Computer Science Learning Research Articles

Decoding Debugging Instruction: A Systematic Literature Review of Debugging Interventions

Students learning computer science frequently struggle with debugging errors in their code. These struggles can have significant downstream effects—negatively influencing how students assess their programming ability and contributing to their decision to drop out of CS courses. However, debugging instruction is often an overlooked topic, and instructors report feeling unaware of effective approaches to teach debugging. Within the literature, research on the topic is sporadic, and though there are rigorous and insightful studies to be found, there is a need to synthesize instructional approaches for debugging. In this article, we review research from 2010 to 2022 on debugging interventions. We summarize the common pedagogical approaches for learning and categorize how these target specific cognitive and non-cognitive debugging skills, such as self-efficacy and emotion regulation. We also present a summary of assessment methods and their outcomes in order to discuss intervention efficacy and directions for further research. Our sample displays a diverse variety of debugging interventions and pedagogical approaches, ranging from games to unplugged activities. An evaluation of article results also presents encouraging findings, revealing several interventions that improved debugging accuracy and learning. Still, we notice gaps in interventions addressing non-cognitive debugging skills and observe limited success in guiding students toward adopting systematic debugging strategies. The review concludes with a discussion of future directions and implications for researchers and instructors in the field.

VR Simulation: Advancing Practical Skills in Computer Science Education

This study presents the successful integration of Virtual Reality (VR) tools as an element in the computer science curriculum at the German University of Technology, Oman. The research study investigates the use of MyScore, a VR application developed by RWTH Aachen University - Teaching & Research Field Engineering Hydrology as an environment for computer hardware assembly and troubleshooting exercises. The VR simulation utilized in this study acts as a gamified environment, incorporating elements like scorekeeping and interactive challenges to enhance practical learning in computer science, akin to game-based strategies that engage and motivate students. Over some weeks, the project involved seven students and one tutor in immersive learning sessions to develop applied skills in computer hardware assembly with VR technology over conventional teaching methods. Structured surveys and direct observations were used for data collection through students' interactions with the VR sessions. We also evaluated the student's learning experiences as well as the usability of technology. The results showed that the user-friendliness of the VR interface and its ability to accurately simulate real-world tasks associated with computer assembly received both positive and negative reactions. While some students praised the technology for being pretty cutting-edge, some criticized it as unrealistic or non-interactive. We also received complaints that ranged from actually moving around in the virtual space to navigating only through teleportation spark points. Specifically, two students got motion sickness, which is a well-known obstacle associated with VR environments, and consequently left the sessions prematurely. The feedback of the instructor pointed out that setting up the VR equipment is straightforward and described some potential methods. Still, a call for more reliability in simulations and better interfaces began to surface as nevertheless less controversial agenda items. However, the instructor saw how VR has the potential to revolutionize educational practices. Providing interactive views between the VR device and students that can act as new learning methods. The present study extends the discussion on educational technology by providing empirical evidence of the benefits and challenges experienced in deploying VR for technical education implementation. These findings thus support the continued development and validation of VR technologies in pursuit of improved commitment, cost-effectiveness, immersion, and environment quality that may maximize learning outcomes in future educational applications.

Gamification Powered by a Large Language Model to Enhance Flipped Classroom Learning in Undergraduate Computer Science

The flipped classroom in computer science has become a popular pedagogy where students complete preparatory reading and videos before class, leaving class time for hands-on practice. In theory, students come to class predisposed with knowledge to complete programming tasks, quizzes, and homework assignments. However, if students do not complete or do not fully understand the preparatory material, those students will not be equipped for class and may also be embarrassed to ask questions during class. In this study, we created a gamified quiz that is powered by a Large Language Model (LLM) that loads in questions from the flipped content transcripts. The game offers students a fun assessment after completing the flipped content that will both motivate them and prepare them for class. The game also provides an anonymous way for students to ask questions as they progress through the game content. Those questions can then be analysed by the instructor and reviewed in class. The study compares in-class quiz scores of a control group versus a group that had access to the gamified quiz in an undergraduate software engineering course over three consecutive course modules. The results obtained from both quantitative and qualitative data are promising, showing an increase in student in-class quiz scores along with positive student engagement with the gamified quiz. Students also reported that the game made them more comfortable with asking questions. Future work would extend this research to more students and over a longer period. The LLM and gamification also have much potential, where games can be created dynamically and be customized and personalized for each student's needs. This work shows an exciting gap in research that could lead to gamified experiences for students in the flipped model that are both relevant and personalized with the use of a LLM, offering the students the greatest chance for success.

