《最新：以诊断学习困难为考量之测验和评量系统文档资料.ppt》由会员分享，可在线阅读，更多相关《最新：以诊断学习困难为考量之测验和评量系统文档资料.ppt（30页珍藏版）》请在三一办公上搜索。
1、1,Relevant Research,Gwo-Jen Hwang(2003),“A conceptual map for developing intelligent tutoring systems”,Computers&Education,Vol.40,No.3,pp.217-235.(SSCI)Gwo-Jen Hwang,Jia-Lin Hsiao and Judy C.R.Tseng(2003),“A Computer-Assisted Approach for Diagnosing Student Learning Problems in Science Courses”,Jour
2、nal of Information Science and Engineering,Vol.19,No.2,pp.229-248.(SCI Expanded,EI)Gwo-Jen Hwang(2005),“A Data Mining Approach to Diagnosis Student Learning Problems in Science Courses”,Journal of Distance Education Technologies,Vol.3,No.4,pp.35-50.(EI),2,A conceptual map for developing intelligent
3、tutoring systems(2003),Conventional testing systems simply give students a score,but dont give them the opportunity to learn how to improve their learning performance.Students would benefit more if the test results could be analyzed and hence advice could be provided accordingly.This study proposes
4、a conceptual map model,which provides learning suggestions by analyzing the subject materials and test results.,3,Concept Effect Relationships(CER),McAleese(1994,1998)indicated that students learn new concepts and new relationships among previously learned concepts.Salisbury(1998)that indicate the e
5、ffect of learning one concept on the learning of other concepts.ex:The names and abbreviations of chemical elements and their atomic weights must be thoroughly learned to comprehend scientific writings or chemical formulae.Such conceptual relation has been defined as“concept effect relationships”by
6、Hwang(2003).,4,Conventional subject materials Structure,Subject materials was viewed as a tree diagram comprising chapters,sections,sub-sections and key concepts to be learned.,5,New Structure:Concept effect Relationships,conceptual mappreviously learned conceptsHi-level concepts,Next,how to get the
7、“Concept effect graphs”?,6,Concept effect table(CET),Two-dimensional table.If CET(Ci,Cj)=1,it is said that Ci is one of the prerequisites of Cj.,“Division”的prerequisites concepts(NPj)=2,Positive integers,SubtractionMultiplication,7,ER(C1)ER(C2)ER(C3),Illustrative example of a test item relationship
8、table(TIRT),wrong,wrong,wrong,wrong,TIRT(Qi,Cj):ranging from 05,0:no relationshipsSUN(Cj):total strange of Cj,(Cj),-,8,Concept effect graph,=The acceptable error rateER(Cj):Add in“To-Be-Enhanced learning path”:average error ratio of Cj for the students who get the bottom 50%of test scores.,=0.55,9,P
9、ATH 3:Addition Multiplication Division Prime numbersWeight=Max(ER(C3),ER(C7),ER(C9),ER(C10)=1.0,PATH 1:Addition SubtractionNegative integersWeight=Max(ER(C3),ER(C6),ER(C8)=0.8,PATH 2:Addition Subtraction Division Prime numbersWeight=Max(ER(C3),ER(C6),ER(C9),ER(C10)=1.0,C1,C9,C8,C7,C6,C2,C4,C5,C3,C10
10、,最關鍵的補救路徑：PATH 2&PATH 3=Max Weight,10,Fuzzy output for learning guidance,Fuzzy sets on ER(Cj),0.3,0.55,0.2,ER(C1)=0.16,ER(C1)=0.16 Very well-learned0.3Well-learned0.55More or less well-learned0.2,11,Illustrative example of a learning guidance(To Student),misunderstood concepts“Addition”,Subtraction,
11、Negative integers,Division,Multiplication and Prime numbers,12,Comments for the student,Comments for the student:1.According to the diagnosis from the system,we found that you have misunderstood concepts Subtraction,Negative integers,Division,Multiplication and Prime numbers,which perhaps results fr
12、om the misunderstanding of Addition.In other words,the major learning problem of yours is the misunderstanding of concept Addition,which affects the learning of other concepts.Suggestion:enhance the study in Addition Subtraction Division Prime numbers and Addition Multiplication Division Prime numbe
