臺灣博碩士論文加值系統

隨著網際網路的快速發展，網路人力銀行已經成為主要的求職管道之一，然而使用人力銀行網站查詢理想工作所得到結果往往太多並且大多無法符合使用者真正的需求，使用者必須要花費許多時間去檢視符合自己理想的項目，因此，推薦系統因應而生，但是推薦系統仍存有一些限制，首先，在使用初期，推薦系統通常無法準確掌握使用者偏好而導致推薦項目完全不符合使用者的需求，其次，推薦系統對於使用者回饋具有高度依賴姓，若使用者不願花費額外時間提供回饋資訊，推薦項目很可能就無法達到高正確率。因此，本研究以人力銀行為目標，如104人力銀行、1111人力銀行等，提出針對線上求職的混合式回饋推薦系統架構，結合隱性和顯性的回饋資訊分析技術，對使用者履歷進行使用者偏好分析，並給予權重分配，產生初期推薦項目，此外，還提出一項新的資料探勘(Data Mining)技術名為JSS-Tree(Job Seeking Searching Tree)，尋找其他與使用者有相似偏好的使用者，將那些具有相似偏好使用者所感興趣的工作項目作為另一種選擇給當前使用者參考。最後將使用者最終選擇的推薦結果作為回饋資訊，為推薦系統進行校正，並減少使用者為尋找理想工作所花費的時間。

Recommender systems have been widely used in many fields, but most of them have high dependency on user's feedbacks to revise recommended options. To job seeker, the recommended mechanism of Job Bank is various, the results of matching profile and corporate recruitment conditions are usually unable to meet both job seeker's preferences and corporate’s requirement. The large database usually waste job seekers much time to search the ideal jobs. Therefore, we proposed a Hybrid Feedback Recommender System for a job seeker. Using Hybrid Feedback Technique to analyze user's preferences by portfolio and a new data mining technique for job bank websites called JSS-Tree (Job Seeking Searching Tree) to find the correlation about job searching of different users and active user. By Hybrid Feedback Recommender System can reduce the time of users searching ideal jobs and the system could have better recommendation results provide the user selects.

目錄
摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 6
表目錄 7
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 1
第二章 相關文獻探討 3
2.1 人力銀行網站 3
2.2 推薦系統 5
2.3 資料探勘 8
第三章 研究方法與過程 13
3.1 求職資料 14
3.2 資料預處理 15
3.3 推薦分析 16
3.3.1 使用者履歷 17
3.3.2 工作職缺 18
3.3.3 條件篩選 19
3.4 推薦計算 20
3.4.1 使用者個人偏好計算 20
3.4.2 使用者相似偏好計算 21
3.5 推薦結果 26
第四章 實驗與結果分析 27
4.1 個人偏好計算實驗 27
4.2 使用者間相似偏好計算實驗 30
第五章 結論 36
參考文獻 38

參考文獻
[1]財團法人資訊工業策進會 數位服務創新研究所: 我國網際網路用戶數調查, "http://www.find.org.tw/market_info.aspx?n_ID=8510"
[2]iThome電週文化事業: 網路求職調查：6成受訪者認為人力網會取代傳統求職媒介, "https://www.ithome.com.tw/node/10456"
[3]創市際市場研究顧問: ARO觀察：就業網站使用狀況, "http://www.ixresearch.com/web-traffic/aro%e8%a7%80%e5%af%9f%e5%b0%b1%e6%a5%ad%e7%b6%b2%e7%ab%99%e4%bd%bf%e7%94%a8%e7%8b%80%e6%b3%81-2/"
[4]創市際市場研究顧問: ARO觀察:不同世代就業網站使用概況, "http://www.ixresearch.com/web-traffic/aro%e8%a7%80%e5%af%9f%e4%b8%8d%e5%90%8c%e4%b8%96%e4%bb%a3%e5%b0%b1%e6%a5%ad%e7%b6%b2%e7%ab%99%e4%bd%bf%e7%94%a8%e6%a6%82%e6%b3%81/"
[5]Francesco Ricci, Lior Rokach, and Bracha Shapira, “Introduction to Recommender Systems Handbook”, springer, pp 1-35, 2011.
[6]Robin Burke, “Hybrid recommender systems: survey and experiments”, User Modeling and User-Adapted Interaction, 2002.
[7]Dr. Sarika Jain, Anjali Grover, Praveen Singh Thakur, Sourabh Kumar Choudhary, “Trends, Problems And Solutions of Recommender System”, International Conference on Computing, Communication and Automation (ICCCA2015), 2015.
[8]M . Tim Jones, “Introduction to Approaches And Algorithms of Recommender System”, 12 December 2013.
[9]Tessy Badriyah, Sefryan Azvy, Wiratmoko Yuwono and Iwan Syarif, “Recommendation system for property search using content based filtering method”, 2018 International Conference on Information and Communications Technology (ICOIACT), 2018.
[10]Frances A. Santos, Diego O. Rodrigues, Thiago H. Silva, Antonio A. F. Loureiro, Richard W. Pazzi, Leandro A. Villas, “Context-Aware Vehicle Route Recommendation Platform: Exploring Open and Crowdsourced Data”, 2018 IEEE International Conference on Communications (ICC), 2018.
[11]Masupha Lerato, Omobayo A. Esan, Ashley-Dejo Ebunoluwa, SM Ngwira, Tranos Zuva, “A survey of recommender system feedback techniques, comparison and evaluation metrics”, Computing, Communication and Security (ICCCS), 2015.
[12]Ameera M. Almasoud, Hend S. Al-Khalifa, Abdulmalik Al-Salman, “Recent Developments in Data Mining Applications and Techniques”, Digital Information Management (ICDIM), 2015.
[13]Adil Jad Allah Eddib, El Mohajir Mohammed, Mohamed Chahhou, “Algorithms and systems for data mining: A survey”, 2014 Third IEEE International Colloquium in Information Science and Technology (CIST), 2014.
[14]Chatklaw Jareanpon, Waranyoo Kiatjindarat, Thanawat Polhome, Kittiya Khongkraphan, “Automatic lyrics classification system using text mining technique”, 2018 International Workshop on Advanced Image Technology (IWAIT), 2018.
[15]A. Raharto Condrobimo, Bahtiar Saleh Abbas, Agung Trisetyarso, Wayan Suparta, Chul-Ho Kang, “Data mining technique with cluster anaysis use K-means algorithm for LQ45 index on Indonesia stock exchange”, 2018 International Conference on Information and Communications Technology (ICOIACT), 2018.
[16]J. Han, M, Kamber, J. Pei, “data mining concepts and techniques”, Third Edition, Elsevier 2012.
[17]Maral Kolahka, Madjid Khalilian, “A recommender system by using classification based on frequent pattern mining and J48 algorithm”, 2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI), 2015.
[18]Jiawei Han, Jian Pei, and Yiwen Yin, “Mining Frequent Patterns without Candidate Generation”, Proceedings of the 2000 ACM SIGMOD international conference on Management of data, 2000.
[19]Faezeh Movahedi, Yiye Zhang, Rema Padman, James F. Antaki, “Mining Temporal Patterns from Sequential Healthcare Data” 2018 IEEE International Conference on Healthcare Informatics (ICHI). 2018.
[20]Hoang Thi Hong Van, Vo Thi Ngoc Chau, Nguyen Hua Phung, “An expanded prefix tree-based mining algorithm for sequential pattern maintenance with deletions”, 2017 2nd International conferences on Information Technology, Information Systems and Electrical Engineering (ICITISEE), 2017.