運用分類技術分析學習行為與迷思概念的智慧系統

An Intelligent System Using Clustering Techniques for Analyzing Learning Behaviors and Misconceptions

鄭憲永(Shein-Yung Cheng)

指導教授 ： 賀嘉生

中原大學/工學院/電子工程研究所/博士(2006年)

https://doi.org/10.6840/CYCU.2006.00410

摘要

人們透過網路連結可以取得很多網路資源。分析使用者取得這些資源方式，可瞭解使用者的網路行為模式。本論文提出兩種使用者行為模式分析方法：行為模式與網站內容無關和網站內容相關。與網站內容無關分析方法利用狀態轉換圖(State Transition Graph)模式，純粹將使用者存取網路資源活動紀錄，做階層活動radix 編碼，針對使用者的活動編碼區分一連串行為。利用分類技術可以將使用者行為分成不同社群與子群組。這些社群與子群組透過行為狀態與轉換機率分析，就可以找出子社群間狀態轉換圖。與網站內容相關分析方法利用慨念階層建構出考題，來測驗使用者對教學網站內容所含慨念了解程度，根據使用者答題狀況，同樣利用分類技術，可以將使用者行為分成不同社群，用來掌握不同學生答題狀況群組，對於內容不了解類型，可以施不同的補充內容。
最後對於狀態轉換圖(STG)方法使用Aprior演算法產生測試資料，檢驗方法的可行性。再以實際教學網站資料，找出預測模型，並檢查模型的預測結果。在國中國文與大學實用英文兩個實際教學課程網站，運用慨念階層表示法測驗考卷，透過線上測驗，立即找出不同社群他們共同的迷失慨念，讓老師針對不同群組學生，調整個別群組教學內容，增加學生學習效率。

關鍵字

階層分類法 ； 狀態轉換圖 ； 使用者行為 ； 網際網路資源 ； 社群分類 ； 慨念圖 ； 學習診斷 ； 資料序列

並列摘要

The Internet enables all electronic information to be connected through communication networks. Users access these Internet resources with different behavior models. This dissertation has proposed two different user behavior model studies: content independent (STG model) and dependent (Concept Hierarchy). For STG model transform resource access actions into behavior models of state-transition graphs. A series of Internet resource access actions are stored in a database of [user, resource-access-action, time] records, indicating that the user accesses the resource at the recorded time. Such access actions are treated as basic behavior elements and form an action hierarchy which possesses different levels of radix codes. For every user, the data sequence is divided into a series of transactions, and all the actions in a transaction constitute a special behavior pattern, called (inter-transaction) behavior. The behavior codes can be aggregated from their action codes and then form a behavior hierarchy. Users can be classified into communities and subgroups by their aggregated behavior codes and behavior transitions. Each community and subgroup has its own behavior models, formulated as a state-transition graph with behavior states and transition probability between behaviors. From the Apriori Algorithm to State-Transition Graph, show how state-transition graphs can be found through the successive steps in AprioriAll algorithm. The second example applies this method to find the predictive models of a real distance education data set and checks the predictability of these models.
Based on the embedded concept hierarchy of a test sheet, this dissertation explores another possibility of using a hierarchical coding and analytical procedure to diagnosis individual and class learning and misconceptions. Concept hierarchy is constructed by the part-of and type-of relationships among concepts and represented with a hierarchical coding scheme. For a given test sheet, all the embedded concepts of the test items are used to transform the responses into an indicator of conceptual understanding and errors. Significant individual misconceptions may be identified using this technique and a data mining clustering algorithm may also be used to identify groups of students in a learning community who may share similar misconceptions. This approach has been integrated as a module into a previously-developed system and the analysis of two data sets from Chinese and English language courses are illustrative of the uses of this approach in distance education as well as a traditional classroom setting.

並列關鍵字

data sequencing ； learning diagnosis ； clustering ； hierarchical taxonomy ； community ； oncept map ； user behavior ； Internet resource ； state-transition graph

參考文獻

21. Heh J. S., Cheng S. Y. & Hsu C. K. (2005). Nested State-transition Graph Data Sequencing Model with Hierarchical Taxonomy through Radix Coding. Journal of Information Science and Engineering, 21(3), 579-605.

1. Advanced Distributed Learning Project, (2002). http://www.adlnet.org/.

4. Aho, A. V. & Corasick, M. J. (1975). Efficient string matching: an aid to bibliographic search. Communications of the ACM, 18(6), 333-340.

18. Grimaldi, R. P. (1994). Discrete and Combinatorial mathematics: an applied introduction. 3rd ed. (pp. 51-100). Massachusetts: Addison-Wesley.

19. Halbwachs, N. (1993) Synchronous Programming of Reactive Systems, Netherlands: Kluwer Academic.