Machine Learning Prediction and Recommendation Framework to Support Introductory Programming Course

The new students struggle to understand the introductory programming courses, due to its intricate nature, which results in higher dropout and increased failure rates. Despite implementing productive methodologies, the instructor struggles to identify the students with distinctive levels of skills. The modern institutes are looking for technology-equipped practices to classify the students and prepare personalized consultation procedures for each class. This paper applies decision tree-based machine learning classifiers to develop a prediction model competent to forecast the outcome of the introductory programming students at an early stage of the semester. The model is then transformed into an adaptive consultation framework which generates three types of colored signals; red, yellow, and green which illustrates whether the student is performing low, average, or high respectively. This provides an opportunity for the instructor to set precautionary measures for low performing students and set complicated tasks that help the highly skilled students to improve their skills further. The experiments compare a set of decision tree-based classifiers and conclude J48 as an efficient model in classifying students in all classes with high accuracy, sensitivity, and F-measure. Even though the aim of the research is to focus on introductory programming courses, however, the framework is flexible and can be implemented in other courses.

A Block-Based Arduino Programming Platform for Developing Computational Thinking Skills for K-12 Students

As a critical set of skills in the 21st century, computational thinking has attracted increasing attention in K-12 education. Microcontrollers, combined with LEDs, actuators, and a variety of sensors, provide students countless real-world projects, such as autonomous vehicles, smart homes, and robotics. By solving those projects through programming, students will not only learn computational skills but also benefit from the hands-on activities to get some experience on solving real-world problems. It makes microcontroller projects a perfect tool to develop the computational thinking skills of K-12 students. Our previous work has proposed a solution for higher graders to program Arduino through Ch, a C/C++ interpreter. It is necessary, however, to develop a platform for lower graders (K-6) since most of them do not have the ability to type through the keyboard. This paper extends our previous work such that students can program Arduino on RoboBlockly, a block-based programming platform. In the paper, we will present two case studies to demonstrate how to build blocks to control the Arduino board and what concepts students will learn from those projects. In addition, the proposed platform also provides an interactive way of transitioning students from the block-based program to a text-based program in Ch.

Learning Computer Programming Using Project-Based Collaborative Learning

The major concern of teaching computer programming in higher education is to provide students with the skills necessary to integrate theory and practice. One of the methods most suited for this task is project-based collaborative learning (PBCL). This study provides an in-depth analysis of students’ experiences, levels of collaboration and challenges in learning computer programming in a PBCL setting. A survey of 428 students was selected from a population of 840 undergraduate computer programming students at all levels using a stratified random sampling technique. It was found that focusing programming courses on real problems made the course more interesting for students. The students gained new interpersonal skills and understood the technical concepts of the courses better. PBCL was found to be suitable for teaching lower level (level 100 and 200) undergraduate programming courses compared with higher level (level 300 and 400) courses. Students' challenges in PBCL computer programming courses include time allocation for projects, choosing appropriate problems and piggy riding in project groups. We expect the findings of this study to influence policy on the teaching of computer programming courses at the undergraduate level.

MOOC Quality Design Criteria for Programming and Non-Programming Students

The purpose of this study is to investigate the quality design criteria for developing a Massive Open Online Course (MOOC). Currently, there are limited studies that highlight the required design criteria for the MOOC programming courses. A descriptive analysis was conducted to examine the characteristics of the three important quality design criteria which are (i) Instructional Design Criteria involving Lecture Organization and Culture; (ii) Technical Criteria involving User Interface, Video Content, Learning and Social Tools, and Learning Analytics; and (iii) E-Assessment. The data were collected from 306 respondents, representing the UUM MOOC students of 2018 class, were further analyzed using the T-Test hypothesis testing to determine whether both the programming and non-programming students require the same quality design criteria. The questionnaire used in this study consists of 46 items related to the MOOC quality design criteria that were adapted from previous studies. The results indicate that out of the nine constructs, four have obtained significant differences in the mean scores, namely the Video Content, Instructional Design, Culture, and E-assessment. This signifies that different quality design criteria are needed for both the programming and non-programming students. The outcome of this study may assist the developers in designing the MOOC by providing the required criteria according to its importance. Keywords: Instructional Design, MOOC, non-Programming, Programming, Quality Design

Evaluation of a Practice System Supporting Distributed Practice for Novice Programming Students

Programming is an important skill in the 21st century, but it is difficult for novices to learn. To help students practice and learn efficiently, the authors developed a mobile platform called Daily Quiz, which incorporated distributed practice theory. To evaluate the impact of distributed practice in programming learning facilitated by Daily Quiz, the authors conducted a between-subject experiment with 200 freshmen divided into two groups. Both groups received the same number of multiple-choice questions via Daily Quiz. However, the control group was encouraged to practice every 7 days, whereas the experimental group was encouraged to practice every 3 days. The results showed that this simple manipulation significantly improved the experimental group’s performance on final exams. Further analysis revealed that the experimental group of students achieved a higher rate of first-check correctness and tended to be more engaged in academic social interaction. Finally, a behavioral sequence analysis was adopted to compare the behavioral patterns of the two groups to investigate how distributed practice helped the students learn more efficiently.