Evaluation of students programming skills on a computer programming course with a hierarchical clustering algorithm

Silva, Davi Bernardo; Silla, Carlos N.

doi:10.1109/fie44824.2020.9274130

Cited by 9 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a research work conducted by D B Silva et al [27] students with similar programming skills were grouped on the basis of their codes processed through natural language processing. Language key keywords are used to perform a word count and form feature vector to be used as input to clustering algorithm.…”

Section: Literature Reviewmentioning

confidence: 99%

A Machine Learning-Based Adaptive Feedback System to Enhance Programming Skill Using Computational Thinking

Kaleem,

Hassan,

Khurshid

2024

IEEE Access

View full text Add to dashboard Cite

The solution of a typical programming task involves algorithmic thinking, pattern recognition, decomposition and abstraction skills. These skills are basic pillars of Computational thinking (CT) and are essential for a computer programmer. Therefore, it is essential for a programming teacher to take these skills into account for evaluation of students. Existing methods for improving programming competency don't consider Computational Thinking of students and perform grading of students without taking these skills into account. Due to this limitation, deficiencies of these skills in students remain unrevealed, posing difficulties for educators to provide a need-oriented feedback. Performance of programming students is thus hindered by lack of interventions. This study proposes a method to evaluate programming students in terms of CT skill components and group them on the basis of their skill set. In this study, 780 students of object-oriented programming (OOP) class were given programming assignments for assessment of programming competencies. These students were then given small programming tasks requiring different computational thinking skill components for their solution. Machine learning approach was used to perform grouping of these students based upon their scores. Six groups of programming students, each having its own set of skill deficiencies, were identified as a result of clustering. One of the groups had an empty set of skill deficiencies and consisted of the students proficient in programming. Each of the other five groups had a non-empty set of skill deficiencies and comprised non-proficient programming students. A group-specific skill development plan was built for the groups having skill deficiencies. It was found that such a feedback was very effective and improved CT skill deficiencies of 82% of students.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Machine Learning-Based Adaptive Feedback System to Enhance Programming Skill Using Computational Thinking

Kaleem,

Hassan,

Khurshid

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Quite a large number of articles are devoted to the formation of programming skills. For example, for beginners [4], for schoolchildren [5,6] and for students [7], both based on Scratch blocks [8] and Python programming environments [9] and Java [10]. The article is devoted to the assessment of the level of competence formation in the field of programming of future computer science teachers and IT specialists [13].…”

Section: Introductionmentioning

confidence: 99%

Formation of Programming Skills among Students of Scientific, Technical and Natural Science Areas of Training Using the Arduino Platform

et al. 2022

View full text Add to dashboard Cite

The problem of improving the educational process of students of scientific, technical and natural science areas of training is one of the relevant aspects of modern pedagogical research. During training, it is necessary to apply new approaches, educational technologies and techniques in order to prepare graduates who are able to independently solve complex scientific, technical and engineering design tasks in the process of modern production. Programming is a universal tool for modeling objects and processes, as well as a powerful tool in developing the thinking of students of scientific, technical and natural science fields of training. The article discusses the issues of formation of programming skills of students based on the use of the Arduino platform. The professional standards are analyzed, the main contradictions of the existing system of training future bachelors in the field of radio electronics and control systems are revealed. The method of organizing effective programming training based on the use of the Arduino platform is presented. The criteria and indicators of the levels of competence formation are given. The results of an experiment on the implementation of the described methodology of teaching programming on the basis of the I.N. Ulyanov Chuvash State University are shown. Using the chi-square criterion, statistical processing of the results of a pedagogical experiment was performed, which convincingly proves that when using the Arduino platform, most students have reached high and advanced levels of programming skills formation.

show abstract

Teachers’ Knowledge in Informatics—Exploring Educational Robotics Resources Through the Lens of Textual Data Analysis

Parriaux,

Reffay,

Drot-Delange

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this research, we are interested in the knowledge of primary and secondary teachers to teach informatics. Using pedagogical resources produced by them as a trace of their enacted Pedagogical Content Knowledge (ePCK), we perform Textual Data Analysis and Clustering to discover the topics they write about. Focusing on resources in educational robotics, we show that lexicon used by teachers is different depending on the robot they use. Reinert’s clustering associates each robot with a separate cluster and a specific vocabulary. Multiple Correspondence Analysis (MCA) shows an opposition between lexicon found in resources using event-driven robots (Thymio and Ozobot) and in resources using sequential robots (Beebot and Bluebot). Event-driven robots tend to be more related with events and behavior notions, as sequential robots tend to be more related with first manipulations of an object and programming notions.

show abstract

Evaluation of students programming skills on a computer programming course with a hierarchical clustering algorithm

Cited by 9 publications

References 31 publications

A Machine Learning-Based Adaptive Feedback System to Enhance Programming Skill Using Computational Thinking

A Machine Learning-Based Adaptive Feedback System to Enhance Programming Skill Using Computational Thinking

Formation of Programming Skills among Students of Scientific, Technical and Natural Science Areas of Training Using the Arduino Platform

Teachers’ Knowledge in Informatics—Exploring Educational Robotics Resources Through the Lens of Textual Data Analysis

Contact Info

Product

Resources

About