Call aus der „Society for Learning Analytics Research“ Webseite

Learning analytics is an interdisciplinary and inclusive field that brings together technologists, psychologists, data scientists, learning scientists, educational domain content experts, and measurement specialists. For all of the strength that comes from such diversity, there are also potential pitfalls when it comes to establishing norms for methodological work. Clow (2013) has described learning analytics as, “a ‘jackdaw’ field of enquiry, picking up ‘shiny’ techniques, tools and methodologies… This eclectic approach is both a strength and a weakness: it facilitates rapid development and the ability to build on established practice and findings, but it—to date—lacks a coherent, articulated epistemology of its own.” For this special section, we call on researchers to focus critical attention on the methods we choose to use, on how we use them, and on how we interrogate these uses in learning analytics.

TOPICS OF INTEREST
We imagine two broad classes of papers, those that take a deep dive into particular use cases and others that take a field-level view on how we should think and talk about methodology in learning analytics.

Papers in the first category should be distinguished from tutorials and from applied research papers in the degree to which they investigate the methods themselves. Manuscripts should incorporate multiple data sets (possibly supplementing real data with simulated data), multiple variations of methodology within a dataset, or both. Topics may include, but are not limited to:

• demarcating assumptions, limitations, and practical boundaries of applicability,
• exploring quality of fit, sensitivity, consequences of operationalization, etc.
• addressing pitfalls, trade-offs, and consequences of “misuse”
• metrics for model evaluation and for comparison of results where multiple models are used

Topics for papers in the second category (field-level) may include, but are not limited to:

• Processes for developing methodological frameworks for learning analytics
• Framing and prioritizing methodological issues for the community
• Community guidelines regarding communication and replicability
• Transferability of methods for different types of data

Weitere Informationen können der kompletten Ausschreibung entnommen werden.