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

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 運用知識圖於公務人員的課程推薦
Course Recommendation for Civil Servant Based on Knowledge Graph
作者 謝政彥
Hsieh, Cheng-Yen
貢獻者 沈錳坤
Shan, Man-Kwan
謝政彥
Hsieh, Cheng-Yen
關鍵詞 課程推薦
知識圖
公務人員
Course Recommendation
Knowledge Graph
Civil Servant
日期 2024
上傳時間 1-Mar-2024 13:40:16 (UTC+8)
摘要 公務人員為推動國家政策、提升國家競爭力，本職學能必須與時俱進。但公務人員每年在職研習的時間與次數有限，因此若能透過課程推薦技術，將可協助公務人員有效地選讀相關訓練課程。 然而公務人員在數十年公務生涯中，會歷經不同服務機關、職等、職務等歷練，教育程度及年齡也會改變，因此課程推薦需考慮公務人員修課時背景，包括職務相關背景及影響喜好相關背景。而且一般成人學習的習慣是希望透過理解找到答案，因此課程推薦須具備可解釋性方能有效協助公務人員理解並進行選課決策。 針對商品的推薦，現已有分別考慮情境背景或具備可解釋性的推薦技術。但較少有兩者兼具的研究。本研究提出一個運用知識圖的公務人員研習背景課程圖，並結合長短期記憶模型的推薦模型。此模型考量公務人員歷年的公務相關背景及個人人口統計背景。經實驗顯示本論文所提出的課程推薦模型，準確率極高且具有可解釋性。
In order to promote national policies and enhance national competitiveness, civil servants must keep pace with the times in their professional skills. However, the opportunities for job training in terms of time and frequency are limited for civil servants each year. Therefore, if course recommendation technology could be utilized, it could assist civil servants in effectively selecting relevant training courses. Over the decades-long career of a civil servant, they will experience different service institutions, ranks, and positions. Their education level and age will also change. Therefore, course recommendations need to take into account the background of civil servants, including job-related background and demographic background that affects preferences. Moreover, course recommendations must be explainable to effectively assist civil servants in understanding and making course selection decisions. Currently there are recommendation techniques that consider context or are explainable for product recommendation, but there is little research to have both. This thesis proposes a Civil-servant Profile Course Graph based on knowledge graph and integrated with the LSTM recommendation model. The proposed model makes recommendation by taking the job-related background and personal demographic background of civil servants into account. Experiments show that the proposed approach is highly accurate and explainable.
參考文獻 [1] L. Anitha, M. K. Devi, and P. A. Devi, A Review on Recommender System. International Journal of Computer Applications, Vol. 82, No. 3, 2013. [2] D. V. Bagul, and S. Barve, A Novel Content-based Recommendation Approach Based on LDA Topic Modeling for Literature Recommendation. IEEE 6th International Conference on Inventive Computation Technologies (ICICT), 2021. [3] Y. Cao, X. Wang, X. He, Z. Hu, and T. S. Chua, Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences. The World Wide Web Conference, 2019. [4] R. Chen, Q. Hua, Y. S. Chang, B. Wang, L. Zhang, and X. Kong, A Survey of Collaborative Filtering-based Recommender Systems: From Traditional Methods to Hybrid Methods Based on Social Networks. IEEE Access, Vol. 6, 2018. [5] G. Durand, N. Belacel, and F. LaPlante, Graph Theory Based Model for Learning Path Recommendation. Information Sciences, Vol. 251, 2013. [6] D. B. Guruge, R. Kadel, and S. J. Halder, The State of the Art in Methodologies of Course Recommender Systems— A Review of Recent Research. Data, Vol. 6, No. 2, 2021. [7] Y. Hu, Y. Koren, and C. Volinsky, Collaborative Filtering for Implicit Feedback Datasets. IEEE 8th International Conference on Data Mining, 2008. [8] M. R. Islam, M. U. Ahmed, S. Barua, and