Pub Date : 2023-08-01DOI: 10.1109/CSEET58097.2023.00031
Jonnathan Berrezueta-Guzman, Stephan Krusche
Large language models, such as ChatGPT, possess the potential to revolutionize educational practices across various domains. Nonetheless, the deployment of these models can inadvertently foster academic dishonesty due to their facile accessibility. In practical courses like programming, where hands-on experience is crucial for learning, relying solely on ChatGPT can hinder students’ ability to engage with the exercises, consequently impeding the attainment of learning outcomes.This paper conducts an experimental analysis of GPT 3.5 and GPT 4, gauging their proficiencies and constraints in resolving a compendium of 22 programming exercises. We discern and categorize exercises based on ChatGPT’s ability to furnish viable solutions, alongside those that remain unaddressed. Moreover, an evaluation of the malleability of the solutions proposed by ChatGPT is undertaken. Subsequently, we propound a series of recommendations aimed at curtailing undue dependence on ChatGPT, thereby fostering authentic competency development in programming. The efficaciousness of these recommendations is underpinned by their integration into the design and delivery of an examination as part of the corresponding course.
{"title":"Recommendations to Create Programming Exercises to Overcome ChatGPT","authors":"Jonnathan Berrezueta-Guzman, Stephan Krusche","doi":"10.1109/CSEET58097.2023.00031","DOIUrl":"https://doi.org/10.1109/CSEET58097.2023.00031","url":null,"abstract":"Large language models, such as ChatGPT, possess the potential to revolutionize educational practices across various domains. Nonetheless, the deployment of these models can inadvertently foster academic dishonesty due to their facile accessibility. In practical courses like programming, where hands-on experience is crucial for learning, relying solely on ChatGPT can hinder students’ ability to engage with the exercises, consequently impeding the attainment of learning outcomes.This paper conducts an experimental analysis of GPT 3.5 and GPT 4, gauging their proficiencies and constraints in resolving a compendium of 22 programming exercises. We discern and categorize exercises based on ChatGPT’s ability to furnish viable solutions, alongside those that remain unaddressed. Moreover, an evaluation of the malleability of the solutions proposed by ChatGPT is undertaken. Subsequently, we propound a series of recommendations aimed at curtailing undue dependence on ChatGPT, thereby fostering authentic competency development in programming. The efficaciousness of these recommendations is underpinned by their integration into the design and delivery of an examination as part of the corresponding course.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130791472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.1109/CSEET58097.2023.00042
Oh Sato, A. Hazeyama
This study regards inspections conducted in project-based learning (PBL) for software development as learning feedback. To solve the problem that inspection comments are distributed separately across platforms, which is an obstacle to classification of comments, we develop a script, Comment Gatherer, which aggregates inspection comments between GitHub and Figma. Then, we describe the concept of a support application that enables the automatic classification of inspection comments by machine learning.
{"title":"Development of a script to aggregate document inspection comments across different platforms to GitHub in a software development PBL","authors":"Oh Sato, A. Hazeyama","doi":"10.1109/CSEET58097.2023.00042","DOIUrl":"https://doi.org/10.1109/CSEET58097.2023.00042","url":null,"abstract":"This study regards inspections conducted in project-based learning (PBL) for software development as learning feedback. To solve the problem that inspection comments are distributed separately across platforms, which is an obstacle to classification of comments, we develop a script, Comment Gatherer, which aggregates inspection comments between GitHub and Figma. Then, we describe the concept of a support application that enables the automatic classification of inspection comments by machine learning.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128952765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.1109/CSEET58097.2023.00046
Kazuki Fukushima, T. Ishio, Kazumasa Shimari, Kenichi Matsumoto
In an assignment-based introductory programming course, a teacher makes a daily class plan based on a textbook and assigns tasks to the students. Assignments are prepared by the teacher so that students can have a better understanding of programming language constructs explained in the course. On the other hand, it is unclear how those language constructs are useful for practical programming tasks. To analyze the practicality of a programming course, this study proposes to compare the vocabularies of code used in textbooks, assignments, and regular programming tasks. If the vocabularies of the textbooks and assignments are closer to that of source code in actual projects, the programming course is considered more practical. As a case study, we have applied the method to evaluate a programming course focusing on data science for graduate students. The result revealed inconsistency between the programming language constructs taught in the course and frequently used in data analysis programs on the Kaggle platform.
