Development of Mobile-Interfaced Machine Learning-Based Predictive Models for Improving Students’ Performance in Programming Courses

ABSTRACTThe benefits of using online exercises have been analysed in terms of distance learning, automatic assessment and self-regulated learning. In this study, we have not found a direct proportional relationship between student performance in the course exercises that use online technologies and the exam grades. We see that the average submission rate to these online exercises is not positively correlated with the exercise points. Yet, our results confirm that doing exercises along supports student learning and skill accumulation equipping them with the knowledge of programming. While the student performance in programming courses is affected by factors such as prior background in programming, cognitive skills and the quality of teaching, completing the course exercises via learning-by-doing is an indispensable part of teaching. Based on the student feedback from the course survey, the students are highly satisfied with using online technologies as part of learning.

An engaging context has been shown to improve student motivation and performance in programming courses. Therefore, we incorporated six hands-on, supplementary, voluntary workshops (called Operation Java Blitz, or OJB) on subjects that were not exhaustively included in the current programming curriculum in Spring 2014. The poster will discuss the sessions, the initial results from 34 students, and future plans.

This paper presents a pedagogical strategy that intends to help students maximize learning and minimize drop-out rates in programming courses. The goal is to motivate students to develop a better programming study behaviour through the utilization of appropriate learning activities and the conscious assessment of their self-efficacy level. The paper also includes some preliminary results of the strategy application with students of Design and Multimedia.

Measuring progress in entrepreneurship education

In this paper we argue that the incorporation of experiences on testing activities, in particular mutation testing, in programming courses adds valuable knowledge to the learning process. Mutation testing is centered on the idea of creating test data for uncovering seeded faults in programs that slightly differ from the original program. These faulty programs are called mutants. Through source code analysis and test case execution, testers have to identify the differences between the original program and the mutants. To do so, testers must have a sound understanding of the program's control flow and instructions. This broad understanding of programming represents a key skill for novice students in programming courses. We evaluate the effects of using mutation testing to improve the learning process of novice students in programming courses. We conclude that the introduction of mutation testing in the learning process provides students with learning experiences that go beyond traditional lectures and hands-on programming courses.

Evaluating the learners to determine their proficiency in programming is a challenging task. In this paper, we attempt to automate this task by analyzing dynamic data collected from programming platform through sensors. Since the performance of students in programming course and their assessment depend on multiple criteria, we model the problem of finding the proficiency of student as a Multi Criteria Decision Making (MCDM) problem. We present a novel solution using Analytic Hierarchy Process (AHP) with which each student is classified into one of the expertise levels which represent their competency in a particular programming language. This competency based approach will help course instructors to grade the students. This grading helps the teachers to identify students who are facing difficulties in learning and to guide them to improve their technical skills. We validate our results by comparing them with marks scored by the students in the examination of that course.

Current literature outlines the documented need for improved communication during patient medication counseling. Although many tools exist, there needs to be a national standardized tool that complies with federal and state law, to objectively measure student pharmacist performance during patient counseling in the community pharmacy setting. The primary objective of this study is to perform an initial analysis of the internal consistency reliability of a patient medication counseling rubric designed with an Indian Health Services theoretical framework. Secondary objectives include measuring changes in student performance over the time of the study. The 18-item rubric was developed to objectively measure student pharmacist performance during patient medication counseling sessions in a 21-h Introductory Pharmacy Practice Experience (IPPE) course. The community-pharmacy-based IPPE patient counseling course evaluates students' communication skills and patient-centered counseling techniques in live and simulated patient counseling sessions. Three pharmacist evaluators assessed a total of 247 student counseling sessions. The rubric's internal consistency reliability was analyzed, and student performance improvement was observed within the course. Students' performance was evaluated as “meets expectations” in most live and simulated sessions. However, an independent groups t-test showed that the mean performance score for the live counseling sessions (2.59, SD = 0.29) was higher (p < 0.001) than that for the simulated counseling sessions (2.35, SD = 0.35). Students' performance in the course improved over three weeks [Week 1: mean (SD) = 2.29 (0.32), Week 2: mean (SD) = 2.44 (0.33), Week 3: mean (SD) = 2.62 (0.29); p < 0.001]. A Tukey-Kramer comparison post hoc test found a significant increase in the mean performance scores between weeks (p < 0.05). The overall internal consistency reliability of the counseling rubric was determined acceptable, with a Cronbach's alpha of 0.75. Further study is required, including the assessment of inter-rater reliability, factor analysis, variable analysis, and use in other states with patient confirmation testing necessary to validate the rubric for use with student pharmacists in the community pharmacy setting.

Self-assessment capabilities, that enables the student to have an insight on his own learning process, are a very desirable skill on any higher education student. It is even more important for transnational students as it allows them to successfully adapt to their new international learning environment. Present work proposes an online tool to help computer science students to develop their self-assessment skills while learning Java programming. It consists on a plug-in for the widely popular Moodle learning management system to work with source code for the Java programming language. The developed plug-in lets students to upload source files, analyzes the code and presents a report to the student using industry standard tools. The report includes both errors, points of improvement and a general comparison with the rest of his classmates, from the software quality standpoint. This way, the student is provided with a framework against to which compare the correctness of the solution he/she has programmed before it is delivered to the teacher for evaluation. The teacher is able to access all this information too, facilitating an insight of how the class, as well as individual students, is progressing. It is expected that the shortening on the classical loop of the student problem solution and teacher feedback will enhance the student self-awareness and will improve his overall performance in programming courses.

