A reflective design case of practical micro-ethics in learning analytics     

Simon Knight  Antonette Shibani  Simon Buckingham Shum 《British journal of educational technology : journal of the Council for Educational Technology》2023,54(6):1837-1857

  相似文献   

Using causal models to bridge the divide between big data and educational theory     

Kirsty Kitto  Ben Hicks  Simon Buckingham Shum 《British journal of educational technology : journal of the Council for Educational Technology》2023,54(5):1095-1124

An extraordinary amount of data is becoming available in educational settings, collected from a wide range of Educational Technology tools and services. This creates opportunities for using methods from Artificial Intelligence and Learning Analytics (LA) to improve learning and the environments in which it occurs. And yet, analytics results produced using these methods often fail to link to theoretical concepts from the learning sciences, making them difficult for educators to trust, interpret and act upon. At the same time, many of our educational theories are difficult to formalise into testable models that link to educational data. New methodologies are required to formalise the bridge between big data and educational theory. This paper demonstrates how causal modelling can help to close this gap. It introduces the apparatus of causal modelling, and shows how it can be applied to well-known problems in LA to yield new insights. We conclude with a consideration of what causal modelling adds to the theory-versus-data debate in education, and extend an invitation to other investigators to join this exciting programme of research.

Practitioner notes

What is already known about this topic

• ‘Correlation does not equal causation’ is a familiar claim in many fields of research but increasingly we see the need for a causal understanding of our educational systems.
• Big data bring many opportunities for analysis in education, but also a risk that results will fail to replicate in new contexts.
• Causal inference is a well-developed approach for extracting causal relationships from data, but is yet to become widely used in the learning sciences.

What this paper adds

• An overview of causal modelling to support educational data scientists interested in adopting this promising approach.
• A demonstration of how constructing causal models forces us to more explicitly specify the claims of educational theories.
• An understanding of how we can link educational datasets to theoretical constructs represented as causal models so formulating empirical tests of the educational theories that they represent.

Implications for practice and/or policy

• Causal models can help us to explicitly specify educational theories in a testable format.
• It is sometimes possible to make causal inferences from educational data if we understand our system well enough to construct a sufficiently explicit theoretical model.
• Learning Analysts should work to specify more causal models and test their predictions, as this would advance our theoretical understanding of many educational systems.

  相似文献   

Some of the things everyone needs to know about robots     

Balle  Simon 《Metascience》2022,31(2):247-250

  相似文献   

Does speed-reading training work,and if so,why? Effects of speed-reading training and metacognitive training on reading speed,comprehension and eye movements     

Marina Klimovich  Simon P. Tiffin-Richards  Tobias Richter 《Journal of Research in Reading》2023,46(2):123-142

Background

Commercial speed-reading training programs are typically marketed with the promise to dramatically increase reading speed without impairing comprehension. From the perspective of reading psychology, it seems quite unlikely that speed-reading training can indeed have such effects. However, research on the effectiveness of modern speed-reading training programs on reading performance in typical readers is sparse. The present study had two goals. First, we sought to extend prior research on speed-reading by assessing the effects of a speed-reading application on reading performance in a pre-training and post-training design with a control group. Second, we aimed to identify the mechanism underlying speed-reading training programs.

Methods

We assessed reading speed, comprehension and eye movements of 30 German-speaking undergraduates (M_age = 22.77 years, SD_age = 3.41 years) before and after they received a commercial, app-based speed-reading training, a metacognitive training or no training.

Results

Results revealed higher reading speed in the speed-reading condition and metacognitive condition compared with the control condition, although not to the extent claimed in the application. Eye-movement data indicated that the increase in reading speed was due to fewer and shorter fixations in measures reflecting late but not early lexical processing. No differences in comprehension performance were observed between the three conditions.

Conclusions

We discuss our findings in support of the idea that the increase in reading speed was not caused by a change in basic characteristics of participants' reading behaviour, but rather by an increase in their awareness of their own reading process. Further research is needed to investigate whether the observed effects are maintained over time.

  相似文献