{"title":"Towards Assessment of Practicality of Introductory Programming Course Using Vocabulary of Textbooks, Assignments, and Actual Projects","authors":"Kazuki Fukushima, T. Ishio, Kazumasa Shimari, Kenichi Matsumoto","doi":"10.1109/CSEET58097.2023.00046","DOIUrl":"https://doi.org/10.1109/CSEET58097.2023.00046","url":null,"abstract":"In an assignment-based introductory programming course, a teacher makes a daily class plan based on a textbook and assigns tasks to the students. Assignments are prepared by the teacher so that students can have a better understanding of programming language constructs explained in the course. On the other hand, it is unclear how those language constructs are useful for practical programming tasks. To analyze the practicality of a programming course, this study proposes to compare the vocabularies of code used in textbooks, assignments, and regular programming tasks. If the vocabularies of the textbooks and assignments are closer to that of source code in actual projects, the programming course is considered more practical. As a case study, we have applied the method to evaluate a programming course focusing on data science for graduate students. The result revealed inconsistency between the programming language constructs taught in the course and frequently used in data analysis programs on the Kaggle platform.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130431614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.1109/cseet58097.2023.00039
Z. Johanyák, József Cserkó, Attila Pásztor
With the increasing popularity of advanced language models and other artificial intelligence technologies, solutions that utilize AI are now widely used in various industries, such as software engineering and education. This article specifically examines the utilization of AI-assisted tools in programming courses at universities. It presents the existing tools available and discusses their practical applications, based on insights from a pilot project. Additionally, the article delves into the perspectives and attitudes of both students and teachers towards these tools.
{"title":"AI-assisted university programming education in practice","authors":"Z. Johanyák, József Cserkó, Attila Pásztor","doi":"10.1109/cseet58097.2023.00039","DOIUrl":"https://doi.org/10.1109/cseet58097.2023.00039","url":null,"abstract":"With the increasing popularity of advanced language models and other artificial intelligence technologies, solutions that utilize AI are now widely used in various industries, such as software engineering and education. This article specifically examines the utilization of AI-assisted tools in programming courses at universities. It presents the existing tools available and discusses their practical applications, based on insights from a pilot project. Additionally, the article delves into the perspectives and attitudes of both students and teachers towards these tools.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122970130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.1109/CSEET58097.2023.00033
Miguel Morales Trujillo, M. Galster
Poor feedback practices for professional development can stall, or even reverse, the professional growth of software engineering professionals. Yet, when setting up feedback systems, organizations often rely on experience or “anecdotal evidence” due to a lack of empirically-grounded guidelines that support those who give and those who receive feedback. Based on responses from a web-based survey, we describe initial challenges and strategies for professional feedback specifically in software engineering. We then explore how software engineering practice can progress towards more evidence-based feedback systems to ensure the continuous growth of professionals. We also present new directions for future research.
{"title":"On Evidence-based Feedback Practices in Software Engineering for Continuous People Improvement","authors":"Miguel Morales Trujillo, M. Galster","doi":"10.1109/CSEET58097.2023.00033","DOIUrl":"https://doi.org/10.1109/CSEET58097.2023.00033","url":null,"abstract":"Poor feedback practices for professional development can stall, or even reverse, the professional growth of software engineering professionals. Yet, when setting up feedback systems, organizations often rely on experience or “anecdotal evidence” due to a lack of empirically-grounded guidelines that support those who give and those who receive feedback. Based on responses from a web-based survey, we describe initial challenges and strategies for professional feedback specifically in software engineering. We then explore how software engineering practice can progress towards more evidence-based feedback systems to ensure the continuous growth of professionals. We also present new directions for future research.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"300 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114049394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.1109/CSEET58097.2023.00028
William Chan, Y. T. Yu, J. Keung, Victor C.S. Lee
We propose a new methodology, the Exercise Creation Methodology (ECM), that leverages recent AI technology advancements to create ChatGPT-assisted programming exercises for beginners. ECM takes an existing exercise as input and mutates it by removing some contents into semantically equivalent but syntactically different versions. The pair of versions are labeled as answered correctly and misleadingly by ChatGPT. The removed contents are re-inserted incrementally with further mutation, ensuring the labels remain unchanged. Using the version with the misleading answer and the ChatGPT elaboration on the other version, we construct a ChatGPT-assisted exercise. The latter version may also serve as a solution. We illustrate ECM using a case study.
