Causal Models and Big Data Learning Analytics

Kumar, Vive; Kinshuk, Kinshuk; Clemens, Clayton; Harris, Steven C.

doi:10.1007/978-3-662-44659-1_3

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work attempted to formalise our models of SRL through the use of discovery‐based methods which extract a causal relationship from input data and even appeared in an AI in Education paper (Brokenshire & Kumar, 2009) but failed to find traction in the field. A later paper arguing that causal models would help LA practitioners to intervene in educational systems was written by one of Brokenshire's supervisors (Kumar et al, 2015), and explored models of writing analytics (WA) and metacognitive reasoning using this same causal discovery‐based approach. However, this line of research never made it into the standard learning sciences literature, and appears to have halted.…”

Section: Causal Modelling—a Bridge Between Data and Educational Theoriesmentioning

confidence: 99%

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

Kitto

Hicks

Shum

2023

Brit J Educational Tech

View full text Add to dashboard Cite

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 notesWhat 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.

show abstract

Section: Causal Modelling—a Bridge Between Data and Educational Theoriesmentioning

confidence: 99%

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

Kitto

Hicks

Shum

2023

Brit J Educational Tech

View full text Add to dashboard Cite

show abstract

“…It bears mention that these conditions might also be satisfied (to some degree) using quasi-experimental or even nonexperimental methods. Particularly when taking into account the temporal ordering of variables and causally relevant background variables, some observational analyses are able to provide distinguishing evidence for causal relationships over mere covariance (Pearl & Verma, 1995;Spirtes, Glymour, & Scheines, 2000;Russo, 2010;Murnane & Willett, 2010;Kumar, Clemens, & Harris, 2015). As Tufte (2003) pronounced, "Correlation is not causation, but it sure is a hint" (p. 4).…”

Section: Causality In Learning Analyticsmentioning

confidence: 99%

Embedding Experiments: Staking Causal Inference in Authentic Educational Contexts

et al. 2018

View full text Add to dashboard Cite

To identify the ways teachers and educational systems can improve learning, researchers need to make causal inferences. Analyses of existing datasets play an important role in detecting causal patterns, but conducting experiments also plays an indispensable role in this research. In this article, we advocate for experiments to be embedded in real educational contexts, allowing researchers to test whether interventions such as a learning activity, new technology, or advising strategy elicit reliable improvements in authentic student behaviours and educational outcomes. Embedded experiments, wherein theoretically relevant variables are systematically manipulated in real learning contexts, carry strong benefits for making causal inferences, particularly when allied with the data-rich resources of contemporary e-learning environments. Toward this goal, we offer a field guide to embedded experimentation, reviewing experimental design choices, addressing ethical concerns, discussing the importance of involving teachers, and reviewing how interventions can be deployed in a variety of contexts, at a range of scales. Causal inference is a critical component of a field that aims to improve student learning; including experimentation alongside analyses of existing data in learning analytics is the most compelling way to test causal claims.

show abstract

“…Smart learning environments need to consider advanced data manipulation techniques such as employing big data and learning analytics to collect, combine and analyse individual learning profiles in order to scientifically generalise and infer each individual learning need in real time in ubiquitous settings that encompass both physical and online activities. Learning analytics by using big data can monitor individual learners' progress and behaviour continuously in order to explore factors that may influence learning efficiency and effectiveness [12,13].…”

Section: Considerations Of Smart Learning Environments Developmentmentioning

confidence: 99%

Learning in a Smart City Environment

Nikolov¹,

Shoikova²,

Krumova³

et al. 2016

JCC

View full text Add to dashboard Cite

Advances in technology in recent years have changed the learning behaviors of learners and reshaped teaching methods and learning environments. The purpose of this paper is to overview a foundational framework and provide models for the planning and implementation of smart learning environments. Introduction is focused on analysis of emerging industries and new types of jobs that are requiring future personnel to be well equipped to meet the need of the expansion requirements of these industries and keep up with their development needs. Gartner's 2015 Hype Cycle for Emerging Technologies identifies the computing innovations such as Internet of Things, Advanced Analytics, Machine Learning, Wearables etc. that organizations should monitor. Learners and students, being the future drivers of these industries, are the main human resource to fulfill the vacancies of these work forces. Constant improvements in and re-evaluation of the curriculum taught to the learners have to be done regularly to keep the learners up-to-date in fulfilling the requirements of these industries and corporations. Universities benefit from these thinking "out of the box practices" by equipping students with work force experience that involves more hands on task with real life infrastructures. Section 2 looks at future Internet domain landscape that comprises a great diversity of technology related topics involved in the implementation of Smart Learning Environments. The purpose of section 3 is to overview a foundational framework and major considerations for the planning and implementation of smart learning environments, behind which is the convergence of advances and developments in social constructivism, psychology, and technology. Section 4 introduces the smart learning models, which are developed to reflect the dynamic knowledge conversion processes in technology enabled smart learning environments. The last section presents a case study of a learning scenario entitled "Monitoring the environmental parameters in a Smart City" as an illustration of experimental learning on Internet of Things, which proofs the power of FORGE (forging online education through FIRE) FP7 project methodology and infrastructure for building remote labs and delivering them to students.

show abstract

Causal Models and Big Data Learning Analytics

Cited by 6 publications

References 12 publications

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

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

Embedding Experiments: Staking Causal Inference in Authentic Educational Contexts

Learning in a Smart City Environment

Contact Info

Product

Resources

About