Learning analytics is the measurement, collection, analysis, and reporting of data about learners and the environments in which the learning occurs. The data allows us to understand and optimize learning and its contexts. Analytics can provide insight into such factors as trends in test scores within specific learner cohorts, the difficulty of specific test items, and learner behaviors within the educational experience.

Most e-learning today is generally accompanied by some standard learning analytics that evaluate the efficacy of the training. However, much of this analysis is done after a user has completed the learning activity, when the data is aggregated to determine trends.

As technology continues to evolve, we see a shift from the post-learning processing of data to the use of technology with artificial intelligence capabilities, providing opportunities to leverage real-time learning analytics to drive a unique experience for each learner as he or she participates in the training.

Engaging With AI

Most of us have a sense of the power of AI, where data is analyzed in real time and the system output changes based on the results of those analytics. If you’ve ever watched Netflix, then you’ve noticed how, after you’ve browsed and viewed some selections, the service will recommend movies and shows that may interest you. Netflix identifies commonalities in what you watched and paired that information with user data from other subscribers to suggest “matches” for you. This helps Netflix not only to make recommendations based on its understanding of audience preferences but also to design and create new shows based on what people seem to like and watch the most.

In education, AI allows us to do something similar. We can monitor learner cohorts as they complete lessons, while simultaneously offering course corrections and suggestions to individual learners when needed. This actively engages them during the learning experience.

Real-time learning analytics make a direct impact by creating a path through the training that is most appropriate for a specific learner. Personalization makes the training efficient and relevant—both a magnet for existing members and a great tool for attracting new ones.

Advancing Microlearning

Microlearning is the practice of breaking down learning into small bursts that are quick and easily digestible. These chunks of content are well suited for adaptable, personalized, and flexible learning. Like Legos, each piece is customized and can fit and build upon another, and each piece can be part of many different educational activities. AI plays heavily in some of the latest technologies that support microlearning.

The complexity of an AI-fueled microlearning experience results in a continuous, real-time assessment of a learner’s progress. This adaptive functionality can prescribe content reinforcement for areas where a learner struggles and identify opportunities to reengage the learner moving forward.

Learning analytics can improve the microlearning experience by helping to identify ineffective or inappropriate content, such as a test item that is too difficult or too easy. A benefit of having the content parsed into smaller sections is the ease with which such obsolete or ineffective information can be updated or replaced.

As Netflix demonstrates, gauging what your audience needs is key. Gathering relevant data can provide insight into your learners’ motivation and commitment. Data from evaluations and test results can provide a strong basis for understanding the learning habits of your audience and how those habits might play into your strategy for developing and distributing content. 

With greater use of analytics—and particularly real-time analytics—to increase learner engagement, it becomes even more important to integrate those findings into precise, actionable tasks such as updating courses or making changes to better meet learner needs. The results will reignite your members’ engagement with learning and reinforce your commitment to helping them advance.