{"title":"Toward AI-assisted Exercise Creation for First Course in Programming through Adversarial Examples of AI Models","authors":"William Chan, Y. T. Yu, J. Keung, Victor C.S. Lee","doi":"10.1109/CSEET58097.2023.00028","DOIUrl":"https://doi.org/10.1109/CSEET58097.2023.00028","url":null,"abstract":"We propose a new methodology, the Exercise Creation Methodology (ECM), that leverages recent AI technology advancements to create ChatGPT-assisted programming exercises for beginners. ECM takes an existing exercise as input and mutates it by removing some contents into semantically equivalent but syntactically different versions. The pair of versions are labeled as answered correctly and misleadingly by ChatGPT. The removed contents are re-inserted incrementally with further mutation, ensuring the labels remain unchanged. Using the version with the misleading answer and the ChatGPT elaboration on the other version, we construct a ChatGPT-assisted exercise. The latter version may also serve as a solution. We illustrate ECM using a case study.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124901157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.1109/CSEET58097.2023.00020
Stefanie Manger, Maximilian Sölch, Matthias Linhuber, Christoph Weinhuber, Philipp Zagar, Stephan Krusche
The COVID-19 pandemic precipitated an unprecedented paradigm shift in higher education, compelling swift adaptation to online teaching methods. Consequently, the merits of remote education, including increased flexibility and geographic independence, were emphasized. At the same time, however, the problems associated with distance education became apparent, such as the lack of networking, collaborative learning, and social interactions. This situation led to detrimental effects on student motivation and learning outcomes in team-oriented software engineering courses.To address the dichotomy of learning preferences, one potential solution proposed is the simultaneous offering of online and onsite instruction. However, such a proposition presents substantial logistical challenges, necessitating additional resources, labor, and organizational overhead. This research paper presents a case study conducted during an introductory programming course, which serves as a precursor to a comprehensive, practical software engineering course. Upon easing of COVID-19 related restrictions, the instructors offered both online and onsite versions of this course and obtained student feedback through interviews to draw a comparative analysis.The study outcomes provide crucial insights into students’ preferences with respect to learning modalities in higher education, particularly within the software engineering discipline. The results indicate a predominant preference for the onsite version of the introductory course. Reasons attributed to this preference include enhanced social interactions, greater enjoyment, and increased motivation, thus highlighting the irreplaceable value of face-to-face education.
{"title":"Is Online Teaching Dead After COVID-19? Student Preferences for Programming Courses","authors":"Stefanie Manger, Maximilian Sölch, Matthias Linhuber, Christoph Weinhuber, Philipp Zagar, Stephan Krusche","doi":"10.1109/CSEET58097.2023.00020","DOIUrl":"https://doi.org/10.1109/CSEET58097.2023.00020","url":null,"abstract":"The COVID-19 pandemic precipitated an unprecedented paradigm shift in higher education, compelling swift adaptation to online teaching methods. Consequently, the merits of remote education, including increased flexibility and geographic independence, were emphasized. At the same time, however, the problems associated with distance education became apparent, such as the lack of networking, collaborative learning, and social interactions. This situation led to detrimental effects on student motivation and learning outcomes in team-oriented software engineering courses.To address the dichotomy of learning preferences, one potential solution proposed is the simultaneous offering of online and onsite instruction. However, such a proposition presents substantial logistical challenges, necessitating additional resources, labor, and organizational overhead. This research paper presents a case study conducted during an introductory programming course, which serves as a precursor to a comprehensive, practical software engineering course. Upon easing of COVID-19 related restrictions, the instructors offered both online and onsite versions of this course and obtained student feedback through interviews to draw a comparative analysis.The study outcomes provide crucial insights into students’ preferences with respect to learning modalities in higher education, particularly within the software engineering discipline. The results indicate a predominant preference for the onsite version of the introductory course. Reasons attributed to this preference include enhanced social interactions, greater enjoyment, and increased motivation, thus highlighting the irreplaceable value of face-to-face education.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130123336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.1109/cseet58097.2023.00047
Rony G. Flatscher
At the Vienna University of Economics and Business Administration (WU), Bachelor students can learn programming from scratch and become able to create portable GUI programs for Windows, macOS and Linux in just one semester. This is possible within 60 hours (4 hours per week) of class attendance (“contact hours”) and a total teaching load of 200 hours, which corresponds to 8 ECTS (European Credit Transfer System). Several critical success factors make this possible, including the course objectives, the course structure, the pedagogical principles, and finally the programming language used for teaching the introductory course [1].
