedings of the 2018 CHI conference on human factors in computing systems, 1–13. Mao, K., Xiao, X., Zhu, J., Lu, B., Tang, R., & He, X. (2020). Item tagging for information retrieval: A tripartite graph neural network based approach. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2327–2336. McInnes, L., Healy, J., & Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426. Menon, A. K., & Elkan, C. (2011). Link prediction via matrix factorization. Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2011, Athens, Greece, September 5-9, 2011, Proceedings, Part II 22, 437– 452. Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, 26. Nascimento, G., Ribeiro, M., Cerf, L., Cesário, N., Kaytoue, M., Raıssi, C., Vasconcelos, T., & Meira, W. (2014). Modeling and analyzing the video game live-streaming community. 2014 9th Latin American Web Congress, 1–9. Nitu, P., Coelho, J., & Madiraju, P. (2021). Improvising personalized travel recommendation system with recency effects. Big Data Mining and Analytics, 4(3), 139–154. Rappaz, J., McAuley, J., & Aberer, K. (2021). Recommendation on live-streaming platforms: Dynamic availability and repeat consumption. Proceedings of the 15th ACM Conference on Recommender Systems, 390–399.
 Salamat, A., Luo, X., & Jafari, A. (2021). Heterographrec: A heterogeneous graph-based neural networks for social recommendations. Knowledge-Based Systems, 217, 106817. Sun, Z., Li, X., Sun, X., Meng, Y., Ao, X., He, Q., Wu, F., & Li, J. (2021). Chinesebert: Chinese pretraining enhanced by glyph and pinyin information. arXiv preprint arXiv:2106.16038. Tian, Z., Liu, Y., Sun, J., Jiang, Y., & Zhu, M. (2021). Exploiting group information for personalized recommendation with graph neural networks. ACM Transactions on Information Systems (TOIS), 40(2), 1–23.
 Wang, M. Y. (2019). Deep graph library: Towards efficient and scalable deep learning on graphs. ICLR workshop on representation learning on graphs and manifolds. Xu, D., Ruan, C., Korpeoglu, E., Kumar, S., & Achan, K. (2020). Inductive representation learning on temporal graphs. arXiv preprint arXiv:2002.07962.
 Yang, T.-W., Shih, W.-Y., Huang, J.-L., Ting, W.-C., & Liu, P.-C. (2013). A hybrid preference-aware recommendation algorithm for live streaming channels. 2013 Conference on Technologies and Applications of Artificial Intelligence, 188–193.
 Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W. L., & Leskovec, J. (2018). Graph convolutional neural networks for web-scale recommender systems. Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, 974–983.
 Yu, S., Jiang, Z., Chen, D.-D., Feng, S., Li, D., Liu, Q., & Yi, J. (2021). Leveraging tripartite interaction information from live stream e-commerce for improving product recommendation. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 3886–3894. Zhang, C., Song, D., Huang, C., Swami, A., & Chawla, N. V. (2019). Heterogeneous graph neural network. Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 793–803. Zhang, M., Wu, S., Yu, X., Liu, Q., & Wang, L. (2022). Dynamic graph neural networks for sequential recommendation. IEEE Transactions on Knowledge and Data Engineering, 35(5), 4741–4753. Zhang, M., & Chen, Y. (2018). Link prediction based on graph neural networks. Advances in neural information processing systems, 31. Zheng, S., Chen, J., Liao, J., & Hu, H.-L. (2023). What motivates users’ viewing and purchasing behavior motivations in live streaming: A stream-streamer-viewer perspective. Journal of Retailing and Consumer Services, 72, 103240. Zhou, C., Bai, J., Song, J., Liu, X., Zhao, Z., Chen, X., & Gao, J. (2018). Atrank: An attention-based user behavior modeling framework for recommendation. Proceedings of the AAAI conference on artificial intelligence, 32(1). Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020). Graph neural networks: A review of methods and applications. AI open, 1, 57–81.