S. Begum, A Systematic Review of Explainable Artificial Intelligence in Terms of Different Application Domains and Tasks. Applied Sciences, Vol. 12, No. 3, 2022. [9] U. Javed, K. Shaukat, I. A. Hameed, F. Iqbal, T. M. Alam, and S. Luo, A Review of Content-based and Context-based Recommendation Systems. International Journal of Emerging Technologies in Learning, Vol. 16, No. 3, 2021. [10] E. S. Khorasani, Z. Zhenge, and J. Champaign, A Markov Chain Collaborative Filtering Model for Course Enrollment Recommendations. 2016 IEEE International Conference on Big Data, 2016. [11] X. Luo, M. Zhou, Y. Xia, and Q. Zhu, An Efficient Non-negative Matrix-factorization-based Approach to Collaborative Filtering for Recommender Systems. IEEE Transactions on Industrial Informatics, Vol. 10, No. 2, 2014. [12] A. H. Nabizadeh, D. Goncalves, S. Gama, J. Jorge, and H. N. Rafsanjani, Adaptive Learning Path Recommender Approach Using Auxiliary Learning Objects. Computers & Education, Vol. 147, 2020. [13] A. H. Nabizadeh, J. P. Leal, H. N. Rafsanjani, and R. R. Shah, Learning Path Personalization and Recommendation Methods: A Survey of the State-of-the-art. Expert Systems with Applications, Vol. 159, 2020. [14] O. N. Osmanlı, A Singular Value Decomposition Approach for Recommendation Systems. Master's Thesis, Middle East Technical University, 2010. [15] A. Polyzou, A. N. Nikolakopoulos, and G. Karypis, Scholars Walk: A Markov Chain Framework for Course Recommendation. The 12th International Conference on Educational Data Mining, 2019. [16] S. Sharma, V. Rana, and M. Malhotra, Automatic Recommendation System Based on Hybrid Filtering Algorithm. Education and Information Technologies, Vol. 27, No. 2, 2022. [17] C. Shi, Y. Li, J. Zhang, Y. Sun, and S. Y. Philip, A Survey of Heterogeneous Information Network Analysis. IEEE Transactions on Knowledge and Data Engineering, Vol. 29, No. 1, 2016. [18] X. Wang, D. Wang, C. Xu, X. He, Y. Cao, and T. S. Chua, Explainable Reasoning over Knowledge Graphs for Recommendation. The AAAI conference on artificial intelligence, Vol. 33, No. 1, 2019. [19] M. Wijewickrema, V. Petras, and N. Dias, Selecting a Text Similarity Measure for a Content-based Recommender System: A Comparison in Two Corpora. The Electronic Library, Vol. 37, No. 3, 2019. [20] Y. Xian, Z. Fu, S. Muthukrishnan, G. De Melo, and Y. Zhang, Reinforcement Knowledge Graph Reasoning for Explainable Recommendation. The 42th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019. [21] Y. Zhang, and X. Chen, Explainable Recommendation: A Survey and New Perspectives. Foundations and Trends® in Information Retrieval, Vol. 14, No. 1, 2020. [22] 陳雪雲，社區導向之積極公民身分學習-從非正規到非正式反思學習。中華民國成人暨終身教育學會編，非正規學習：151-182。北市：師大書苑，2005。
描述 碩士
國立政治大學
資訊科學系
109753207
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0109753207
資料類型 thesis
dc.contributor.advisor 沈錳坤zh_TW
dc.contributor.advisor Shan, Man-Kwanen_US
dc.contributor.author (Authors) 謝政彥zh_TW
dc.contributor.author (Authors) Hsieh, Cheng-Yenen_US
dc.creator (作者) 謝政彥zh_TW
dc.creator (作者) Hsieh, Cheng-Yenen_US
dc.date (日期) 2024en_US
dc.date.accessioned 1-Mar-2024 13:40:16 (UTC+8)-
dc.date.available 1-Mar-2024 13:40:16 (UTC+8)-
dc.date.issued (上傳時間) 1-Mar-2024 13:40:16 (UTC+8)-
dc.identifier (Other Identifiers) G0109753207en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/150164-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學系zh_TW