{"title":"Workshop “Business Programming” - Critical Factors from Zero to Portable GUI Programming in 4 Hours","authors":"Rony G. Flatscher","doi":"10.1109/cseet58097.2023.00047","DOIUrl":"https://doi.org/10.1109/cseet58097.2023.00047","url":null,"abstract":"At the Vienna University of Economics and Business Administration (WU), Bachelor students can learn programming from scratch and become able to create portable GUI programs for Windows, macOS and Linux in just one semester. This is possible within 60 hours (4 hours per week) of class attendance (“contact hours”) and a total teaching load of 200 hours, which corresponds to 8 ECTS (European Credit Transfer System). Several critical success factors make this possible, including the course objectives, the course structure, the pedagogical principles, and finally the programming language used for teaching the introductory course [1].","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134101903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.1109/CSEET58097.2023.00035
M. K. Sabariah, V. Effendy, Jati H. Husen, Daffa Hilmy Fadhlurrohman, Rony Setyawansyah
University-level software engineering education faces the challenge of providing both fundamental concepts while delivering to their students the latest trend in tools and practices. However, software engineering programs may not be capable of solving those challenges with their own resources. In this paper, we present our experience in solving those challenges by cooperating with an industrial partner by developing a collaboration program to provide knowledge of the latest industrial software engineering practice. We discovered that the program has several other benefits besides providing knowledge of industrial software engineering practice. However, challenges and concerns still need to be solved and addressed to ensure the proper execution of the collaboration program.
{"title":"Experiences With Gap-Bridging Software Engineering Industry-Academia Collaborative Education Program","authors":"M. K. Sabariah, V. Effendy, Jati H. Husen, Daffa Hilmy Fadhlurrohman, Rony Setyawansyah","doi":"10.1109/CSEET58097.2023.00035","DOIUrl":"https://doi.org/10.1109/CSEET58097.2023.00035","url":null,"abstract":"University-level software engineering education faces the challenge of providing both fundamental concepts while delivering to their students the latest trend in tools and practices. However, software engineering programs may not be capable of solving those challenges with their own resources. In this paper, we present our experience in solving those challenges by cooperating with an industrial partner by developing a collaboration program to provide knowledge of the latest industrial software engineering practice. We discovered that the program has several other benefits besides providing knowledge of industrial software engineering practice. However, challenges and concerns still need to be solved and addressed to ensure the proper execution of the collaboration program.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114162217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.1109/CSEET58097.2023.00030
Sandro Speth, Niklas Meißner, Steffen Becker
In recent years, artificial intelligence (AI) has been increasingly used in education and supports teachers in creating educational material and students in their learning progress. AI-driven learning support has recently been further strengthened by the release of ChatGPT, in which users can retrieve explanations for various concepts in a few minutes through chat. However, to what extent the use of AI models, such as ChatGPT, is suitable for the creation of didactically and content-wise good exercises for programming courses is not yet known. Therefore, in this paper, we investigate the use of AI-generated exercises for beginner and intermediate programming courses in higher education using ChatGPT. We created 12 exercise sheets with ChatGPT for a beginner to intermediate programming course focusing on the objects-first approach. We report our process, prompts, and experience using ChatGPT for this task and outline good practices we identified. The generated exercises are assessed and revised, primarily using ChatGPT, until they met the requirements of the programming course. We assessed the quality of these exercises by using them in our external teaching assignment course at the University of Education Ludwigsburg and let the students evaluate them. Results indicate the quality of the generated exercises and the time-saving for creating them using ChatGPT. However, our experience showed that while it is fast to generate a good version of an exercise, almost every exercise requires minor manual changes to improve its quality.
{"title":"Investigating the Use of AI-Generated Exercises for Beginner and Intermediate Programming Courses: A ChatGPT Case Study","authors":"Sandro Speth, Niklas Meißner, Steffen Becker","doi":"10.1109/CSEET58097.2023.00030","DOIUrl":"https://doi.org/10.1109/CSEET58097.2023.00030","url":null,"abstract":"In recent years, artificial intelligence (AI) has been increasingly used in education and supports teachers in creating educational material and students in their learning progress. AI-driven learning support has recently been further strengthened by the release of ChatGPT, in which users can retrieve explanations for various concepts in a few minutes through chat. However, to what extent the use of AI models, such as ChatGPT, is suitable for the creation of didactically and content-wise good exercises for programming courses is not yet known. Therefore, in this paper, we investigate the use of AI-generated exercises for beginner and intermediate programming courses in higher education using ChatGPT. We created 12 exercise sheets with ChatGPT for a beginner to intermediate programming course focusing on the objects-first approach. We report our process, prompts, and experience using ChatGPT for this task and outline good practices we identified. The generated exercises are assessed and revised, primarily using ChatGPT, until they met the requirements of the programming course. We assessed the quality of these exercises by using them in our external teaching assignment course at the University of Education Ludwigsburg and let the students evaluate them. Results indicate the quality of the generated exercises and the time-saving for creating them using ChatGPT. However, our experience showed that while it is fast to generate a good version of an exercise, almost every exercise requires minor manual changes to improve its quality.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125428041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：