The Transition Matrix -- A classification of navigational patterns between LMS course sections

• URL: http://arxiv.org/abs/2506.13275v1
• Date: Mon, 16 Jun 2025 09:14:20 GMT
• Title: The Transition Matrix -- A classification of navigational patterns between LMS course sections
• Authors: Tobias Hildebrandt, Lars Mehnen,
• Abstract summary: This study analyzes navigational data from 747 courses in the Moodle LMS at a technical university of applied sciences.<n>Findings include that many of the generated heatmap include one or more diagonal axis, indicating that students typically navigate from the current to the next or previous section.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning management systems (LMS) like Moodle are increasingly used to support university teaching. As Moodle courses become more complex, incorporating diverse interactive elements, it is important to understand how students navigate through course sections and whether course designs are meeting student needs. While substantial research exists on student usage of individual LMS elements, there is a lack of research on broader navigational patterns between course sections and how these patterns differ across courses. This study analyzes navigational data from 747 courses in the Moodle LMS at a technical university of applied sciences, representing (after filtering) around 4,400 students and 1.8 million logged events. By mapping section names across a large sample of courses, the analysis enables cross-course comparisons of student navigational sequences between sections. Transition matrices and heat map visualizations are used to identify common navigational patterns. Findings include that many of the generated heatmap include one or more diagonal axis, indicating that students typically navigate from the current to the next or previous section. More fine-grained patterns show typical behavior for blended learning scenarios. Other patterns include dominant sections.

Related papers

• Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images [58.38037252899024]
  We present a system using Multimodal LLMs to analyze a large database with tens of millions of images.<n>We aim to capture frequent co-occurring changes ("trends") across a city over a certain period.<n>We find it significantly outperforms baselines and is able to discover interesting trends from images captured in large cities.
  arXiv  Detail & Related papers  (2025-04-11T17:55:45Z)
• Context-Enhanced Multi-View Trajectory Representation Learning: Bridging the Gap through Self-Supervised Models [27.316692263196277]
  MVTraj is a novel multi-view modeling method for trajectory representation learning. It integrates diverse contextual knowledge, from GPS to road network and points-of-interest to provide a more comprehensive understanding of trajectory data. Extensive experiments on real-world datasets demonstrate that MVTraj significantly outperforms existing baselines in tasks associated with various spatial views.
  arXiv  Detail & Related papers  (2024-10-17T03:56:12Z)
• Cross-course Process Mining of Student Clickstream Data -- Aggregation and Group Comparison [0.0]
  This paper introduces novel methods for analyzing student interaction data extracted from course management systems like Moodle. We present a method for standardizing section labels across courses, cross-course analysis to uncover broader usage patterns.
  arXiv  Detail & Related papers  (2024-09-04T11:28:02Z)
• MultiCaM-Vis: Visual Exploration of Multi-Classification Model with High Number of Classes [0.2900810893770134]
  We present our interactive visual analytics tool, called MultiCaM-Vis. It provides Emphoverview+detail style parallel coordinate views and a Chord diagram for exploration and inspection of class-level miss-classification of instances.
  arXiv  Detail & Related papers  (2023-09-09T08:55:22Z)
• Self-Supervised Representation Learning With MUlti-Segmental Informational Coding (MUSIC) [6.693379403133435]
  Self-supervised representation learning maps high-dimensional data into a meaningful embedding space. We propose MUlti-Segmental Informational Coding (MUSIC) for self-supervised representation learning.
  arXiv  Detail & Related papers  (2022-06-13T20:37:48Z)
• A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting [42.061275727906256]
  We propose a novel multi-view multi-task (MVMT) learning framework for MTS forecasting. MVMT information is deeply concealed in the MTS data, which severely hinders the model from capturing it naturally. We develop two kinds of basic operations, namely task-wise affine transformation and task-wise normalization, respectively.
  arXiv  Detail & Related papers  (2021-09-02T06:11:26Z)
• Revealing the Hidden Patterns: A Comparative Study on Profiling Subpopulations of MOOC Students [61.58283466715385]
  Massive Open Online Courses (MOOCs) exhibit a remarkable heterogeneity of students. The advent of complex "big data" from MOOC platforms is a challenging yet rewarding opportunity to deeply understand how students are engaged in MOOCs. We report on clustering analysis of student activities and comparative analysis on both behavioral patterns and demographical patterns between student subpopulations in the MOOC.
  arXiv  Detail & Related papers  (2020-08-12T10:38:50Z)
• Exploring Navigation Styles in a FutureLearn MOOC [61.58283466715385]
  This paper presents for the first time a detailed analysis of fine-grained navigation style identification in MOOCs backed by a large number of active learners. It provides insight into online learners' temporal engagement, as well as a tool to identify vulnerable learners.
  arXiv  Detail & Related papers  (2020-08-10T19:12:21Z)
• DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning [83.48587570246231]
  Visual Similarity plays an important role in many computer vision applications. Deep metric learning (DML) is a powerful framework for learning such similarities. We propose and study multiple complementary learning tasks, targeting conceptually different data relationships. We learn a single model to aggregate their training signals, resulting in strong generalization and state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-04-28T12:26:50Z)
• Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer [116.46533207849619]
  We study the impact of scale and location mismatch in the few-shot learning scenario. We propose a novel Spatially-aware Matching scheme to effectively perform matching across multiple scales and locations.
  arXiv  Detail & Related papers  (2020-01-06T14:10:20Z)
• A System for Real-Time Interactive Analysis of Deep Learning Training [66.06880335222529]
  Currently available systems are limited to monitoring only the logged data that must be specified before the training process starts. We present a new system that enables users to perform interactive queries on live processes generating real-time information.
  arXiv  Detail & Related papers  (2020-01-05T11:33:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.