Ramon Mayor Martins, Christiane Gresse Von Wangenheim, Marcelo Fernando Rauber, Jean Carlo Rossa Hauck, Melissa Figueiredo Silvestre
Knowledge about Machine Learning is becoming essential, yet it remains a restricted privilege that may not be available to students from a low socio-economic status background. Thus, in order to provide equal opportunities, we taught ML concepts and applications to 158 middle and high school students from a low socio-economic background in Brazil. Results show that these students can understand how ML works and execute the main steps of a human-centered process for developing an image classification model. No substantial differences regarding class periods, educational stage, and sex assigned at birth were observed. The course was perceived as fun and motivating, especially to girls. Despite the limitations in this context, the results show that they can be overcome. Mitigating solutions involve partnerships between social institutions and university, an adapted pedagogical approach as well as increased on-by-one assistance. These findings can be used to guide course designs for teaching ML in the context of underprivileged students from a low socio-economic status background and thus contribute to the inclusion of these students.
{"title":"Teaching Machine Learning to Middle and High School Students from a Low Socio-Economic Status Background","authors":"Ramon Mayor Martins, Christiane Gresse Von Wangenheim, Marcelo Fernando Rauber, Jean Carlo Rossa Hauck, Melissa Figueiredo Silvestre","doi":"10.15388/infedu.2024.13","DOIUrl":"https://doi.org/10.15388/infedu.2024.13","url":null,"abstract":"Knowledge about Machine Learning is becoming essential, yet it remains a restricted privilege that may not be available to students from a low socio-economic status background. Thus, in order to provide equal opportunities, we taught ML concepts and applications to 158 middle and high school students from a low socio-economic background in Brazil. Results show that these students can understand how ML works and execute the main steps of a human-centered process for developing an image classification model. No substantial differences regarding class periods, educational stage, and sex assigned at birth were observed. The course was perceived as fun and motivating, especially to girls. Despite the limitations in this context, the results show that they can be overcome. Mitigating solutions involve partnerships between social institutions and university, an adapted pedagogical approach as well as increased on-by-one assistance. These findings can be used to guide course designs for teaching ML in the context of underprivileged students from a low socio-economic status background and thus contribute to the inclusion of these students.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134901694","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}
Deivid E. S. Silva, Tayana Conte, Natasha M. C. Valentim
Contemporary society is characterized by diversity and intricacy, necessitating more meaningful learning experiences. To meet these evolving needs, the incorporation of computational systems into education must acknowledge the distinctive characteristics of learners. Therefore, we conducted a Systematic Mapping Study (SMS) to investigate technologies that support the Learner eXperience (LX) design in computational systems. LX refers to learners’ perceptions, reactions, and achievements while engaging with learning resources, encompassing digital games, simulations, and multimedia. The SMS results uncovered distinct LX design technologies, with a noticeable inclination towards learner-centric strategies. Interestingly, the results highlighted a scarcity of research targeting non-traditional learning environments (e.g., technical visits) and that facilitate interactions among learners beyond their own classmates (e.g., industry experts). In this way, the SMS contributes by revealing LX design technologies, LX design elements, relevant constructs/theories, computational systems, environments, contexts, and other related factors, thereby enhancing the understanding of optimal learning experiences within computational learning systems.