Framework of Computer Science Learning Through Hybrid Service Learning Oriented Visual Toward the Continuum of Visualization Thinking and Generic Skills

Computer Science learning requires students to think logically and understand its practical implementation in real-life situation clearly. However, the lack of learning activities that bridge the gap between theory and practice hinders their ability to depict learned concepts in real-world scenarios and master generic skills. Therefore, Computer Science education necessitates visualising learning concepts in real-life contexts, such as implementing Service Learning activities. However, in the current post-COVID-19 endemic situation, it is not feasible to implement this approach fully face-to-face. Thus, integrating Service Learning activities through technology-mediated means is essential in Computer Science education. Hybrid Service Learning activities, using technology as a medium, are instructional designs that provide opportunities for students to apply theoretical knowledge practically in real-life situations. Therefore, in this study, Computer Science learning activities were designed with visual materials through a hybrid service learning website to support the continuum of students' visual thinking and their generic skills. Subsequently, the effects of Computer Science learning activities on the continuum of students' visual thinking, level of generic skills, and perception were analyzed. A quasi-experimental study design was used, which involved a total of 27 respondents and took 15 weeks to complete. The research data was analyzed using descriptive analysis and inferential statistics. The results of paired t-test for the continuum of students' visual thinking levels, including visual thinking, visual learning, and visual communication, indicated an improvement with a significant difference of [p<0.05] between the pre- and post-activities. In terms of students' generic skills levels, the paired t-test for the pre-Service Learning [PS], during-Service Learning [DS], and post-Service Learning [AS] phases showed a significant difference of [p<0.05], which indicated an increase in students' mastery of skills and changes between each phase. Furthermore, students' perceptions revealed positive feedback towards hybrid service learning. Overall, based on the findings of this study, a framework for visual-based hybrid service learning was developed as a guide for Computer Science education to support the continuum of students' visual thinking and their level of generic skills.

Computational musicking: music + coding as a hybrid practice

ABSTRACT While there is a growing body of research that explores the integration of music and coding in learning environments, much of this work has either emphasised the technical aspects of computer language design or music as a motivational context within which to learn computer science concepts. In this paper, we report on a study in which five undergraduate students with experience in both music and coding completed two creative musical tasks: one using conventional instruments and tools and one using Python code in an online music + coding environment. Inspired by the work of Christopher Small (1998. Musicking: The Meanings of Performing and Listening. University Press of New England), we describe music + coding as a set of interlocking processes which we call computational musicking and explore how practices from both domains are reimagined in this new hybrid context. We introduce semiotic theories of translation and transcription to make sense of the computational musicking process and describe strategies that participants devised in their creative process.

Effects of a Creativity-Enhancement Intervention on Preservice Elementary Teachers’ Creativity in Computing Education

AbstractRecently, creativity has been acknowledged for its importance in improving computer science learning and attitudes. However, very little is known about how to integrate creativity in preservice teacher computing education. Toward this end, we developed a creativity-enhancement intervention in an online Creative Computing instructional module to introduce preservice elementary teachers (N = 76) to the ideas of creativity in the context of computing education. Using a pre-/posttest quasi-experimental design, we examined the effects of the creativity-enhancement intervention on participants’ person-, process-, and Scratch product-related creativity compared to the same curriculum that did not include the creativity-enhancement intervention. Preservice elementary teachers who received the creativity-enhancement intervention reported significantly higher person- and process-related creativity and produced more creative Scratch projects than their peers who did not receive the intervention. When looking at the three creativity strands holistically, the study findings provide strong evidence that the intervention had a positive effect on preservice elementary teachers’ creativity in the context of computing education.