描述 碩士
國立政治大學
資訊管理學系
111356033
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0111356033
資料類型 thesis
dc.contributor.advisor 林怡伶<br>蕭舜文zh_TW
dc.contributor.advisor Lin, Yi-Ling<br>Hsiao, Shun-Wengen_US
dc.contributor.author (Authors) 廖偉丞zh_TW
dc.contributor.author (Authors) Liao, Wei-Chengen_US
dc.creator (作者) 廖偉丞zh_TW
dc.creator (作者) Liao, Wei-Chengen_US
dc.date (日期) 2024en_US
dc.date.accessioned 4-Sep-2024 14:05:20 (UTC+8)-
dc.date.available 4-Sep-2024 14:05:20 (UTC+8)-
dc.date.issued (上傳時間) 4-Sep-2024 14:05:20 (UTC+8)-
dc.identifier (Other Identifiers) G0111356033en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/153158-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊管理學系zh_TW
dc.description (描述) 111356033zh_TW
dc.description.abstract (摘要) 直播電子商務 (live commerce) 的快速發展，對推薦系統 (RSs) 帶來了新的挑戰，需要建模用戶、商品和主播之間複雜的三方關係，並適當捕捉用戶偏好的變化。本研究提出了一種新的直播電子商務圖形時間感知推薦系統 (LGT-RS) 來應對這些挑戰。LGT-RS 利用圖卷積網絡 (GCNs) 來建模用戶、商品和主播之間的複雜關係，並結合了時間編碼方法來捕捉用戶偏好隨時間的動態演變。此外，為豐富數據並提升模型性能，LGT-RS 融合了一個針對商品、用戶和主播的統一詞嵌入空間。LGT-RS 的有效性通過在台灣直播電商平台真實世界數據集上的大量實驗得到了驗證。結果表明，LGT-RS 在 topK 推薦和鏈接預測任務上的性能優於其他幾個基準模型。本研究通過解決複雜三方關係、快速變化的用戶偏好以及數據集中有限的特徵等挑戰，推進了直播電商推薦系統的發展。zh_TW
dc.description.abstract (摘要) The rapid growth of livestreaming e-commerce (live commerce) poses new challenges for recommender systems (RSs), necessitating the modeling of complex tripartite relationships among users, items, and streamers and capturing user preferences change properly. This study introduces a novel Live commerce Graphical Time-aware Recommender System (LGT-RS) to address these challenges. LGT-RS leverages Graph Convolutional Networks (GCNs) to model the complex relationships between users, items, and streamers, and incorporates a time encoding method to capture the dynamic evolution of user preferences over time. Furthermore, to enhance data richness and improve model performance, LGT-RS integrates a unified word embedding space for items, users, and streamers. The effectiveness of LGT-RS is validated through extensive experiments on a real-world dataset from a Taiwanese live commerce platform. The results demonstrate LGT-RS's superior performance compared to several baseline models in topK recommendation and link prediction tasks.en_US
dc.description.tableofcontents 1 Introduction 1 2 Related Work 4 2.1 Live Streaming Recommender System 4 2.2 Graph-based Recommender Systems 5 2.3 Time Encoding Methods in Graph Neural Network 6 2.4 Link Prediction based on Graph 7 3 Methodology 8 3.1 Notations and Problem Definition 9 3.2 Overview of Proposed Method 11 3.3 User, Item, and Streamer Embedding Initialization 11 3.4 Time Encoding Method 12 3.5 Convolutional Layer 13 3.6 Neighbor Sampling and Negative Sampling 15 3.6.1 Neighbor Sampling 15 3.6.2 Negative Sampling 16 3.7 Model Prediction and Optimization 17 4 Experiments 19 4.1 Dataset 19 4.2 Experiment Settings 20 4.2.1 Environment 20 4.2.2 Hyperparameters 20 4.2.3 Evaluation Metrics 21 4.2.4 Baselines 22 4.3 Experiment Results 23 4.3.1 Overall Performance and Ablation Study 23 4.3.2 Visualizing The Significance of Modeling Tripartite Relationships 25 4.3.3 Visualizing The Significance of Integrating Temporal Information 28 5 Conclusions 34 6 Limitation and Future Work 35 Reference 36zh_TW
dc.format.extent 3680904 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0111356033en_US
dc.subject (關鍵詞) 直播電商zh_TW
dc.subject (關鍵詞) 圖神經網絡zh_TW
dc.subject (關鍵詞) 時間感知zh_TW
dc.subject (關鍵詞) 推薦系統zh_TW
dc.subject (關鍵詞) Live Commerceen_US
dc.subject (關鍵詞) GNNen_US
dc.subject (關鍵詞) Time-awareen_US
dc.subject (關鍵詞) Recommender Systemen_US
dc.title (題名) 於直播電商環境下結合時間因素基於圖卷積網絡的推薦系統zh_TW
dc.title (題名) Leveraging the Tripartite Relationships with Livestreaming E-Commerce Graphical Time-aware Recommender Systemen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) Chang, J., Gao, C., He, X., Jin, D., & Li, Y. (2021). Bundle recommendation and generation with graph neural networks. IEEE Transactions on Knowledge and Data Engineering, 35(3), 2326–2340. Fan, W., Ma, Y., Li, Q., He, Y., Zhao, E., Tang, J., & Yin, D. (2019). Graph neural networks for social recommendation. The world wide web conference, 417–426. Favale, T., Soro, F., Trevisan, M., Drago, I., & Mellia, M. (2020). Campus traffic and e-learning during covid-19 pandemic. Computer networks, 176, 107290. Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in neural information processing systems, 30. He, X., Liao, L., Zhang, H., Nie, L., Hu, X., & Chua, T.-S. (2017). Neural collaborative filtering. Proceedings of the 26th international conference on world wide web, 173–182. Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. Kotnis, B., & Nastase, V. (2017). Analysis of the impact of negative sampling on link prediction in knowledge graphs. arXiv preprint arXiv:1708.06816. Liben-Nowell, D., & Kleinberg, J. (2003). The link prediction problem for social networks. Proceedings of the twelfth international conference on Information and knowledge management, 556–559. Lin, C.