Whether you have thousands of users, thousands of learning resources, or both, pinpointing the most beneficial training content and courses can be overwhelming for any L&D practitioner. In this post, we'll show you a simple way to get started and take a deep dive into the world of long-tail distribution.
The Quick Fix
By plotting the data on a chart, you can compare the frequency of certain categories or actions. For example, let’s identify the most popular content selections within an organization by:
- plotting the categorical variable, or the characteristic you’re evaluating, on the x-axis (i.e., content)
- plotting the frequency of the variable on the y-axis (i.e., number of times a piece of content is accessed by learners)
- arranging the data from highest to lowest frequency to quickly identify the most-accessed content
The Deep Dive: Long-Tail Distribution
When reviewing data around learners’ content usage and activity, it’s common to find that learners use the same few pieces of training content significantly more often than the majority of other resources—which also means there’s probably a large number of underutilized resources. Similarly, there’s generally a small number of employees who are significantly more active than their peers.
In statistics, this is known as the “long-tail” distribution because, as you plot the results on a graph, you’ll see a peak at the start with a long tail of dwindling results along the x-axis. Chances are, the long-tail distribution applies in your organization, too. For example, it might tell you that:
- 10% of learners are responsible for 80% of forum posts.
- Each month, one e-learning course is used thousands of times, another five courses are used more than 100 times, and the remaining hundreds of courses are used less than 100 times.
- A handful of salespeople are responsible for more than half the sales (see the following chart).
Benefits of Long-Tail Distribution
Identifying the long tail in a data set and the people or resources at the top of it can be hugely insightful in directing time and money for the most impact. For example, by identifying:
- the handful of learning materials that support the majority of your organization’s learning, you can focus your spending on optimizing those resources rather than expending effort on the hundreds of resources that are less used.
- your most active learning platform users, you can gauge their feedback and ask them help you promote the platform to others.
- your top performers both in terms of assessment and job performance, you can focus retention efforts to ensure you keep, reward, and encourage your best people.
Things to Consider
Of course, these insights need to be used within the context of your organization’s particular situation and circumstances. For example, pilots form a relatively small portion of an airline’s workforce. As a result, pilot training may not appear as popular when compared to the usage of other learning experiences within the entire organization. Clearly, this doesn’t mean pilot training should be ignored. Instead, this is an indication that data (and perhaps training budgets) need to be segmented by job role as part of learning evaluation.
About the author
As one of the authors of xAPI, Andrew Downes has years of expertise in data-driven learning design. With a background in instructional design and development, he’s well versed in creating learning experiences and platforms in corporate and academic environments.
Subscribe to our blog