Applications of Learning Analytics


Any assessment of the ethics of learning analytics requires a comprehensive understanding of these applications and their impact. We classify the potential applications of learning analytics based on what analytics can do and how they work. Development in many of these application areas has already started, so this is as much a snapshot of the state of the art today as it is a prediction of future technology.

Pages

All Applications of Analytics
This page provides an index of all applications of analytics and AI in teaching and learning.

Media

Module 2 - Introduction, Oct 18, 2021

Applications of Analytics, Oct 19, 2021

Descriptive Analytics, Oct 20, 2021

Diagnostic Analytics, Oct 21, 2021

Predictive Analytics, Oct 22, 2021

Module 2 - Discussion, Oct 22, 2021

Prescriptive Analytics, Oct 26, 2021

Generative Analytics, Oct 26, 2021

Deontic Analytics, Oct 26, 2021

Live Events

2021/10/18 12:00 Module 2 - Introduction

2021/10/22 12:00 Module 2 - Discussion

Tasks

Applications of Analytics

Part 1. Review the presentation for Tuesday, Applications of Analytics, and consider whether any additional applications could be added to this list. If you can think of another application of analytics, go to the 'Add Application' page and submit your suggestion.

Part 2. For the application you've submitted, or for any existing application, identify a web page or document offering an example of that application. Then go to the 'Add Link' page and add your link, selecting the 'Application' category that it belongs to.

Part 3. These submissions will be collected and we will review them during the Friday discussion. If you would like credit (ie., a badge) for this work, write a blog post discussing your approach to each of the two tasks, and include links in your post to the link you uploaded.

Due: May 25, 2022

Your Posts

Diagnostic Analytics
Stephen Downes,

This presentation begins with a review of this week's task, then looks in detail at the various diagnostic applications of AI and analytics, reviewing the set with a brief description and some examples.

Web: [This Post]

Synopsis

Institutions have been gathering data on students and others for many years, ranging from registration information to access control to activity records. Until recently, this data was not used extensively for analytics. (Kay, Korn & Oppenheim, 2012) This is changing rapidly. The applications of analytics in education will be widespread and pervasive. Any assessment of the ethics of learning analytics requires a comprehensive understanding of these applications and their impact.

There’s a lot of optimism surrounding learning analytics, tempered with caution. “Although some of this excitement may be based on unrealistic expectations and limited knowledge of the complexities of the underpinning technologies,” writes Tuomu (2018), “it is reasonable to expect that the recent advances in AI and machine learning will have profound impacts on future labour markets, competence requirements, as well as in learning and teaching practices”

We can look at the motivations for learning analytics to develop a sense of what to expect from the technology. Institutions may desire, for example (Kay, Korn & Oppenheim, 2012):

  • responses to economic and competitive pressures

  • agility of analysis 

  • good practice in modern enterprise management.

  • intelligent personalised services 

  • visualization of patterns and trends in large-scale data 

In what follows we classify the potential applications of learning analytics based on what analytics can do and how they work. Modern analytics is based mostly in supervised machine learning and neural networks, and these in turn provide algorithms for pattern recognition, regression, and clustering (Raghu & Schmidt, 2020).

Built on these basic capabilities are four widely-used categories (Brodsky, et.al., 2015; Boyer and Bonnin, 2017) to which I add additional fifth and sixth categories: 

  • descriptive analytics, answering the question “what happened?”; 

  • diagnostic analytics, answering the question “why did it happen?”; 

  • predictive analytics, answering the question “what will happen?”; 

  • prescriptive analytics, answering the question “how can we make it happen?”; and

  • generative analytics, which use data to create new things, and

  • deontic analytics, answering the question “what should happen?”.

Within each of these categories we can locate the various applications that fall under the heading ‘learning analytics’, as suggested by motivations outlined above. We will find that development in more of these application areas has already started, so that this is less a prediction of future technology (though some applications may yet be years away) and more of a snapshot of the state of the art today.

Descriptive Analytics

Descriptive analytics include analytics focused on description, detection and reporting, including mechanisms to pull data from multiple sources, filter it, and combine it. The output of descriptive analytics includes visualizations such as pie charts, tables, bar charts or line graphs. Descriptive analytics can be used to define key metrics, identify data needs, define data management practices, prepare data for analysis, and present data to a viewer. (Vesset, 2018).

Diagnostic Analytics - Diagnostic analytics look more deeply into data in order to detect patterns and trends. Such a system could be thought of as being used to draw an inference about a piece of data based on the patterns detected in sample or training data, for example, to perform recognition, classification or categorization tasks.

Predictive Analytics - Predictive analytics answer the question, what will (probably) happen, based on an identification of patterns and trends in existing data, and an extrapolation of that pattern or trend to probably future states. For example, such an analytics system might look at a student's participation  in a course and then predict whether the student will pass or fail.

Prescriptive Analytics - Prescriptive analytics recommend solutions. The use of prescriptive analytics may inform a human user or a machine system of a need that requires fulfillment. Such needs may be generated from rules or principles, limits or bounds of operation, equations or balancing mechanisms, or user input. The requirement for some solution may be based on the existence of a need combined with a prediction suggesting that the need has not or will not be met. For example, analytics may predict rising pressure levels that exceed the tolerance of a pipeline.

Generative Analytics - Generative analytics employ previous analyses of data in other to generate original content based on parameters or properties of the data studied, combined with predictions or requirements for future data. For example, generative analytics may use as data the library of Picasso's paintings, and then generate new Picasso-style paintings based on photographs or drawings.

Deontic Analytics - Deontic analytics answer the question, "what should happen?" This is a class of analytics that look at expressions of sentiments, needs, desires, and other such factors in order to determine what sort of outcome would be best, and then works toward achieving that outcome. In this sense it is the use of analytics to inject ethical, political or cultural order into the environment, whether ti be a discussion list, an allocation of resources, or management of staff.

Even as this work is being written, new applications of analytics in learning appear every day. The list of AI-generated content continues to expand, for example, and it is not a stretch to imagine learning resources being developed automatically on an as-needed basis in the imaginable future. 

So the list of applications above should be taken into consideration only as a tentative snapshot. To remain current, it is advisable to follow online repositories of analytics projects, for example, the Oklahoma University the Projects in Artificial Intelligence Registry (PAIR, 2020), which “serves as a global directory of active and archival AI projects and research and might eventually serve as a hub for various initiatives” (O’Brien, 2020).

In the meantime, the list of applications provided here serves as a baseline describing the objectives and desired outcomes of learning analytics, and therefore as a listing of the benefits expected from this activity, as a counter to the ethical risks and considerations raised in the next chapter. After all, if there were no benefit to be derived from analytics, there would be no ethical implications; we would simply treat analytics as a form of social vandalism. But the potential benefits, as we have seen, are real.