dc.description (描述) 109753207zh_TW
dc.description.abstract (摘要) 公務人員為推動國家政策、提升國家競爭力，本職學能必須與時俱進。但公務人員每年在職研習的時間與次數有限，因此若能透過課程推薦技術，將可協助公務人員有效地選讀相關訓練課程。 然而公務人員在數十年公務生涯中，會歷經不同服務機關、職等、職務等歷練，教育程度及年齡也會改變，因此課程推薦需考慮公務人員修課時背景，包括職務相關背景及影響喜好相關背景。而且一般成人學習的習慣是希望透過理解找到答案，因此課程推薦須具備可解釋性方能有效協助公務人員理解並進行選課決策。 針對商品的推薦，現已有分別考慮情境背景或具備可解釋性的推薦技術。但較少有兩者兼具的研究。本研究提出一個運用知識圖的公務人員研習背景課程圖，並結合長短期記憶模型的推薦模型。此模型考量公務人員歷年的公務相關背景及個人人口統計背景。經實驗顯示本論文所提出的課程推薦模型，準確率極高且具有可解釋性。zh_TW
dc.description.abstract (摘要) In order to promote national policies and enhance national competitiveness, civil servants must keep pace with the times in their professional skills. However, the opportunities for job training in terms of time and frequency are limited for civil servants each year. Therefore, if course recommendation technology could be utilized, it could assist civil servants in effectively selecting relevant training courses. Over the decades-long career of a civil servant, they will experience different service institutions, ranks, and positions. Their education level and age will also change. Therefore, course recommendations need to take into account the background of civil servants, including job-related background and demographic background that affects preferences. Moreover, course recommendations must be explainable to effectively assist civil servants in understanding and making course selection decisions. Currently there are recommendation techniques that consider context or are explainable for product recommendation, but there is little research to have both. This thesis proposes a Civil-servant Profile Course Graph based on knowledge graph and integrated with the LSTM recommendation model. The proposed model makes recommendation by taking the job-related background and personal demographic background of civil servants into account. Experiments show that the proposed approach is highly accurate and explainable.en_US
dc.description.tableofcontents 致謝 i 摘要 ii Abstract iii 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機 2 1.3 研究目的 3 第二章 文獻研究 4 2.1 推薦系統 4 2.2 課程推薦 8 第三章 研究方法 12 3.1 知識圖 12 3.2 研究架構 14 3.3 建立公務人員研習背景課程圖 15 3.4 訓練推薦模型 18 3.5 產出推薦課程 22 第四章 實驗設計 23 4.1 資料集 23 4.2 實驗步驟 24 4.2.1 建立公務人員研習背景課程圖 24 4.2.2 路徑萃取 32 4.2.3 訓練mKPRN 模型 33 4.2.4 模型評估 35 4.3 實驗結果 37 4.3.1 訓練損失值及驗證損失值 37 4.3.2 模型評估 40 4.3.3 推薦課程可解釋性 44 第五章 結論與未來研究 48 5.1 結論 48 5.2 未來研究 49 參考文獻 50 附錄 53zh_TW
dc.format.extent 3204867 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0109753207en_US
dc.subject (關鍵詞) 課程推薦zh_TW
dc.subject (關鍵詞) 知識圖zh_TW
dc.subject (關鍵詞) 公務人員zh_TW
dc.subject (關鍵詞) Course Recommendationen_US
dc.subject (關鍵詞) Knowledge Graphen_US
dc.subject (關鍵詞) Civil Servanten_US
dc.title (題名) 運用知識圖於公務人員的課程推薦zh_TW
dc.title (題名) Course Recommendation for Civil Servant Based on Knowledge Graphen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] L. Anitha, M. K. Devi, and P. A. Devi, A Review on Recommender System. International Journal of Computer Applications, Vol. 82, No. 3, 2013. [2] D. V. Bagul, and S. Barve, A Novel Content-based Recommendation Approach Based on LDA Topic Modeling for Literature Recommendation. IEEE 6th International Conference on Inventive Computation Technologies (ICICT), 2021. [3] Y. Cao, X. Wang, X. He, Z. Hu, and T. S. Chua, Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences. The World Wide Web Conference, 2019. [4] R. Chen, Q. Hua, Y. S. Chang, B. Wang, L. Zhang, and