{"title":"A Systematic Mapping Study about Learner Experience Design in Computational Systems","authors":"Deivid E. S. Silva, Tayana Conte, Natasha M. C. Valentim","doi":"10.15388/infedu.2024.12","DOIUrl":"https://doi.org/10.15388/infedu.2024.12","url":null,"abstract":"Contemporary society is characterized by diversity and intricacy, necessitating more meaningful learning experiences. To meet these evolving needs, the incorporation of computational systems into education must acknowledge the distinctive characteristics of learners. Therefore, we conducted a Systematic Mapping Study (SMS) to investigate technologies that support the Learner eXperience (LX) design in computational systems. LX refers to learners’ perceptions, reactions, and achievements while engaging with learning resources, encompassing digital games, simulations, and multimedia. The SMS results uncovered distinct LX design technologies, with a noticeable inclination towards learner-centric strategies. Interestingly, the results highlighted a scarcity of research targeting non-traditional learning environments (e.g., technical visits) and that facilitate interactions among learners beyond their own classmates (e.g., industry experts). In this way, the SMS contributes by revealing LX design technologies, LX design elements, relevant constructs/theories, computational systems, environments, contexts, and other related factors, thereby enhancing the understanding of optimal learning experiences within computational learning systems.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135536599","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}
Marcelo Fernando Rauber, Christiane Gresse von Wangenheim, Pedro Alberto Barbetta, Adriano Ferreti Borgatto, Ramon Mayor Martins, Jean Carlo Rossa Hauck
The insertion of Machine Learning (ML) in everyday life demonstrates the importance of popularizing an understanding of ML already in school. Accompanying this trend arises the need to assess the students’ learning. Yet, so far, few assessments have been proposed, most lacking an evaluation. Therefore, we evaluate the reliability and validity of an automated assessment of the students’ learning of an image classification model created as a learning outcome of the “ML for All!” course. Results based on data collected from 240 students indicate that the assessment can be considered reliable (coefficient Omega = 0.834/Cronbach's alpha α=0.83). We also identified moderate to strong convergent and discriminant validity based on the polychoric correlation matrix. Factor analyses indicate two underlying factors “Data Management and Model Training” and “Performance Interpretation”, completing each other. These results can guide the improvement of assessments, as well as the decision on the application of this model in order to support ML education as part of a comprehensive assessment.
机器学习(ML)在日常生活中的应用证明了在学校普及机器学习知识的重要性。伴随这种趋势而来的是评估学生学习的需要。然而，到目前为止，提出的评估很少，大多数都缺乏评估。因此，我们评估了学生学习图像分类模型的自动评估的可靠性和有效性，该模型是作为“ML for All!””课程。根据240名学生的数据，测评结果可以认为是可靠的(系数Omega = 0.834/Cronbach's α=0.83)。我们还根据多元相关矩阵确定了中度到强的收敛效度和判别效度。因子分析表明，“数据管理与模型训练”和“绩效解释”两个潜在因素是相互补充的。这些结果可以指导评估的改进，以及该模型应用的决定，以支持ML教育作为综合评估的一部分。
{"title":"Reliability and Validity of an Automated Model for Assessing the Learning of Machine Learning in Middle and High School: Experiences from the “ML for All!” course","authors":"Marcelo Fernando Rauber, Christiane Gresse von Wangenheim, Pedro Alberto Barbetta, Adriano Ferreti Borgatto, Ramon Mayor Martins, Jean Carlo Rossa Hauck","doi":"10.15388/infedu.2024.10","DOIUrl":"https://doi.org/10.15388/infedu.2024.10","url":null,"abstract":"The insertion of Machine Learning (ML) in everyday life demonstrates the importance of popularizing an understanding of ML already in school. Accompanying this trend arises the need to assess the students’ learning. Yet, so far, few assessments have been proposed, most lacking an evaluation. Therefore, we evaluate the reliability and validity of an automated assessment of the students’ learning of an image classification model created as a learning outcome of the “ML for All!” course. Results based on data collected from 240 students indicate that the assessment can be considered reliable (coefficient Omega = 0.834/Cronbach's alpha α=0.83). We also identified moderate to strong convergent and discriminant validity based on the polychoric correlation matrix. Factor analyses indicate two underlying factors “Data Management and Model Training” and “Performance Interpretation”, completing each other. These results can guide the improvement of assessments, as well as the decision on the application of this model in order to support ML education as part of a comprehensive assessment.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135536056","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}
Teaching programming is a complex process requiring learning to develop different skills. To minimize the challenges faced in the classroom, instructors have been adopting active methodologies in teaching computer programming. This article presents a Systematic Mapping Study (SMS) to identify and categorize the types of methodologies that instructors have adopted for teaching programming. We evaluated 3,850 papers published from 2000 to 2022. The results provide an overview and comprehensive view of active learning methodologies employed in teaching programming, technologies, programming languages, and the metrics used to observe student learning in this context. In the results, we identified thirty-seven different ALMs adopted by instructors. We realized that seventeen publications describe teaching approaches that combine more than one ALM, and the most reported methodologies in the studies are Flipped Classroom and Gamification-Based Learning. In addition, we are proposing an educational and collaborative tool called CollabProg, which summarizes the primary active learning methodologies identified in this SMS. CollabProg will assist instructors in selecting appropriate ALMs that align with their pedagogical requirements and teaching programming context.
