Visual Learning Analytics of Multidimensional Student Behavior in Self-regulated Learning
| Autor: | Rafael Messias Martins, Elias Berge, Marcelo Milrad, Italo Masiello |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Learning environment 05 social sciences Exploratory research 050109 social psychology Machine learning computer.software_genre 050105 experimental psychology Exploratory data analysis Analytics 0501 psychology and cognitive sciences Artificial intelligence business Self-regulated learning Cluster analysis Visual learning computer Formal learning |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030297350 EC-TEL |
| DOI: | 10.1007/978-3-030-29736-7_78 |
| Popis: | In Self-Regulated Learning (SLR), the lack of a predefined, formal learning trajectory makes it more challenging to assess students’ progress (e.g. by comparing it to specific baselines) and to offer relevant feedback and scaffolding when appropriate. In this paper we describe a Visual Learning Analytics (VLA) solution for exploring students’ datasets collected in a Web-Based Learning Environment (WBLE). We employ mining techniques for the analysis of multidimensional data, such as t-SNE and clustering, in an exploratory study for identifying patterns of students with similar study behavior and interests. An example use case is presented as evidence of the effectiveness of our proposed method, with a dataset of learning behaviors of 6423 students who used an online study tool during 18 months. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|