Can Interaction Patterns with Supplemental Study Tools Predict Outcomes in CS1?

Estey, Anthony; Coady, Yvonne

doi:10.1145/2899415.2899428

Cited by 28 publications

(35 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…O trabalho de [Estey and Coady 2016] apresentou o BitFit 2 , uma ferramenta desenvolvida para que alunos de turmas IPC possam fazer atividades semanais. A ferramenta, além de ser um ACAC, disponibiliza uma série progressiva de dicas para cada atividade.…”

Section: Trabalhos Relacionadosunclassified

“…Para ilustrar, o método proposto alcançou nas duas primeiras semanas acurácia de 78.3% no experimento 1 e 72.8% no experimento 2, enquanto que [Leinonen et al 2016] obtiveram sua maior acurácia na semana 8, sendo 71,8%. Já [Estey and Coady 2016] atingiu 81% de taxa média de reconhecimento de alunos na ZD ao longo do experimento, entretanto os autores obtiveram 30% nas duas primeiras semanas de aula, enquanto o método proposto atingiu 79,3% de recall negativo da sessão 1 do experimento 2. Vale mencionar que os métodos propostos por [Leinonen et al 2016, Estey andCoady 2016] foram aplicados em bases de dados diferentes desta pesquisa.…”

Section: Figura 3 Quantidade De Alunos Na Ze E Zd Em Cada Sessãounclassified

“…Já [Estey and Coady 2016] atingiu 81% de taxa média de reconhecimento de alunos na ZD ao longo do experimento, entretanto os autores obtiveram 30% nas duas primeiras semanas de aula, enquanto o método proposto atingiu 79,3% de recall negativo da sessão 1 do experimento 2. Vale mencionar que os métodos propostos por [Leinonen et al 2016, Estey andCoady 2016] foram aplicados em bases de dados diferentes desta pesquisa. Entretanto, ambos foram realizados em cenários educacionais semelhantes ao deste estudo.…”

Section: Figura 3 Quantidade De Alunos Na Ze E Zd Em Cada Sessãounclassified

See 2 more Smart Citations

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

Section: Trabalhos Relacionadosunclassified

Section: Figura 3 Quantidade De Alunos Na Ze E Zd Em Cada Sessãounclassified

See 1 more Smart Citation

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

show abstract

“…As an optional feature, students could use a series of hints that progressively lead them through each question, and the final hint provided a full sample solution. Our previous work [5] provides more detailed information about the features present in the learning tool, including the types of hints and exercises provided.…”

Section: Data Collectionmentioning

confidence: 99%

“…Previous work on predictors of success in CS1 suggest that low-performing students, who tend not to recover, can be identified within the first few weeks of the semester [1,5]. Studies on debugging proficiency [8,11,12,20] and study behaviour [4,6,16] have also shown how patterns in log data can be used to accurately predict student performance.…”

Section: Introductionmentioning

confidence: 99%

Automatically Classifying Students in Need of Support by Detecting Changes in Programming Behaviour

Estey

Keuning

Coady

2017

Proceedings of the 2017 ACM SIGCSE Technical Symposium on Computer Science Education

Self Cite

View full text Add to dashboard Cite

Educational research has established that learning can be defined as an enduring change in behaviour, which results from practice or other forms of experience. In introductory programming courses, proficiency is typically approximated through relatively small but frequent assignments and tests. Scaling these assessments to track significant behavioural change is challenging due to the subtle and complex metrics that must be collected from large student populations. Based on a four-semester study, we present an analysis of learning tool interaction data collected from 514 students and 38,796 solutions to practice programming exercises. We first evaluate the effectiveness of measuring workflow patterns to detect students at-risk of failure within the first three weeks of the semester. Our early predictor analysis accurately detects 81% of the students who struggle throughout the course. However, our early predictor also captures transient struggling, as 43% of the students who ultimately did well in the course were classified as at-risk. In order to better differentiate sustained versus transient struggling, we further propose a trajectory metric which measures changes in programming behaviour. The trajectory metric detects 70% of the students who exhibit sustained struggling, and mis-classifies only 11% of students who go on to succeed in the course. Overall, our results show how detecting changes in programming behaviour can help us differentiate between learning and struggling in CS1.

show abstract

Predicting student performance in computing courses based on programming behavior

Araya

Beas

Stamulis

et al. 2022

Comp Applic In Engineering

View full text Add to dashboard Cite

In the context of programming language courses, offering early and personalized assistance to students with difficulties in solving code exercises is fundamental to helping them improve their performance. To this end, it is desirable to detect those students with behavioral patterns that could potentially result in poor performance in a timely manner. In this study, we analyze different behavioral metrics for predicting the performance of students in a 2nd-year computer science course. Metrics are extracted from practical sessions, that is, code exercise labs that may be finished online during a period of 5-7 days. In addition to well-known metrics (e.g., the relative time spent solving compilation/execution errors or skills for removing compilation errors), we also incorporate metrics that take into account the work habits of students (e.g., timestamps in which the student has undertaken 25%, 50%, and 75% of the exercise lab) and similarity between codes. With a sample of 224 students from seven different course groups, we construct robust

show abstract

Can Interaction Patterns with Supplemental Study Tools Predict Outcomes in CS1?

Cited by 28 publications

References 15 publications

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

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

Automatically Classifying Students in Need of Support by Detecting Changes in Programming Behaviour

Predicting student performance in computing courses based on programming behavior

Contact Info

Product

Resources

About