{"title":"Active Learning Methodologies for Teaching Programming in Undergraduate Courses: A Systematic Mapping Study","authors":"Ivanilse Calderon, Williamson Silva, Eduardo Feitosa","doi":"10.15388/infedu.2024.11","DOIUrl":"https://doi.org/10.15388/infedu.2024.11","url":null,"abstract":"Teaching programming is a complex process requiring learning to develop different skills. To minimize the challenges faced in the classroom, instructors have been adopting active methodologies in teaching computer programming. This article presents a Systematic Mapping Study (SMS) to identify and categorize the types of methodologies that instructors have adopted for teaching programming. We evaluated 3,850 papers published from 2000 to 2022. The results provide an overview and comprehensive view of active learning methodologies employed in teaching programming, technologies, programming languages, and the metrics used to observe student learning in this context. In the results, we identified thirty-seven different ALMs adopted by instructors. We realized that seventeen publications describe teaching approaches that combine more than one ALM, and the most reported methodologies in the studies are Flipped Classroom and Gamification-Based Learning. In addition, we are proposing an educational and collaborative tool called CollabProg, which summarizes the primary active learning methodologies identified in this SMS. CollabProg will assist instructors in selecting appropriate ALMs that align with their pedagogical requirements and teaching programming context.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135537425","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}
This study investigates the effect of programming courses on the computational thinking (CT) skills of elementary school students and the learning effectiveness of students from different backgrounds who are studying programming. We designed a OwlSpace programming course into an elementary school curriculum. Students in fourth and fifth grades were taught the fundamentals of programming. We measured and analyzed the effectiveness of their CT skills and self-efficacy in CT. The researchers analyzed the changes in the CT of different gender, different grade, and different past experience students in programming courses and then made specific recommendations for information technigy teachers and related units. The results demonstrate that students learned and improved their CT skills by taking OwlSpace programming course. Additionally, gender, grade, and past experience are found to have no impact on the students’ learning that means the course can improve students ability without limited any characteristics.
{"title":"Effect of an OwlSpace Programming Course on the Computational Thinking of Elementary School Students","authors":"Wei-Ying Li, Lu Tzu-Chuen","doi":"10.15388/infedu.2024.07","DOIUrl":"https://doi.org/10.15388/infedu.2024.07","url":null,"abstract":"This study investigates the effect of programming courses on the computational thinking (CT) skills of elementary school students and the learning effectiveness of students from different backgrounds who are studying programming. We designed a OwlSpace programming course into an elementary school curriculum. Students in fourth and fifth grades were taught the fundamentals of programming. We measured and analyzed the effectiveness of their CT skills and self-efficacy in CT. The researchers analyzed the changes in the CT of different gender, different grade, and different past experience students in programming courses and then made specific recommendations for information technigy teachers and related units. The results demonstrate that students learned and improved their CT skills by taking OwlSpace programming course. Additionally, gender, grade, and past experience are found to have no impact on the students’ learning that means the course can improve students ability without limited any characteristics.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76272039","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}
When it comes to mastering the digital world, the education system is more and more facing the task of making students competent and self-determined agents when interacting with digital artefacts. This task often falls to computing education. In the traditional fields of computing education, a plethora of models, guidelines, and principles exist, which help scholars and teachers identify what the relevant aspects are and which of them one should cover in the classroom. When it comes to explaining the world of digital artefacts, however, there is hardly any such guiding model. The ARIadne model introduced in this paper provides a means of explanation and exploration of digital artefacts which help teachers and students to do a subject analysis of digital artefacts by scrutinizing them from several perspectives. Instead of artificially separating aspects which target the same phenomena within different areas of education (like computing, ICT or media education), the model integrates technological aspects of digital artefacts and the relevant societal discourses of their usage, their impacts and the reasons behind their development into a coherent explanation model.
