隨著數位學習(E-learning)的盛行，讓學習已經不再受時間跟地點的限制，只要能上網就能進行學習，但也因為其方便性，使得參與課程的人數也遠超以往，評定成績的方式也因此需做了不同的調整，對於某些科目來說，是非、選擇、填空等題型是不恰當的，所以同儕互評(Peer Assessment)變成大型課程評定作業成績的一種方式。本研究將探討在大型課程中，學習者在評定他人作業的態度對整體同儕互評系統的影響，並對研究之模型做適當的調整，從信效度的角度對模型的結果進行分析，再提出從HITS演算法修改來的同儕互評模型，試圖以HITS演算法的精神，找出好的評分者、與不好的評分者，從中找出學習者在評定他人作業成績時胡亂給分的特徵，利用協同過濾進行分析，使同儕互評系統不因這些使用者而導致結果與真實狀況有極大的誤差，以提升系統的可信度。

With the popularity of E-learning, learning itself was no longer restricted by time and location, but available just with an accessible internet. Yet, due to its convenience, the average number of learners participated in an online course has become more than ever, and therefore homework assessment becomes a great challenge for instructors and require being adjusted accordingly. Amongst these adjustments, peer assessment is one of potential approaches applied to homework assessment in a large-scaled course. This study aims to explore the impact of learner’s attitude on Peer Assessment System, and accordingly makes appropriate adjustment based on the research result from the perspective of validity. And we intend to find out the features of the learners do the assessment in a random manner and use collaborative filtering to identify them with these features. With the identification of these learners, it is expected the Peer Assessment System would produce the results similar to those made by human experts, and hence increase its assessment reliability.

中文摘要 I
ABSTRACT II
誌　謝 III
目錄 IV
表目錄 V
圖目錄 VI
第一章 緒論 1
1.1研究動機與背景 1
1.2研究目的與問題 2
1.2.1研究目的 2
1.2.1研究問題 2
第二章 文獻探討 3
2.1同儕互評(PEER ASSESSMENT) 3
2.2網路學習的同儕互評 4
2.3協同過濾互評（COLLABORATIVE FILTERING） 5
2.4超連結引發之主題網頁檢索名次排序法（HYPERLINK-INDUCED TOPIC SEARCH） 8
第三章 研究方法 10
3.1協同過濾同儕互評測試 10
3.2協同過濾互評調整 12
3.3 HITS同儕互評 14
第四章 實驗設計 18
4.1實驗方法 18
4.1.1學生成績 18
4.2實驗結果與分析 19
4.2.1協同過濾同儕互評 19
4.2.2HITS同儕互評 21
4.2.3HITS同儕互評與Outlier的比較 24
4.2.4協同過濾搭配HITS同儕互評 25
4.2.5限制批改份數的同儕互評 26
第五章 結論 30
參考文獻 32

[1]于富雲、鄭守杰，"網路同儕互評與標準建構歷程對 國小學生後設認知影響的實證性研究，" 國立臺北師範學院學報，第十七卷第一期,頁197-226
[2]于富雲、鄭守杰、杜明璋、陳德懷，"網路同儕互評與評量標準來源對批判思考能力之影響，" 國立臺南師範學院「南師學報」第 37 卷第二期教育類,頁1-21
[3]沈慶珩、黃信義，" 網路同儕互評在Moodle系統上的應用," 教育資料與圖書館學43卷3期,頁267-284
[4]楊國鑫, 2001,推廣網路同儕互評系統於高級工業職業學校教學課程之研究。國立交通大學資訊科學研究所碩士論文
[5]Aleksandra Klasnja Milicevic , Alexandros Nanopoulos and Mirjana Ivanovic, "Social tagging in recommender systems: a survey of the state-of-the-art and possible extensions," Artificial Intelligence Review archive Volume 33, Issue 3, pp.187 - 209, March 2010.
[6]Andriy Shepitsen, Jonathan Gemmell, Bamshad Mobasher, and Robin Burke , "Personalized Recommendation in Social Tagging Systems Using Hierarchical Clustering," Proceedings of the 2008 ACM conference on Recommender systems, pp.259-266, 2008.
[7]Ammer, J. J. "Peer evaluation model for enhancing writing performance of students with learning disabilities," Reading ＆ Writing Quarterly, Volume 14, pp.263-282, 1998.
[8]A. Buda and A.Jarynowski, "Life-time of correlations and its applications," Andrzej Buda Wydawnictwo NiezaleĹĽne, pp.5–21, December 2010
[9]Chris Piech , Jonathan Huang , Zhenghao Chen , Chuong Do, Andrew Ng and Daphne Koller ,"Tuned Models of Peer Assessment in MOOCs, " Proceedings of The 6th International Conference on Educational Data Mining , Jul 2013.
[10]Frank Loll , Niels Pinkwart , "Using Collaborative Filtering Algorithms as eLearning Tools," Proceedings of the 42nd Hawaii International Conference on System Sciences, 2009.
[11]Fallows, S.and Chandramohan, B. "Multiple approaches to assessment: reflections on use of tutor, peer and self-assessment, " Teaching in Higher Education, Volume 6, Issue 2, pp.229-246, April 2001.
[12]Huizhi Liang, Yue Xu, Yuefeng Li, Richi Nayak and Xiaohui Tao , "Connecting Users and Items with Weighted Tags for Personalized Item Recommendations ," HT '10 Proceedings of the 21st ACM conference on Hypertext and hypermedia , pp.51-60 , 2010.
[13]J. Kleinberg. "Authoritative sources in a hyperlinked environment," Proc. 9th ACM-SIAM Symposium on Discrete Algorithms, 1998.
[14]Leandro Balby Marinho and Lars Schmidt-Thiem , "Collaborative Tag Recommendations," Proceedings of the 31st Annual Conference of the Gesellschaft für Klassifikation e.V., Albert-Ludwigs-Universität Freiburg, pp.533-540, March 7–9, 2007.
[15]Steve Cooper and Mehran Sahami , "Education Reflections on Stanford’s MOOCs," Communications of the ACM, Volume 56, No. 2 ,February 2013
[16]Stephan Trahasch , " Towards a Flexible Peer Assessment System , " Information Technology Based Higher Education and Training. ITHET Proceedings of the FIfth International Conference on, pp. 516-520, 2004
[17]Topping, K. J.. "Peer assessment between students in colleges and universities," Review of Educational Research, Vol.68, pp.249-276, 1998.
[18]Towler, L. and Broadfoot, P. “Self-assessment in the primary school,” Education Review, Volume 44, Issue 2, pp. 137-151, 1992.
[19]Xing Xing, Weishi Zhang, Zhichun Jia and Xiuguo Zhang, "Learning to Recommend Top-k Items in Online Social Networks," World Congress on Information and Communication Technologies, 2012.
[20]Xiufeng Xia , Shu Zhang and Xiaoming Li , " A Personalized Recommendation Model based on Social Tags," Database Technology and Applications (DBTA), 2nd International Workshop on , 2010.