With vigorous development of the Internet, e-learning system has become more and more popular. How to provide customized course according to individual learning characteristics and capability, and how to create the activity tree in SCORM 2004 with appropriate associated sequencing definition for different learners are two important issues. Thus, in this thesis, we propose a four phase Learning Portfolio Mining (LPM) Approach, which uses sequential pattern mining, clustering approach, and decision tree creation sequentially, to extract learning features from learning portfolio and to create a decision tree to predict which group a new learner belongs to.
Then, in the last Phase, we also propose an algorithm to create personalized activity tree which can be used in SCORM compliant learning environment.
Then, we implemented a prototype of LPM system and used this system to make an empirical experience at senior high school. The experimental results show that our proposed approach is feasible for those students. In addition, the results also show that our system provide more adaptive to learners and is accepted by most users. In other hand, we also get some suggests about our system and we can design other features to
enhance our LPM system.
In the near future, we will extend the user model definition and enhance our mining approach for providing learners with more personalized learning guidance.
Furthermore, we will enhance the experiment design and utilize statistic tools to verify the significant difference of our experiment. The mined learning patterns could also be further evaluated by the learning results of students. These statistics information could feed back to each phase of our mining approach. Finally, we will use the results to modify the parameters of each phase to provide more adaptivity environment to learners.
Bibliography:
[1] Apache Xerces, http://www.apache.org
[2] Sharable Content Object Reference Model (SCORM), http://www.adlnet.org
[3] W3C,http://www.w3.org
[4] R. Aggrawal and R. Srikant, “Mining Sequential Patterns”, International
Conference on Data Engineering(ICDE), 1996.
[5] S. Beekhoven, U.D. Jong and H.V. Hout, “Different Course, Different Students, Same Results? An Examination of Differences in Study Progress of Students in Different Courses”, Higher Education, Vol. 46, 2003, pp. 37-59.
[6] C.K. Chang, G. D. Chen and K. L. Ou ,“Student Portfolio Analysis for Decision Support of Web Based Classroom Teacher by Data Cube Technology”, Journal of Educational Computing Research, Vol. 19, No. 3, 1998.
[7] V. Carchiolo, A. Longheu and M. Malgeri, “Adaptive Formative Paths in a Web-Based Learning Environment”, Educational Technology & Society, Vol. 5, No. 4, 2002, pp. 64-75.
[8] G. D. Chen, C. C. Liu, K. L. Ou and B. J. Liu, “Discovering Decision Knowledge From Web Log Portfolio for Managing Classroom Processes by Applying
Decision Tree and Data Cube Technology”, Journal of Educational Computing
Research, Vol. 23, No. 3 , 2000, pp. 305-332.
[9] W. Chen, and R. Mizoguchi., “Communication Content Ontology for Learner Model Agent in Multi-agent Architecture”,Advanced Research in Computers and Communications in Education, Proc. ICCE'99, pp. 95-102.
[10] D.G. Dewhurst, H.A. Macleod and T.A.M. Norris, “Independent Student Learning Aded by Computers: An Acceptable Alternative to Lectures?”,
Computer and Education, Vol.35, 2000, pp. 223-241.
[11] S. Eugene, “The Relationship between Learning Style and Cognitive Style ”,
Personality and Individual Differences, Vol.30, 2001, pp. 609-616
[12] U. Fayyad, “Data Mining and Knowledge Discovery in Database: Implications for Scientific Databases”, Proceedings of Ninth International Conference on
Scientific and Statistical Database Management, 1997, pp. 2-11.
[13] T. Feng and M. Fionn, “Towards knowledge Discovery from WWW Log Data”,
Proceeding of the International Conference on Information Technology: Coding
and Computing, 2000.
[14] J.E. Gilbert and C.Y. Han, “Adapting Instruction in Search of ‘A Significant Difference’ ” , Journal of Network and Computer Application, Vol. 22, 1999, pp.
149-160.