-Y., & Chen, H.-S. (2019). Personalized channel recommendation on live streaming platforms. Multimedia Tools and Applications, 78, 1999–2015. Liu, F., Cheng, Z., Zhu, L., Gao, Z., & Nie, L. (2021). Interest-aware message-passing gcn for recommendation. Proceedings of the Web Conference 2021, 1296–1305. Liu, Y.-W., Lin, C.-Y., & Huang, J.-L. (2015). Live streaming channel recommendation using hits algorithm. 2015 IEEE International Conference on Consumer Electronics- Taiwan, 118–119. Lu, Z., Annett, M., & Wigdor, D. (2019). Vicariously experiencing it all without going outside: A study of outdoor livestreaming in china. Proceedings of the ACM on Human-Computer Interaction, 3(CSCW), 1–28. Lu, Z., Xia, H., Heo, S., & Wigdor, D. (2018). You watch, you give, and you engage: A study of live streaming practices in china. Proceedings of the 2018 CHI conference on human factors in computing systems, 1–13. Mao, K., Xiao, X., Zhu, J., Lu, B., Tang, R., & He, X. (2020). Item tagging for information retrieval: A tripartite graph neural network based approach. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2327–2336. McInnes, L., Healy, J., & Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426. Menon, A. K., & Elkan, C. (2011). Link prediction via matrix factorization. Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2011, Athens, Greece, September 5-9, 2011, Proceedings, Part II 22, 437– 452. Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, 26. Nascimento, G., Ribeiro, M., Cerf, L., Cesário, N., Kaytoue, M., Raıssi, C., Vasconcelos, T., & Meira, W. (2014). Modeling and analyzing the video game live-streaming community. 2014 9th Latin American Web Congress, 1–9. Nitu, P., Coelho, J., & Madiraju, P. (2021). Improvising personalized travel recommendation system with recency effects. Big Data Mining and Analytics, 4(3), 139–154. Rappaz, J., McAuley, J., & Aberer, K. (2021). Recommendation on live-streaming platforms: Dynamic availability and repeat consumption. Proceedings of the 15th ACM Conference on Recommender Systems, 390–399.
 Salamat, A., Luo, X., & Jafari, A. (2021). Heterographrec: A heterogeneous graph-based neural networks for social recommendations. Knowledge-Based Systems, 217, 106817. Sun, Z., Li, X., Sun, X., Meng, Y., Ao, X., He, Q., Wu, F., & Li, J. (2021). Chinesebert: Chinese pretraining enhanced by glyph and pinyin information. arXiv preprint arXiv:2106.16038. Tian, Z., Liu, Y., Sun, J., Jiang, Y., & Zhu, M. (2021). Exploiting group information for personalized recommendation with graph neural networks. ACM Transactions on Information Systems (TOIS), 40(2), 1–23.
 Wang, M. Y. (2019). Deep graph library: Towards efficient and scalable deep learning on graphs. ICLR workshop on representation learning on graphs and manifolds. Xu, D., Ruan, C., Korpeoglu, E., Kumar, S., & Achan, K. (2020). Inductive representation learning on temporal graphs. arXiv preprint arXiv:2002.07962.
 Yang, T.-W., Shih, W.-Y., Huang, J.-L., Ting, W.-C., & Liu, P.-C. (2013). A hybrid preference-aware recommendation algorithm for live streaming channels. 2013 Conference on Technologies and Applications of Artificial Intelligence, 188–193.
 Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W. L., & Leskovec, J. (2018). Graph convolutional neural networks for web-scale recommender systems. Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, 974–983.
 Yu, S., Jiang, Z., Chen, D.-D., Feng, S., Li, D., Liu, Q., & Yi, J. (2021). Leveraging tripartite interaction information from live stream e-commerce for improving product recommendation. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 3886–3894. Zhang, C., Song, D., Huang, C., Swami, A., & Chawla, N. V. (2019). Heterogeneous graph neural network. Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 793–803. Zhang, M., Wu, S., Yu, X., Liu, Q., & Wang, L. (2022). Dynamic graph neural networks for sequential recommendation. IEEE Transactions on Knowledge and Data Engineering, 35(5), 4741–4753. Zhang, M., & Chen, Y. (2018). Link prediction based on graph neural networks. Advances in neural information processing systems, 31. Zheng, S., Chen, J., Liao, J., & Hu, H.-L. (2023). What motivates users’ viewing and purchasing behavior motivations in live streaming: A stream-streamer-viewer perspective. Journal of Retailing and Consumer Services, 72, 103240. Zhou, C., Bai, J., Song, J., Liu, X., Zhao, Z., Chen, X., & Gao, J. (2018). Atrank: An attention-based user behavior modeling framework for recommendation. Proceedings of the AAAI conference on artificial intelligence, 32(1). Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020). Graph neural networks: A review of methods and applications. AI open, 1, 57–81.zh_TW