Recruiting Practices in Informal CS Learning

Introduction: Computer science (CS) lacks representation from people who identify as one or more of the following identities: woman, Black, Indigenous, Hispanic, Latina/Latino/Latinx, or disabled. We refer to these groups as historically underrepresented groups (HUGs). Informal learning, like CS summer camps and hackathons, can increase interest in K-12 students but still struggles to broaden participation. Objectives: In this study, we examine one source of struggle for informal learning programs: recruiting practices. Methods: Towards the goal of understanding this struggle, we interviewed 14 informal K-12 CS learning programs across a diverse region in the Northwestern United States to understand what recruiting practices are being used. We used a cultural competency lens to examine the variation within recruiting practices and how some practices could lead to broader participation in computing. Results: We identified 18 different recruiting practices used by informal CS learning program organizers. Some programs had similar practices, but subtle differences in implementation that led them to fall at different points on the cultural competence continuum. More culturally competent implementations generally involve reflection on the needs of specific populations that programs were trying to recruit, on why previous recruiting implementations did not work, and on feedback from stakeholders to change their implementations. This is the first paper to investigate how the implementation of the recruiting practice determines its cultural competency. Conclusion: Results from this study illuminate some of the problems informal CS programs face in broadening participation in computing and provide insights on how program organizers’ can overcome them. Our work highlights how students or parents access resources, the challenges program organizers encounter, and whether current recruiting practices effectively engage students from HUGs.

Development and interpretation of a multimodal predictive model for prognosis of gastrointestinal stromal tumor

Gastrointestinal stromal tumor (GIST) is the most common mesenchymal original tumor in gastrointestinal (GI) tract and is considered to have varying malignant potential. With the advancement of computer science, radiomics technology and deep learning had been applied in medical researches. It’s vital to construct a more accurate and reliable multimodal predictive model for recurrence-free survival (RFS) aiding for clinical decision-making. A total of 254 patients underwent surgery and pathologically diagnosed with GIST in The First Hospital of China Medical University from 2019 to 2022 were included in the study. Preoperative contrast enhanced computerized tomography (CE-CT) and hematoxylin/eosin (H&E) stained whole slide images (WSI) were acquired for analysis. In the present study, we constructed a sum of 11 models while the multimodal model (average C-index of 0.917 on validation set in 10-fold cross validation) performed the best on external validation cohort with an average C-index of 0.864. The multimodal model also reached statistical significance when validated in the external validation cohort (n = 42) with a p-value of 0.0088 which pertained to the recurrence-free survival (RFS) comparison between the high and low groups using the optimal threshold on the predictive score. We also explored the biological significance of radiomics and pathomics features by visualization and quantitative analysis. In the present study, we constructed a multimodal model predicting RFS of GIST which was prior over unimodal models. We also proposed hypothesis on the correlation between morphology of tumor cell and prognosis.

Using the gaming chatbot to develop algorithmic and logical thinking skills

The use of special computer games in classes increases student engagement and maintains their interest in learning, including learning computer science. Due to the logical and rational nature of solving programming problems, logic games and puzzle games that develop cognitive abilities, logical and algorithmic thinking are well suited for teaching computer science. Considering the popularity of Wordle puzzle game and the fact that word games are very effective for developing cognitive abilities, a gaming chatbot with puzzle tasks organized according to Wordle principles was developed for learning computer science and programming. The aim of the article is to investigate the effect of the developed gaming chatbot on students’ algorithmic and logical thinking.The study involved 3rd year undergraduate students of the educational program “Information Systems and Technologies”, Faculty of Information Technologies, Moscow Polytechnic University. The students used the gaming chatbot outside of class for 10 days and completed surveys before and after use. The analysis of the students’ surveys showed the impact of this gaming chatbot on the activation of memory, attention and to a greater extent logical thinking of the students, as well as on assessing students’ perception of the complexity of programming, their own knowledge of programming languages and logical thinking skills.The results of the study expand current ideas regarding the use of gaming chatbots and Wordle-type puzzle tasks in teaching computer science and programming. The presented gaming chatbot will help to increase students’ interest in classes, students’ involvement in the learning process, and ensure the development of their cognitive abilities.The conclusions of the article may be of practical interest to informatics and programming teachers. They contribute to the development of the direction of building gaming chatbots, as well as the use of word puzzles for teaching computer science.