[15] V. Guralnik and G. Kartpis, “A Scalable Algorithm for Clustering Sequential data”, Proceedings of the 2001 IEEE International Conference on Data Mining, 2001, pp. 179-186.
[16] D.J. Hall and G.B. Ball, "ISODATA : A Novel Nethod of Data Analysis and Pattern Classification", Technical report, Stanford Research Institute, Menlo park CA, 1965.
[17] D.A. Kolb, “Learning Style Inventory: Technical Manual”, Boston, Mass: McBer
originally published in 1976, 1985.
[18] D. McIlroy, B. Bunting, K. Tierney and M. Gordon, “The Relation of Gender and Background Experience to Self-reported Computing Anxieties and Cognitions”, Computer in Human Behavior, Vol.17, 2001, pp. 21-33.
[19] K.A. Papanikolaoua, M. Grigoriadoua and G.D. Magoulasb, and H. Kornilakisa,
“Towards New Forms of Knowledge Communication: The Adaptive Dimension of A Web-base Learning Environment”, Computer and Education, Vol. 39, 2002, pp. 333-360.
[20] J.Quinlan, “Induction of Decision Trees”, Machine learning, Vol.1, 1986, pp.81-106.
[21] R. Riding and I. Cheema, “Cognitive Styles—An oOverview and Integration”,
Educational Psychology, 11(3-4), 1991, pp.193-215.
[22] J.E. Sharp, “Using Portfolio in Classroom”, Proceedings of 27th Frontiers in
Education Conference, 1997, pp. 272-279.
[23] R. Srikant and R. Aggrawal, “Mining Sequential Patterns: Generalizations and Performance Improvements”, The Fifth International Conference on Extending
Database Technology,1996.
[24] L. Shashaani and A. Khalili, “Gender and Computers: Similarities and Differences in Iranian College Students’ Attitudes Toward Computers”, Computer
and Education , Vol.37, 2001, pp. 363-375.
[25] Y. Shang, H.C. Shi, and S.S. Chen, “An Intelligent Distributed Environment for Active Learning”, ACM Journal of Educational Resources in Computing, Vol. 1, Issue 2, 2001, Article 4,17pages.
[26] K. Smith and H. Tillema, “Evaluating Portfolio Use As A Learning Tool For Professionals”, Scandinavian Journal research , Vol. 42, No. 2, 1998, pp.193-205.
[27] E. Trantafillou, A. Poportsis and S. Demetriadis, “The Design and The Formative Evaluation of An Adaptive Educational System based on Cognitive ”,
Computer and Education, Vol. 41, 2003, pp. 87-103.
[28] C. J. Tsai, S. S. Tseng, and G. H. Su, “Design of An Object-oriented and Rule-based Virtual School,” Proc. of GCCCE’00/ICCAI’00, pp. 320-327, Singapore, 2000.
[29] C. J. Tsai, S. S. Tseng, and G. H. Su, “虛擬教室的設計與實作,” 遠距教育季 刊, 第 15/16 期, pp. 16-25, 2000.
[30] C. J. Tsai, S. S. Tseng, C. T. Chen, H. L. Hsu, and J. R. Cheng, “Design of An Object-oriented Teaching Material Authoring System,” Proc. of GCCCE/ICCAI’01, pp. 1008-1015, Taipei, Taiwan, R.O.C., 2001.
[31] V. Tsiriga and M. Virvou, “Dynamically Initializing The Student Model in A Web-based Language Turor”, First International IEEE Symposium
“INTELLIGENT SYSTEMS”, 2002.
[32] E.V. Wilson, “Student Characteristics and Computer-Mediated Communication”,
Computer and Education, Vol.34, 2000, pp. 67-76.
[33] M.J. Zaki, “SPAD: An Efficient Algorithm for Mining Frequent Sequences”,
Machine Learning, Vol.42, 2001, pp. 31-60.
[34] H.A. Witkin, P.K. Ottman, E. Raskin and S.A. Karp, “A manual for the
embedded figures tests”, Consulting Psychologists, Palo Alto, CA,1971
Appendix A: Learning Style Indicator
z What kind of learner are you?