Parallel programming skills are becoming more popular due to the unprecedented boom in artificial intelligent and high-performance computing. Programming assignments are widely used in parallel programming courses to measure student performance and expose students to constraints in real projects. However, due to the difficulty level of these assignments, many students struggle to write fully functional and adequately documented programs. To improve student performance, we implemented a moderated two-stage format for five course projects in a graduate-level introductory parallel programming class. Each project is divided into two stages where students complete the assignment individually without any collaboration in the first stage. Then students work in pairs to work on the same project in the second stage so they can review each other's work from the first stage and improve their programs collaboratively. For two of the five projects, a moderated meeting is conducted in between the two stages where the instructor moderated a group discussion on general issues raised by students. We found that students' performance improved from stage one to stage two. In addition, the two projects with a moderated meeting show better performance gains. This paper also examines students' perceptions of and experiences with the moderated two-stage projects. Students favor working on two-stage projects because they had a chance to discuss challenging concepts and the moderated discussion session tend to guide them to the correct path should they make mistakes in stage one.

This work proposes a study focused on Continuous Integration (CI) tools in teaching programming courses as well as for automatically grading student assignments. There are many automatic grading tools for students' programming assignments which share most of their functionalities with CI tools. We would like to provide a methodology on how to implement this tool in teaching programming languages. We will evaluate and compare common CI tools and run experiments with students in programming courses.

Programming courses become prominent as one of the courses in which undergraduate students are unsuccessful especially in departments which offer computer education. Students often state that these courses are quite difficult compared to other courses. Therefore, a qualitative phenomenological approach was used to reveal the reasons of the failures of the undergraduate students in programming courses and to examine the difficulties they confronted with programming. In this scope, the laboratory practices of the Internet Programming course were observed in fall term of the 2013-2014 academic year in a university at central Anatolia. Interviews were made with 12 undergraduate students taking this course. Finally, the difficulties students experienced in the programming were determined as programming knowledge, programming skills, understanding semantics of the program, and debugging. Students emphasized that the biggest causes of failure in programming languages are lack of practice, not using algorithms and lack of knowledge. In addition, it was seen that the students who had high programming experience possess higher programming success and self-efficacy related to programming

Self-regulation of learning (SRL) is considered a vital skill in education, empowering students to control their learning process across multiple subjects. However, students often lack SRL abilities, which might impact their academic performance. One strategy to mitigate this problem is supporting students to assist their regulatory processes. Despite positive results in other subjects, how this support influences programming learning still needs further evidence. This study aims to contribute to this field by examining how the provision of SRL support influences students' programming performance and code development. The following research questions were established: RQ1) How does the programming performance of the group that received SRL support compare to that of the control group without support? RQ2) Do students receiving SRL support commit fewer programming errors than the control group without support? RQ3) Do students receiving SRL support maintain a more consistent learning routine than the control group without support? RQ4) What is the relationship between SRL abilities, programming performance, error commitment, and learning routine? To achieve this objective, a single-blind randomized experiment was conducted, and students were grouped into two experimental conditions, one receiving SRL support and a control group without support. Forty-nine students enrolled in an online introductory programming course participated in this study. The findings revealed that students who received SRL support achieved superior course grades, highlighting the benefit of this type of intervention. At the same time, the influence of SRL support and SRL abilities on programming error commitment is still unclear. Possibilities for future research to expand knowledge about the influence of SRL on code develonment are discussed.

The influence of temperament style on a student’s choice of and performance in a computer programming course

The flipped classroom, a form of blended learning, has gained popularity in higher education due to its potential to improve student engagement and performance. This approach addresses limitations in traditional teaching methods, such as didactic lectures and passive learning methods, by moving content delivery outside class and utilizing in-person sessions for active learning activities. This study aimed to assess the effectiveness of the flipped classroom as a teaching-learning strategy and to gather students’ opinions of the idea. A second-year undergraduate nursing class (n = 96) was split into two groups, one of which used the flipped classroom technique and the other the conventional approach in a quasi-experimental design. Questionnaires on a Likert scale were utilized to assess students’ opinions of the flipped classroom, and pre-and post-test results were evaluated. A variety of statistical analyses were used to compare mean scores and evaluate the efficacy of the flipped classroom, including paired and independent t-tests. A quasi-experimental study involving a second-year undergraduate nursing class showed a statistically significant improvement in student performance and a positive perception of the flipped classroom approach with P&lt;0.001. The flipped classroom in nursing education allows students to learn at their own pace through pre-class work, with an instructor as a facilitator. This personalized approach uses technology like online platforms and collaborative tools to deliver lectures and facilitate in-class activities, potentially improving student engagement, critical thinking, and clinical reasoning abilities.

Programming anxiety is a well-documented challenge in introductory computing courses, particularly among students with no prior exposure to programming. Scaffolding strategies such as pair programming, Parsons puzzles, and starter code templates are widely used to reduce anxiety and build confidence during the early stages of learning. Although starter templates often include explanatory comments and partially completed code, the relative effectiveness of these different scaffold types in mitigating anxiety has not been systematically examined. This article reports findings from a controlled experiment conducted during the first laboratory session of an undergraduate C programming course for students from different engineering and science disciplines. Pairs of students were randomly assigned to one of three conditions: a control group using blank templates, a comments-based scaffold group, and a code-based scaffold group. Coding anxiety was measured using a questionnaire with subscales related to self-efficacy, partner interaction, and peer judgement. Contrary to our expectations, the control group showed a greater reduction in coding anxiety than either scaffolded group, and students in the comments-based condition reported larger decreases in anxiety than those receiving code-based scaffolds. These findings suggest that for beginners, even well-intentioned scaffolds can temporarily increase the perceived difficulty in task completion.