Computational Thinking Assessment: Bibliometric Analysis-VOSviewer

Computational thinking is a very important ability in the transitional era of the industrial revolution 4.0 to 5.0 because it has a role in supporting problem solving, especially in the field of Education by applying computer thinking. Seeing the role of computational thinking in education, an assessment is needed to assess students' ability to apply computational thinking to solve problems, especially in learning computer science. Therefore, the aim of this study is to present a high-quality bibliometric review of various literature on assessment computational thinking. This type of research is bibliometric analysis using VOSviewer. Literature was collected from the Scopus database of 191 articles published in 2019-2023. The results of this study show that in the network visualization results there are 5 clusters, namely cluster 1 (43 items), cluster 2 (31 items), cluster 3 (27 items), cluster 4 (21 items), and cluster 5 (19 items). Meanwhile, on the results of overlay visualization and density visualization, it can be seen that the computational thinking assessment research shows that when it is associated with the themes of instrument, validity, reliability, and computer science education, not much research has been done so that there are opportunities for renewable research by taking these themes.

What’s cost got to do with it? Cost belief trajectories of undergraduate computer science students

Students want to learn computer science due to its usefulness for future careers, however they often meet challenges in introductory courses. In the increasingly digital world, it is important to understand some important psychological consequences of such challenges: perceived costs of pursuing computer science. This study thus investigated semester-long trajectories of four cost perceptions (effort, opportunity, psychological, and emotional) and their relations to achievement, major intentions, and career intentions (N = 831). All cost beliefs showed average increases, although with nuanced differences in levels and slopes, and the four costs differentially predicted student outcomes. Interestingly, the intercept of psychological cost negatively predicted final course grades while positively predicting major and career intentions. Women reported steeper increases in cost perceptions compared to men. The findings highlight the differential functioning of cost perceptions, with implications for the importance of targeting different aspects of cost perceptions to mitigate students’ barriers to success in computer science.

An automated, unobtrusive, formative assessment of creativity in a computer science and music remixing learning environment.

An automated, unobtrusive, formative assessment of creativity in a computer science and music remixing learning environment.

MolLoG: A Molecular Level Interpretability Model Bridging Local to Global for Predicting Drug Target Interactions.

Developing new pharmaceuticals is a costly and time-consuming endeavor fraught with significant safety risks. A critical aspect of drug research and disease therapy is discerning the existence of interactions between drugs and proteins. The evolution of deep learning (DL) in computer science has been remarkably aided in this regard in recent years. Yet, two challenges remain: (i) balancing the extraction of profound, local cohesive characteristics while warding off gradient disappearance and (ii) globally representing and understanding the interactions between the drug and target local attributes, which is vital for delivering molecular level insights indispensable to drug development. In response to these challenges, we propose a DL network structure, MolLoG, primarily comprising two modules: local feature encoders (LFE) and global interactive learning (GIL). Within the LFE module, graph convolution networks and leap blocks capture the local features of drug and protein molecules, respectively. The GIL module enables the efficient amalgamation of feature information, facilitating the global learning of feature structural semantics and procuring multihead attention weights for abstract features stemming from two modalities, providing biologically pertinent explanations for black-box results. Finally, predictive outcomes are achieved by decoding the unified representation via a multilayer perceptron. Our experimental analysis reveals that MolLoG outperforms several cutting-edge baselines across four data sets, delivering superior overall performance and providing satisfactory results when elucidating various facets of drug-target interaction predictions.