X. Kong, A Survey of Collaborative Filtering-based Recommender Systems: From Traditional Methods to Hybrid Methods Based on Social Networks. IEEE Access, Vol. 6, 2018. [5] G. Durand, N. Belacel, and F. LaPlante, Graph Theory Based Model for Learning Path Recommendation. Information Sciences, Vol. 251, 2013. [6] D. B. Guruge, R. Kadel, and S. J. Halder, The State of the Art in Methodologies of Course Recommender Systems— A Review of Recent Research. Data, Vol. 6, No. 2, 2021. [7] Y. Hu, Y. Koren, and C. Volinsky, Collaborative Filtering for Implicit Feedback Datasets. IEEE 8th International Conference on Data Mining, 2008. [8] M. R. Islam, M. U. Ahmed, S. Barua, and S. Begum, A Systematic Review of Explainable Artificial Intelligence in Terms of Different Application Domains and Tasks. Applied Sciences, Vol. 12, No. 3, 2022. [9] U. Javed, K. Shaukat, I. A. Hameed, F. Iqbal, T. M. Alam, and S. Luo, A Review of Content-based and Context-based Recommendation Systems. International Journal of Emerging Technologies in Learning, Vol. 16, No. 3, 2021. [10] E. S. Khorasani, Z. Zhenge, and J. Champaign, A Markov Chain Collaborative Filtering Model for Course Enrollment Recommendations. 2016 IEEE International Conference on Big Data, 2016. [11] X. Luo, M. Zhou, Y. Xia, and Q. Zhu, An Efficient Non-negative Matrix-factorization-based Approach to Collaborative Filtering for Recommender Systems. IEEE Transactions on Industrial Informatics, Vol. 10, No. 2, 2014. [12] A. H. Nabizadeh, D. Goncalves, S. Gama, J. Jorge, and H. N. Rafsanjani, Adaptive Learning Path Recommender Approach Using Auxiliary Learning Objects. Computers & Education, Vol. 147, 2020. [13] A. H. Nabizadeh, J. P. Leal, H. N. Rafsanjani, and R. R. Shah, Learning Path Personalization and Recommendation Methods: A Survey of the State-of-the-art. Expert Systems with Applications, Vol. 159, 2020. [14] O. N. Osmanlı, A Singular Value Decomposition Approach for Recommendation Systems. Master's Thesis, Middle East Technical University, 2010. [15] A. Polyzou, A. N. Nikolakopoulos, and G. Karypis, Scholars Walk: A Markov Chain Framework for Course Recommendation. The 12th International Conference on Educational Data Mining, 2019. [16] S. Sharma, V. Rana, and M. Malhotra, Automatic Recommendation System Based on Hybrid Filtering Algorithm. Education and Information Technologies, Vol. 27, No. 2, 2022. [17] C. Shi, Y. Li, J. Zhang, Y. Sun, and S. Y. Philip, A Survey of Heterogeneous Information Network Analysis. IEEE Transactions on Knowledge and Data Engineering, Vol. 29, No. 1, 2016. [18] X. Wang, D. Wang, C. Xu, X. He, Y. Cao, and T. S. Chua, Explainable Reasoning over Knowledge Graphs for Recommendation. The AAAI conference on artificial intelligence, Vol. 33, No. 1, 2019. [19] M. Wijewickrema, V. Petras, and N. Dias, Selecting a Text Similarity Measure for a Content-based Recommender System: A Comparison in Two Corpora. The Electronic Library, Vol. 37, No. 3, 2019. [20] Y. Xian, Z. Fu, S. Muthukrishnan, G. De Melo, and Y. Zhang, Reinforcement Knowledge Graph Reasoning for Explainable Recommendation. The 42th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019. [21] Y. Zhang, and X. Chen, Explainable Recommendation: A Survey and New Perspectives. Foundations and Trends® in Information Retrieval, Vol. 14, No. 1, 2020. [22] 陳雪雲，社區導向之積極公民身分學習-從非正規到非正式反思學習。中華民國成人暨終身教育學會編，非正規學習：151-182。北市：師大書苑，2005。zh_TW