13、rs sequences.,PATH 2,PATH 3,13,Practical Example,14,Intelligent testing and diagnostic system(ITES),Windows NT platform.CLIPS format.(a well-known expert system shell developed by NASA(Giarratano&Riley,1989)ITES comprises:student profile databaseitem bankJava-based interfacetesting and diagnostic un
14、itfuzzy interface.,15,Experiment,Experiment period:2001.9.2001.12.(3 months)Material:An elementary schools natural science course.Conditions:The same teacherSixty K-6 students from two classesGroup-A(Control group):30 students,received regular on-line tutoringtesting without learning guidanceGroup-B
15、(Experimental group):30 studentsreceived regular on-line tutoringlearning suggestions and relevant homework,16,Pre-test,樣本變異數同質性t檢定,t-test=0.05,t(29)=1.699,Group-AGroup-BGroup diff.(1-2),Grade Pooled Equal 58 2.32Grade Satterthwaite Unequal 56.7 2.32,Variable Method Variances df t Value,Equality of
16、variances,Grade Folded F 29 29 1.36 0.4079,Group A Group B:performanceof Groups A and B in the pre-test differs significantly.,Variable Method Num df Den df F value Pr F,t2.32 t(=.05)1.699the performance of Groups A and B in the pre-test differs significantly,17,Post-test,t-test=0.05,t(29)=1.699,Gro
17、up-AGroup-BGroup diff.(1-2),GRADE Pooled Equal 58-2.47GRADE Satterthwaite Unequal 56.7-2.47,Variable Method Variances df t Value,Equality of variances,Grade Folded F 29 29 1.95 0.0782,Variable Method Num df Den df F value Pr F,Group B Group A:performanceof Groups A and B in the post-test differs sig
18、nificantly.,t2.47 t(=.05)1.699a significant difference between the performance of Groups B and A,18,A graphical user interface is provided for constructing the conceptual effect graph,19,A Computer-Assisted Approach for Diagnosing Student Learning Problems in Science Courses(2003,SCI Expanded,EI),Un
19、familiar with computer programming,time-consuming,friendly user interface for teachers to apply it unaided.CER Generator:Generating concept effect relationships based on previous records of student answer sheets,20,CER-builder-Define support/belief values to generate a set of CER,21,The generated CE
20、R can be edited by the teacher,22,Physics course,The final concept effect graph with support=0.2 and belief=0.9.,Fig.8.Percentage of concepts involved in the concept effect relationships of the Physics course.,23,Evaluation of the Efficacy of the CER Builder,Experimental period:March 2001 to June 20
21、01.Material:Natural Science course at an elementary school60 studentsGroup A(Control group)(V1):received regular on-line testing without learning guidance.Group B(experimental group)(V2):received learning suggestions and relevant homework after each on-line test.Pre-test,post-test:The statistical re
22、sults obtained by applying SPSS.,24,Post-test&Pre-test,p-value(Sig.2-tailed)=.024(=.01)=Ho成立the mean score of Group A=Group B.,p-value(Sig.2-tailed)=.009 Ho不成立the mean score of Group B Group A,25,A Data Mining Approach to Diagnosis Student Learning Problems in Science Courses(2005,Journal of Distanc
23、e Education Technologies),A data mining approach that is capable of assisting teachers to provide information needed for guiding students during the learning process.Data Mining for Constructing Concept-Effect Relationships.Input Data-Answer Sheet Summary Table,26,27,Similar experimental results hav
24、e been derived on three courses,28,Evaluation for efficacy of the data mining approach,29,Conclusion,This study proposes a conceptual map method for modeling the prerequisite relationships among concepts to be learned.Several experiments have been conducted,which indicate that the group of students
25、who received the learning guidance can make significant progress compared with the control group.Two different approaches have been proposed to assist the teachers in constructing the concept-effect relationships.More experiments on Social Science or Language courses might be interesting,Thank you for your attention!,
