Using Learning Analytics to Investigate Patterns of Performance and Engagement in Large Classes

Khosravi, Hassan; Cooper, Kendra M. L.

doi:10.1145/3017680.3017711

Cited by 34 publications

(22 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The elbow method was used to detect the number of student interaction clusters per cycle through computing and plotting the sum of squared errors in order to identify where the marginal gain drops significantly, producing an angle (elbow) in the graph. In line with existing work (Guo and Reinecke, 2014;Park et al, 2017;Khosravi and Cooper, 2017), we found 3 or 4 clusters (depending on the course, edition, and cycle). We then noticed that, in all clusters, the feature that records course access (i.e., course views) was the most meaningful one to discriminate the clusters.…”

Section: Analysis and Resultssupporting

confidence: 89%

Supporting Instructors in Analyzing Student Logs From Virtual Learning Environments

DAMASCENO¹

View full text Add to dashboard Cite

Section: Analysis and Resultssupporting

confidence: 89%

Supporting Instructors in Analyzing Student Logs From Virtual Learning Environments

DAMASCENO¹

View full text Add to dashboard Cite

“…Several recent systematic literature reviews have been published on LADs [6,41]. Schwendimann et al [41] provide a comprehensive picture of the common data sources that are used by LADS, which include clickstream logs (e.g., [12,14,25,34]), data related to learning artefacts (e.g., [11,16,20,24,45]), survey data (e.g., [4,35,40]), institutional databases (e.g., [9,19,23]), physical user activities (e.g., [16,31,44]) and data captured from external educational technologies (e.g., [10,26,27,36]). To make sense of these data LADs provide a variety of visualisation options.…”

Section: Related Workmentioning

confidence: 99%

Recommending Insightful Drill-Downs Based on Learning Processes for Learning Analytics Dashboards

Shabaninejad

Khosravi

Leemans

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Learning Analytics Dashboards (LADs) make use of rich and complex data about students and their learning activities to assist educators in understanding and making informed decisions about student learning and the design and improvement of learning processes. With the increase in the volume, velocity, variety and veracity of data on students, manual navigation and sense-making of such multi-dimensional data have become challenging. This paper proposes an analytical approach to assist LAD users with navigating the large set of possible drill-down actions to identify insights about learning behaviours of the sub-cohorts. A distinctive feature of the proposed approach is that it takes a process mining lens to examine and compare students' learning behaviours. The process oriented approach considers the flow and frequency of the sequences of performed learning activities, which is increasingly recognised as essential for understanding and optimising learning. We present results from an application of our approach in an existing LAD using a course with 875 students, with high demographic and educational diversity. We demonstrate the insights the approach enables, exploring how the learning behaviour of an identified sub-cohort differs from the remaining students and how the derived insights can be used by instructors.

show abstract

“…Técnicas de agrupamento têm sido usadas para, nos casos de salas de aula numerosas, categorizar os programadores iniciantes usando análise automatizada de registros para revelar padrões na programação dos estudantes [Khosravi e Cooper 2017].…”

Section: Trabalhos Relacionadosunclassified

“…Uma abordagem individualizada por parte dos docentes, dedicando atenção e acompanhamento específico a cada aluno visando mitigar as dificuldades de aprendizado, torna-se inviável pelo fato dessas turmas de CS0 serem habitualmente numerosas [Khosravi e Cooper 2017].…”

Section: Introductionunclassified

Analisando a influência de atributos demográficos no desempenho de estudantes em uma disciplina de introdução à programação

Pereira¹,

Carvalho²,

Souto³

2019

Anais Do Workshop Sobre Educação Em Computação (WEI)

View full text Add to dashboard Cite

O baixo desempenho de alunos em disciplinas introdutórias de programação é cenário comum em cursos de graduação de ciências exatas e de engenharia. Fatores externos ao ambiente acadêmico são tão decisivos em relação aos resultados quanto os aspectos inerentes ao processo de aprendizagem. Com base na aplicação de técnicas de mineração de dados educacionais sobre os dados de uma instituição de ensino superior brasileira, observou-se que o desempenho em uma disciplina de introdução à programação para non-majors está correlacionado a características socioeconômicas e educacionais prévias ou a um subconjunto criado a partir da combinação destes atributos. Por sua vez, identificar antecipadamente estudantes em risco de reprovação pode ajudar a reduzir a evasão em disciplinas de programação.

show abstract

Using Learning Analytics to Investigate Patterns of Performance and Engagement in Large Classes

Cited by 34 publications

References 18 publications

Supporting Instructors in Analyzing Student Logs From Virtual Learning Environments

Supporting Instructors in Analyzing Student Logs From Virtual Learning Environments

Recommending Insightful Drill-Downs Based on Learning Processes for Learning Analytics Dashboards

Analisando a influência de atributos demográficos no desempenho de estudantes em uma disciplina de introdução à programação

Contact Info

Product

Resources

About