{"title":"ARIadne – An Explanation Model for Digital Artefacts","authors":"Felix Winkelnkemper, Lukas Höper, Carsten Schulte","doi":"10.15388/infedu.2024.09","DOIUrl":"https://doi.org/10.15388/infedu.2024.09","url":null,"abstract":"When it comes to mastering the digital world, the education system is more and more facing the task of making students competent and self-determined agents when interacting with digital artefacts. This task often falls to computing education. In the traditional fields of computing education, a plethora of models, guidelines, and principles exist, which help scholars and teachers identify what the relevant aspects are and which of them one should cover in the classroom. When it comes to explaining the world of digital artefacts, however, there is hardly any such guiding model. The ARIadne model introduced in this paper provides a means of explanation and exploration of digital artefacts which help teachers and students to do a subject analysis of digital artefacts by scrutinizing them from several perspectives. Instead of artificially separating aspects which target the same phenomena within different areas of education (like computing, ICT or media education), the model integrates technological aspects of digital artefacts and the relevant societal discourses of their usage, their impacts and the reasons behind their development into a coherent explanation model.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89851591","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}
Sabiha Yeni, Nataša Grgurina, Mara Saeli, F. Hermans, J. Tolboom, E. Barendsen
There is an increasing interest in the integration of computational thinking (CT) in the K-12 curriculum. By integrating CT into other disciplines, the aim is to equip students with essential skills to navigate domain-specific challenges. This study conducts a systematic review of 108 peer-reviewed scientific papers to analyze in which K-12 subjects CT is being integrated, learning objectives, CT integration levels, instructional strategies, technologies and tools employed, assessment strategies, research designs and educational stages of participants. The findings reveal that: (a) over two-thirds of the CT integration studies predominantly focus on science and mathematics; (b) the majority of the studies implement CT at the substitution level rather than achieving a transformation impact; (c) active learning is a commonly mentioned instructional strategy, with block-based languages and physical devices being frequently utilized tools; (d) in terms of assessment, the emphasis primarily lies in evaluating attitudes towards technology or the learning context, rather than developing valid and reliable assessment instruments. These findings shed light on the current state of CT integration in K-12 education. The identified trends provide valuable insights for educators, curriculum designers, and policymakers seeking to effectively incorporate CT across various disciplines in a manner that fosters meaningful skill development with an interdisciplinary approach. By leveraging these insights, we can strive to enhance CT integration efforts, ensuring the holistic development of students' computational thinking abilities and promoting their preparedness for the increasingly interdisciplinary domains of digital world.
{"title":"Interdisciplinary Integration of Computational Thinking in K-12 Education: A Systematic Review","authors":"Sabiha Yeni, Nataša Grgurina, Mara Saeli, F. Hermans, J. Tolboom, E. Barendsen","doi":"10.15388/infedu.2024.08","DOIUrl":"https://doi.org/10.15388/infedu.2024.08","url":null,"abstract":"There is an increasing interest in the integration of computational thinking (CT) in the K-12 curriculum. By integrating CT into other disciplines, the aim is to equip students with essential skills to navigate domain-specific challenges. This study conducts a systematic review of 108 peer-reviewed scientific papers to analyze in which K-12 subjects CT is being integrated, learning objectives, CT integration levels, instructional strategies, technologies and tools employed, assessment strategies, research designs and educational stages of participants. The findings reveal that: (a) over two-thirds of the CT integration studies predominantly focus on science and mathematics; (b) the majority of the studies implement CT at the substitution level rather than achieving a transformation impact; (c) active learning is a commonly mentioned instructional strategy, with block-based languages and physical devices being frequently utilized tools; (d) in terms of assessment, the emphasis primarily lies in evaluating attitudes towards technology or the learning context, rather than developing valid and reliable assessment instruments. These findings shed light on the current state of CT integration in K-12 education. The identified trends provide valuable insights for educators, curriculum designers, and policymakers seeking to effectively incorporate CT across various disciplines in a manner that fosters meaningful skill development with an interdisciplinary approach. By leveraging these insights, we can strive to enhance CT integration efforts, ensuring the holistic development of students' computational thinking abilities and promoting their preparedness for the increasingly interdisciplinary domains of digital world.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81514259","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}
