Programming Pluralism: Using Learning Analytics to Detect Patterns in the Learning of Computer Programming

Blikstein, Paulo; Worsley, Marcelo; Piech, Chris; Sahami, Mehran; Cooper, Steven H.; Koller, Daphne

doi:10.1080/10508406.2014.954750

Cited by 229 publications

(116 citation statements)

References 43 publications

Supporting

Mentioning

102

Contrasting

Unclassified

Order By: Relevance

“…For example, we expected that one state might have been characterised by the engagement with the module videos and the annotation tool, but not beyond the level of the module requirements, thus corresponding to the satisfying module requirements strategy (identified in the clustering step). Even though HMM is based on the assumption that the next state depends only on the immediate previous state, which in the context of learning is not entirely correct, it has been shown that this statistical simplification leads to models that capture meaningful patterns and offer predictions of student behaviour (e.g., Blikstein et al, 2014;Jeong et al, 2010). The HMM provides a transition matrix with the probabilities of the transitions among states (including continued stay in the same state), so that in each module and for each user we can estimate how likely it is that they will keep the same or change their learning strategy.…”

Section: Data Collection and Analysis Methodsmentioning

confidence: 99%

“…To extract learning strategies from the collected trace data, we relied on unsupervised statistical methods, such as clustering and hidden Markov models, which have proven beneficial for mining latent, unobservable constructs from learning traces (e.g., Blikstein et al, 2014;Kovanović, Gašević, Joksimović, Hatala, & Adesope, 2015;Lust et al, 2013a).…”

Section: Self-regulated Learning and Learning Strategiesmentioning

confidence: 99%

See 1 more Smart Citation

Identifying engagement patterns with video annotation activities: A case study in professional development

Mirriahi

Jovanović

Dawson

et al. 2018

AJET

View full text Add to dashboard Cite

The rapid growth of blended and online learning models in higher education has resulted in a parallel increase in the use of audio-visual resources among students and teachers. Despite the heavy adoption of video resources, there have been few studies investigating their effect on learning processes and even less so in the context of academic development. This paper uses learning analytic techniques to examine how academic teaching staff engage with a set of prescribed videos and video annotations in a professional development course. The data was collected from two offerings of the course at a large research-intensive university in Australia. The data was used to identify patterns of activity and transition states as users engaged with the course videos and video annotations. Latent class analysis and hidden Markov models were used to characterise the evolution of engagement throughout the course. The results provide a detailed description of the evolution of learner engagement that can be readily translated into action aimed at increasing the quality of the learning experience.

show abstract

Section: Data Collection and Analysis Methodsmentioning

confidence: 99%

Section: Self-regulated Learning and Learning Strategiesmentioning

confidence: 99%

Identifying engagement patterns with video annotation activities: A case study in professional development

Mirriahi

Jovanović

Dawson

et al. 2018

AJET

View full text Add to dashboard Cite

show abstract

“…The data we use in our study is higher resolution, allowing us to examine coding behaviour at the keystroke, rather than the compile event level. Blikstein et al describe a range of metrics that can be automatically extracted from IDE code snapshots, and use them to characterise student coding behaviour [21]. The techniques included observing the sizes of changes in the programs over time using abstract syntax trees.…”

Section: Analysing Coding Behaviourmentioning

confidence: 99%

Evidencing the Value of Inquiry Based, Constructionist Learning for Student Coders

2017

View full text Add to dashboard Cite

Abstract-For the last decade, there has been growing interest in the STEAM approach (essentially combining methods and practices in arts, humanities and social sciences into STEM teaching and research) with its potential to deliver better research and education, and to enable us to produce students who can work more effectively in the current and developing market-place. However, despite this interest, there seems to be little quantitative evidence of the true power of STEAM learning, especially describing how it compares and performs with respect to more established approaches. To address this, we present a comparative, quantitative study of two distinct approaches to teaching programming, one based on STEAM (with an open-ended inquiry-driven, inductive approach), the other based on a more traditional, non-STEAM approach (where constrained problems are set and solved deductively). Our key results evidence how students exhibit different styles of programming in different types of lessons and, crucially, that students who tend to exhibit more of the style of programming observed in our STEAM lessons also tend to achieve higher grades. We present our claims through a range of visualisations and statistical validations which clearly show the significance of the results, despite the small scale of the study. We believe that this work provides clear evidence for the advantages of STEAM over non-STEAM, and provides a strong theoretical and technological framework for future, larger studies.Keywords-STEAM; xAPI; coding; education; pedagogy IntroductionOver the last 10 years, we have developed and delivered a range of degree programmes at our institution that aim to bring an arts inflected pedagogy into the teaching of computer science. We make extensive use of what is considered a STEAM approach to engineering education [1], an approach we describe in detail later in the paper. Over the last decade, we have seen how a range of employers, especially from the creative industries, are keen to employ graduates from our courses. Anecdotally, the graduates demonstrate a more creative and experimental approach to engineering, and are able to adapt quickly to using new technologies in new settings.But anecdotal evidence is not enough. We would like to know the measurable impact, if any, this pedagogical approach actually has on student learning. Do students iJEP -Vol. 7, No. 3, 2017 109Paper-Evidencing the Value of Inquiry Based, Constructionist Learning for Student Coders learn to code in a different way with this approach, compared to more traditional approaches? If they do, does this impact positively upon learning outcomes? In this paper, we set out to investigate these questions, as we find there is a lack of research explicitly comparing how different pedagogical approaches impact on the way students learn programming. Our first step towards addressing this apparent gap in knowledge has been to design and deploy a novel technological platform for teaching programming. The system has been designed to support our teachin...

show abstract

“…Dessa forma, os tipos de análises possibilitadas por tais dados permitem que o docente não avalie tão somente o produto enviado pelo aluno, mas todo o processo por trás dele, ou seja, permite uma avaliação formativa [Blikstein et al 2014].…”

Section: Introductionunclassified

Predição de Zona de Aprendizagem de Alunos de Introdução à Programação em Ambientes de Correção Automática de Código

Dwan

Oliveira

Fernandes

2017

Anais Do XXVIII Simpósio Brasileiro De Informática Na Educação (SBIE 2017)

View full text Add to dashboard Cite

Abstract. The present work proposes and validates a method to infer the learning zone of CS1 students in an online judge. To do so, the student's grade will be predicted, using a programming profile based on the data left by them as they solve exercises in that system. Students who scored lower than 5 were classified in a difficulty zone, otherwise in an expertise zone. Machine learning algorithms were used to make the prediction. The proposed predictive model obtained an accuracy of 78.3 % at the first two weeks of class, which overcomes research results that were conducted in similar scenarios.

show abstract

Programming Pluralism: Using Learning Analytics to Detect Patterns in the Learning of Computer Programming

Cited by 229 publications

References 43 publications

Identifying engagement patterns with video annotation activities: A case study in professional development

Identifying engagement patterns with video annotation activities: A case study in professional development

Evidencing the Value of Inquiry Based, Constructionist Learning for Student Coders

Predição de Zona de Aprendizagem de Alunos de Introdução à Programação em Ambientes de Correção Automática de Código

Contact Info

Product

Resources

About