SYSTEM OF REVIEW LEARNING OUTCOMES STANDARD BY MACHINE LEARNING PRINCIPLES

Main Article Content

Paijit Suksomboon

Abstract

The researcher has developed system of review learning outcomes standard by machine learning principles, and studied the achievement by learning outcomes. By creating a model from the learning outcomes according to the standard of 40 subjects, analyzing, selection subjects group by similar expected learning outcomes characteristics of 31 columns in five areas by defining the level of inheritance for learning outcomes, three levels are 0-no expected, 1-expected a little, and 2-expected outcome must be achieved, to use the principles of machine learning, group the appropriate subjects to part of measure learning achievement. Then study the learning achievement to review the learning outcome standard of the target group curricula. As support guidelines on the decision-making concerning the curriculum development in future, the results of research concluded that prototype system based on the machine learning and studied the achievement by learning outcomes which summarized into two aspects as follows that;  1) Assessment of the importance of the overall information was at a high level (86.67%),  focusing on information on learning outcomes standards in the highest level (96%), information on curriculum objectives/goals in the highest level (93.33%), and information on teaching behaviors in the highest level (90%), respectively. 2) Assessment to use of information on the prototype system showing the consist of teaching, course description and expected learning outcome at the highest level (92%), has resulted in the review of curriculum mapping for the next curriculum improvement at the highest level (96.67%). Therefore, this model system can be used to review learning outcomes according to educational standards and to support decision-making in curriculum development.

Article Details

How to Cite
Suksomboon, P. (2022). SYSTEM OF REVIEW LEARNING OUTCOMES STANDARD BY MACHINE LEARNING PRINCIPLES . Journal of Industrial Education, 21(1), 91–101. Retrieved from https://ph01.tci-thaijo.org/index.php/JIE/article/view/246905
Section
Research Articles

References

Arreerard, R. (2018). Defamatory text classification on online social media [Master’s thesis]. Chulalongkorn University. (in Thai)

Chengz. (2019, October 3). Measure model performance from the confusion matrix. https://bit.ly/3qglU45 (in Thai)

Hiangrat, P., Sacchanand, C., & Choempayong, S. (2018). Information literacy of undergraduate students of Rajabhat Universities. TLA Research Journal, 11(1), 33-47. (in Thai)

Ma-oon, R. (2016). Effective teaching and learning in higher education. Southern Technology Journal, 9(2), 169-176. (in Thai)

Sae-Wong, W. (2018). Classification of anger voice in call center dialog [Master’s thesis]. Chulalongkorn University. (in Thai)

SAS Institute. (2022). Machine learning: Significance and definition. https://www.sas.com/th_th/insights/analytics/machine-learning.html (in Thai)

Sawekngam, W. (2016, February 19). Lecture documents: Teaching management in active learning. https://shorturl.asia/N1Zlk (in Thai)

Suksomboon, P., & Suksomboon, N. (2018). Development of a decision support system for the quality of teaching using academic database and multi-dimensional analysis. Industrial Technology Lampang Rajabhat University Journal, 11(2), 54–66. (in Thai)

Thachai, W. (2017, March 15). Determination of optimal k number using silhouette method. https://bit.ly/3yKKYUR (in Thai)