Evmorfia-Iro Bartzia, Michael Lodi, M. Sbaraglia, Simon Modeste, Viviane Durand-Guerrier, S. Martini
In this paper, we present an activity to introduce the idea of public-key cryptography and to make pre-service STEM teachers explore fundamental informatics and mathematical concepts and methods. We follow the Theory of Didactical Situations within the Didactical Engineering methodology (both widely used in mathematics education research) to design and analyse a didactical situation about asymmetric cryptography using graphs. Following the phases of Didactical Engineering, after the preliminary analysis of the content, the constraints and conditions of the teaching context, we conceived and analysed the situation a priori, with a particular focus on the milieu (the set of elements students can interact with) and on the choices for the didactical variables. We discuss their impact on the problem-solving strategies the participants need to elaborate to decrypt an encrypted message. We implemented our situation and collected qualitative data. We then analysed a posteriori the different stategies that participants used. The comparison of the a posteriori analysis with the a priori analysis showed the learning potential of the activity. To elaborate on different problem-solving strategies, the participants need to explore and understand several concepts and methods from mathematics, informatics, and the frontier of the two disciplines, also moving between different semiotic registers.
{"title":"An Unplugged Didactical Situation on Cryptography between Informatics and Mathematics","authors":"Evmorfia-Iro Bartzia, Michael Lodi, M. Sbaraglia, Simon Modeste, Viviane Durand-Guerrier, S. Martini","doi":"10.15388/infedu.2024.06","DOIUrl":"https://doi.org/10.15388/infedu.2024.06","url":null,"abstract":"In this paper, we present an activity to introduce the idea of public-key cryptography and to make pre-service STEM teachers explore fundamental informatics and mathematical concepts and methods. We follow the Theory of Didactical Situations within the Didactical Engineering methodology (both widely used in mathematics education research) to design and analyse a didactical situation about asymmetric cryptography using graphs. Following the phases of Didactical Engineering, after the preliminary analysis of the content, the constraints and conditions of the teaching context, we conceived and analysed the situation a priori, with a particular focus on the milieu (the set of elements students can interact with) and on the choices for the didactical variables. We discuss their impact on the problem-solving strategies the participants need to elaborate to decrypt an encrypted message. We implemented our situation and collected qualitative data. We then analysed a posteriori the different stategies that participants used. The comparison of the a posteriori analysis with the a priori analysis showed the learning potential of the activity. To elaborate on different problem-solving strategies, the participants need to explore and understand several concepts and methods from mathematics, informatics, and the frontier of the two disciplines, also moving between different semiotic registers.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88744398","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}
Marjahan Begum, Pontus Haglund, Ari Korhonen, Violetta Lonati, Mattia Monga, Filip Strömbäck, Artturi Tilanterä
There can be many reasons why students fail to answer correctly to summative tests in advanced computer science courses: often the cause is a lack of prerequisites or misconceptions about topics presented in previous courses. One of the ITiCSE 2020 working groups investigated the possibility of designing assessments suitable for differentiating between fragilities in prerequisites (in particular, knowledge and skills related to introductory programming courses) and advanced topics. This paper reports on an empirical evaluation of an instrument focusing on data structures, among those proposed by the ITiCSE working group. The evaluation aimed at understanding what fragile knowledge and skills the instrument is actually able to detect and to what extent it is able to differentiate them. Our results support that the instrument is able to distinguish between some specific fragilities (e.g., value vs. reference semantics), but not all of those claimed in the original report. In addition, our findings highlight the role of relevant skills at a level between prerequisite and advanced skills, such as program comprehension and reasoning about constraints. We also suggest ways to improve the questions in the instrument, both by improving the distractors of the multiple choice questions, and by slightly changing the content or phrasing of the questions. We argue that these improvements will increase the effectiveness of the instrument in assessing prerequisites as a whole, but also to pinpoint specific fragilities.
