2014 Fiscal Year Research-status Report
Programming learner supports dependent on institutes
| Project/Area Number |
26730178
|
|---|
| Research Institution | Ritsumeikan University |
|---|
Principal Investigator |
デイン.テイ.ドン フウオン 立命館大学, 情報理工学部, 助手 (90712117)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Keywords | portfolio / programming / understanding level / machine learning |
|---|
| Outline of Annual Research Achievements |
We have developed the following modules in 2014.
Database: A portfolio database is developped to conduct an experiment in Vietnam. We have conducted an experiment in Danang College of Education. All button clicks onto Web exercise pages are recorded into the portfolio database. The database automatically recognizes specific sequences of button clicks taken for a high level action such as submitting coded and viewing samples.
Understanding Status Filter: In programming, it is necessary for students to have prospects indicating what programming knowledge they organize into a code. We have developed a method to determine whether learners work on assignments along with programming prospects. The method acquires reference histories to programming knowledge learners consult to get programming prospects. A classifier trained with a machine learning algorithm discriminates reference histories with programming prospects from others. The classifier uses data retrieved from the portfolio database.
Successful Case Filter: An automatic detection of students who write inappropriate source codes enables teachers to supervise them with higher priority. We have proposed a method to detect backward students. The method calculates the similarity of student codes to model codes in the context of teaching units. The students whose codes are low in the similarity to the model code are regarded as the backward student. The method facilitates teachers to detect students to be supervised more easily.
|
| Current Status of Research Progress |
Current Status of Research Progress
1: Research has progressed more than it was originally planned.
Reason
We have conducted an experiment in Danang College of Education, using the database we have developped. Based on data collected in the experiment, we have analyzed a way how students improve their understanding level. In addition to that, we have proposed a method to select students who are successfull in programming, using the data from Japanese students.
|
| Strategy for Future Research Activity |
We are now seeking a method to calculate the understanding level and the motivation of students from portfolio data, using the non-negative matrix factorization. We have finished the implementation of the method. We are in a state to analyze actual data collected in 2012, and 2013.
|
| Causes of Carryover |
We did a presentation in an international conference in Kitakyushu at the end of March. For this business trip, we save the fee.
|
| Expenditure Plan for Carryover Budget |
We have used up all the money in the business trip.
|