Read each statement carefully. To the left of each statement, write the code that best describes how each statement applies to you.
Answer honestly as there are no correct or incorrect answers. It is best if you do not think about each question too long, as this could lead you to the wrong conclusion.
z SECTION 1
Place either an AE or a RO next to the statement below, depending upon which part of the statement mostly closely describes you.
1. _____ (AE) - I often produce off-the-cuff ideas that at first might seem silly or half-baked. (RO) - I am thorough and methodical.
2. _____ (AE) - I am normally the one who initiates conversations. (RO) - I enjoy watching people.
3. _____ (AE) - I am flexible and open minded. (RO) - I am careful and cautious.
4. _____ (AE) - I like to try new and different things without too much preparation. (RO) - I investigate a new topic or process in depth before trying it.
5. _____ (AE) - I am happy to have a go at new things. (RO) - I draw up lists up possible courses of actions when starting a new project.
6. _____ (AE) - I like to get involved and to participate. (RO) - I like to read and observe.
7. _____ (AE) - I am loud and outgoing. (RO) - I am quite and somewhat shy.
8. _____ (AE) - I make quick and bold decisions. (RO) - I make cautious and logical decisions.
9. _____ (AE) - I speak slowly, after thinking. (RO) - I speak fast, while thinking.
Total of AEs - _____. Total of ROs - _____. The one that has the larger number is your task preference.
z SECTION 2
Place either an AC or a CE next to the statement below, depending upon which part of the statement mostly closely describes you.
1. _____ (AC) - I ask probing questions when learning a new subject. (CE) - I am good at picking up hints and techniques from other people.
2. _____ (AC) - I am rational and logical. (CE) - I am practical and down to earth.
3. _____ (AC) - I plan events down to the last detail. (CE) - I like realistic, but flexible plans.
4. _____ (AC) - I like to know the right answers before trying something new. (CE) - I try things out by practicing to see if they work.
5. _____ (AC) - I analyze reports to find the basic assumptions and inconsistencies. (CE) - I rely upon others to give me the basic gist of reports.
6. _____ (AC) - I prefer working alone. (CE) - I enjoy working with others.
7. _____ (AC) - Others would describe me as serious, reserved, and formal. (CE) - Others would describe me as verbal, expressive, and informal.
8. _____ (AC) - I use facts to make decisions. (CE) - I use feelings to make decisions.
9. _____ (AC) - I am difficult to get to know. (CE) - I am easy to get to know.
Total of ACs - _____. Total of CEs - _____. The one that has the larger number is your thought or emotional preference.
Appendix B: Pretest attitude toward computers
Extent agreement or disagreement with the following statements (appropriately phrased on a 1-5 scale where 1=strongly agree and 5= strongly disagree)
ATT1. Apprehensiveness in using a computer
ATT2. Positive experiences in using computer applications
ATT3. Belief of computers’ role in education in terms of importance.
ATT4. Belief of computers’ role in business in terms of importance.
ATT5. Overall(positive) view of the role of computers.
Appendix C: the Social status Indicator
V1. What is the educational background of your father?
Doctor Master College Senior high school Others
V2. What is the educational background of your mother?
Doctor Master College Senior high school Others
V3. What is the income of your family each month?
$0~$1500 $1500~$3000 $3000~$4500 $4500~$6000 $6000 up
Appendix D: the Satisfaction Measure Indicator
Extent agreement or disagreement with the following statements (appropriately phrased on a 1-5 scale where 1=strongly agree and 5= strongly disagree)
V1. Ability to use the system without additional help.
V2. Degree of motivation infused by the instruction program to learn the
material.
V3. Comprehensiveness of the instructional material.
V4. Enjoyment with the way the instructional material was presented.
V5. Variety of display formats (text, graphs, etc.) used.
V6. User-friendliness of the system.
V7. Ease of use of the system.
V8. Overall, I was very satisfied with the presentation of instructional material.
V9. Overall, I was very satisfied with the system.
V10. Overall, I have a very positive learning experience.