Getting a grip on how we talk about computational practices in science in settings of teacher learning

AbstractBackgroundScience teachers' understanding of the roles of computing practices in science frame how they enact scientific computational practices in their teaching and how their students perceive the relationship between computational practices and scientific endeavours.ObjectivesThis critical, integrative review synthesizes teacher learning literature about the role of computational literacy and computing practices in K‐12 science teaching.MethodsWe examined 54 peer‐reviewed articles and analysed the ways the researchers and teacher participants describe the affordances of integrating computational thinking (CT) and other computational practices in science. We characterize how CT and computational practices are framed in relation to scientific learning goals. We identify six primary affordances for integrating computational practices with science that are conveyed to teachers and by teachers, as represented in these studies of teacher learning.Results and ConclusionsThese six perspectives include (1) learning computer science principles, (2) developing CT dispositions, (3) engagement and inclusion in science, (4) taking ownership of science, (5) supporting learning science content, and (6) participating in computational practice as a form of scientific epistemic practice. Our analysis indicates that computational thinking and computational practices are often integrated in science in order to teach something about computing (e.g., Perspective 1), rather than to support learners' scientific work. Only the 29 articles coded for the sixth perspective—that is, in service of epistemic aims in science—demonstrate commitment to students' uses of computational ideas and practices as epistemic tools to participate in the sensemaking work of science.TakeawaysComparison of Perspectives 5 and 6 illustrates the nuance between computational practices in science that reify something students have already “figured out,” rather than those that serve epistemic goals. Perspective 6 encapsulates the deep synergy among (1) the reflexive nature of computing with scientific ideas and (2) computing as a central practice in science and engineering. We contend that a more focused message of computational practices in service of scientific sensemaking goals is necessary if we expect teachers to enact CT and related computational practices in their classrooms.

Reducing Road Mishaps: A CNN Model for Driver Fatigue Detection

Over the last few decades, there have been substantial developments in a variety of domains, including computer science, artificial intelligence, and machine learning, which has accelerated the evolution and application of intelligent systems in specific areas such as transportation. One way these systems are used in transportation is through fatigue detection, and to enable this technology, Convolutional Neural Networks serve as the foundation on which this system is built. CNNs are frequently employed in computer vision applications because they can automatically extract pertinent features from input data without the need for manual feature engineering. This CNN-based fatigue detection system was built in-order to address the repercussions of fatigued driving by monitoring the driver’s facial features in real-time so as to predict the fatigue levels and send out an alert to restore the driver’s alertness level so as to reduce road mishap. The system relies on visual input from a camera, which sends this input to a fatigue detection program installed on a Raspberry Pi microprocessor and sends out via alerts via a display and audio alerts via a piezoelectric buzzer. The model shows excellent performance, consistently achieving high accuracy, peaking at 97.34% on the 64th epoch, and consistently maintaining high validation accuracy, reaching 96.02% in the 67th epoch, indicating its ability to function effectively.

Mirror Mentoring: Black Women’s Experiences Serving as Mentors for Black Girls During a Virtual Computer Science Camp

Several studies have reported the positive benefits of informal Computer Science learning programs for Black girls, which include staff, mentors, and peers reflective of the girls in the program; however, we do not know enough about what motivates Black women to sign up to teach in such programs, or how representation in mentoring affects future CS learning for Black girls. Here we report the intersectional experiences of 11 Black women who served as instructors and mentors for the virtual INTech Summer Camp. The women in this study confirm that it is imperative to consider the intersectional experiences of Black women in CS as a whole, without explicating their identities. We found that Black women in CS feel that it is their responsibility to give back to Black girls to pay it forward from their own mentorship experiences. The Black women in our study describe seeking to fill a gap in mentorship that they experienced themselves, to share their knowledge and experiences to support the development of others who can relate to that intersection of identifying as Black and a girl or woman. Providing positive representation to encourage young Black girls to pursue tech careers is imperative to diversifying the tech workforce.