{"title":"Empirical Evaluation of a Differentiated Assessment of Data Structures: The Role of Prerequisite Skills","authors":"Marjahan Begum, Pontus Haglund, Ari Korhonen, Violetta Lonati, Mattia Monga, Filip Strömbäck, Artturi Tilanterä","doi":"10.15388/infedu.2024.05","DOIUrl":"https://doi.org/10.15388/infedu.2024.05","url":null,"abstract":"There can be many reasons why students fail to answer correctly to summative tests in advanced computer science courses: often the cause is a lack of prerequisites or misconceptions about topics presented in previous courses. One of the ITiCSE 2020 working groups investigated the possibility of designing assessments suitable for differentiating between fragilities in prerequisites (in particular, knowledge and skills related to introductory programming courses) and advanced topics. This paper reports on an empirical evaluation of an instrument focusing on data structures, among those proposed by the ITiCSE working group. The evaluation aimed at understanding what fragile knowledge and skills the instrument is actually able to detect and to what extent it is able to differentiate them. Our results support that the instrument is able to distinguish between some specific fragilities (e.g., value vs. reference semantics), but not all of those claimed in the original report. In addition, our findings highlight the role of relevant skills at a level between prerequisite and advanced skills, such as program comprehension and reasoning about constraints. We also suggest ways to improve the questions in the instrument, both by improving the distractors of the multiple choice questions, and by slightly changing the content or phrasing of the questions. We argue that these improvements will increase the effectiveness of the instrument in assessing prerequisites as a whole, but also to pinpoint specific fragilities.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75746848","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}
Educational data mining is widely deployed to extract valuable information and patterns from academic data. This research explores new features that can help predict the future performance of undergraduate students and identify at-risk students early on. It answers some crucial and intuitive questions that are not addressed by previous studies. Most of the existing research is conducted on data from 2-3 years in an absolute grading scheme. We examined the effects of historical academic data of 15 years on predictive modeling. Additionally, we explore the performance of undergraduate students in a relative grading scheme and examine the effects of grades in core courses and initial semesters on future performances. As a pilot study, we analyzed the academic performance of Computer Science university students. Many exciting discoveries were made; the duration and size of the historical data play a significant role in predicting future performance, mainly due to changes in curriculum, faculty, society, and evolving trends. Furthermore, predicting grades in advanced courses based on initial pre-requisite courses is challenging in a relative grading scheme, as students’ performance depends not only on their efforts but also on their peers. In short, educational data mining can come to the rescue by uncovering valuable insights from academic data to predict future performance and identify the critical areas that need significant improvement.
{"title":"Enhancing Student Performance Prediction via Educational Data Mining on Academic data","authors":"Z. Alamgir, Habiba Akram, S. Karim, Aamir Wali","doi":"10.15388/infedu.2024.04","DOIUrl":"https://doi.org/10.15388/infedu.2024.04","url":null,"abstract":"Educational data mining is widely deployed to extract valuable information and patterns from academic data. This research explores new features that can help predict the future performance of undergraduate students and identify at-risk students early on. It answers some crucial and intuitive questions that are not addressed by previous studies. Most of the existing research is conducted on data from 2-3 years in an absolute grading scheme. We examined the effects of historical academic data of 15 years on predictive modeling. Additionally, we explore the performance of undergraduate students in a relative grading scheme and examine the effects of grades in core courses and initial semesters on future performances. As a pilot study, we analyzed the academic performance of Computer Science university students. Many exciting discoveries were made; the duration and size of the historical data play a significant role in predicting future performance, mainly due to changes in curriculum, faculty, society, and evolving trends. Furthermore, predicting grades in advanced courses based on initial pre-requisite courses is challenging in a relative grading scheme, as students’ performance depends not only on their efforts but also on their peers. In short, educational data mining can come to the rescue by uncovering valuable insights from academic data to predict future performance and identify the critical areas that need significant improvement.","PeriodicalId":45270,"journal":{"name":"Informatics in Education","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81624307","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：