Application of Machine Learning to Customer Churn Risk Prediction

Accompanied by technological globalization and upswing of telecommunication industry in the 21st century, the number of operators is springing up like mushrooms after rain in the market and that intensifies the industry competition environment due to the unprecedented growth trend and the challenges. As a research hotspot in the field of business analysis, prediction of customer attrition risk possesses some extensive range pertaining to applications within global marketing, telecommunications and other fields. Due to the complex relationship between customer information and the products used, it is difficult for merchants to conduct effective risk assessments. Nevertheless, customer churn risk prediction has made such rapid progress over the past few years with the development within computer science and machine learning so that the researchers would be able to establish more potential connections and achieve more accurate predictions about customer churn. This article summarizes customer churn risk prediction in the order of time and technology iteration, and mainly introduces 9 classic prediction methods based on machine learning. Additionally, four relevant performance measurement metrics and one data set are explored. Eventually, in view of the problems existing in the current customer churn risk prediction methods, prospects for future research are proposed.

Football Player Classification

Clustering is an essential tool in data mining research and applications. It is the subject of active research in many fields of study, such as computer science, data science, statistics, pattern recognition, artificial intelligence, and machine learning. Several clustering techniques have been proposed and implemented, and most of them successfully find excellent quality or optimal clustering results in the domains mentioned earlier. However, there has been a gradual shift in the choice of clustering methods among domain experts and practitioners alike, which is precipitated by the fact that most traditional clustering algorithms still depend on the number of clusters provided a priori. These conventional clustering algorithms cannot effectively handle real-world data clustering analysis problems where the number of clusters in data objects cannot be easily identified. Also, they cannot effectively manage problems where the optimal number of clusters for a high-dimensional dataset cannot be easily determined. Therefore, there is a need for improved, flexible, and efficient clustering techniques. Recently, a variety of efficient clustering algorithms have been proposed in the literature, and these algorithms produced good results when evaluated on real-world clustering problems. This study presents an up-to-date systematic and comprehensive review of traditional and state-of-the-art clustering techniques for different domains. This survey considers clustering from a more practical perspective. It shows the outstanding role of clustering in various disciplines, such as education, marketing, medicine, biology, and bioinformatics. It also discusses the application of clustering to different fields attracting intensive efforts among the scientific community, such as big data, artificial intelligence, and robotics. This survey paper will be beneficial for both practitioners and researchers. It will serve as a good reference point for researchers and practitioners to design improved and efficient state-of-the-art clustering algorithms.

ICT TRENDS IN EDUCATION: A BIBLIOMETRICS STUDY OF THE PAST TWENTY YEARS OF STUDIES

Technology is a major component in education. Therefore, it must be investigated in order to gather knowledge for additional study. 185 articles were assessed using the PRISMA approach in conjunction with VOS-Viewer via Scopus data collecting. Analysing the quantity of articles, nations, citations, journals, and research partnerships on digital assessment in education is how evaluation is done. Knowledge map analysis is another way to investigate co-occurrence mapping. According to the research findings, the number of articles published rises annually, with the UK having the highest number of published publications. The research with the most citations is "Affordances of ICT in science learning: Implications for an integrated pedagogy," the journal with the most publications is "International Journal of Science Education," and the most well-liked partnership is the work done in Germany and the United Kingdom. The author with the most citations is "Webb M.E." Additionally, cluster analysis indicates that there are five primary categories—computer science education, education, science education, teaching, and science learning—that are most closely related to one another. Teaching, education, and computer science education are hot subjects right now.

ICT TRENDS IN EDUCATION: A BIBLIOMETRICS STUDY OF THE PAST TWENTY YEARS OF STUDIES

Technology is a major component in education. Therefore, it must be investigated in order to gather knowledge for additional study. 185 articles were assessed using the PRISMA approach in conjunction with VOS-Viewer via Scopus data collection. Analyzing the quantity of articles, countries, citations, journals, and research partnerships on ICT in education is how evaluation is done. Knowledge map analysis is another way to investigate co-occurrence mapping. According to the research findings, the number of articles published rises annually, with the UK having the highest number of published publications. The research with the most citations is "Affordances of ICT in Science Learning: Implications for an Integrated Pedagogy," the journal with the most publications is "International Journal of Science Education," and the most well-liked partnership is the work done in Germany and the United Kingdom. The author with the most citations is "Webb M.E." Additionally, cluster analysis indicates that there are five primary categories—computer science education, education, science education, teaching, and science learning—that are most closely related to one another. Teaching, education, and computer science education are hot subjects right now.