Thoughts on Contextual Recommender Systems + Personalized Learning (Part 1): An Intro

Photo by Nong Vang on Unsplash

Hello! It seems I need a way to keep track of my thoughts, questions, and ideas in a way that isn’t quite as messy and easy to lose as my hastily scribbled notes.

So I’m going to start this, and hopefully, it will help!
And then whoever reads this gets to see how unorganized my thoughts are, embarrassingly, but that will be future me’s problem.

With the COVID-19 pandemic, there is a considerable need to adapt to and improve online teaching and learning. Even after the pandemic (hopefully soon enough, but who knows), I believe that online education will likely remain changed. With this, emerging technologies used to aid online education have great potential. But how do we know these technologies will be valuable? How do we know they aren’t merely adding to the excess of existing tools out there already?

In general, I want to explore what technologies already exist, how they help teachers and students, and how the developers of those technologies evaluate usefulness. 

Currently, I am thinking about contextual recommender systems and personalized learning and wondering how one might combine the two.

In one paper, Verbert et al. state that “Technology Enhanced Learning (TEL) domain, the deployment of recommender systems has attracted increased interest during the past years.” Recommender systems (RS) can address various challenges in learning, such as “filter[ing] content for different learning settings” [1]. This seems to relate to the notion of personalized learning. The authors continue to discuss the use of contextual recommender systems in TEL.

Context can be defined as “any information that can be used to characterize the situation of an entity. An entity is a person, place, or object that is considered relevant to the interaction between a user and an application, including the user and applications themselves.”

Dey et al. [2], cited in [1] Verbert et al.

And it is this context that can provide the necessary meaning to educational systems.

Verbert et al. classify “context information” into the following: (1) computing, (2) location, (3) time, (4) physical conditions, (5) activity, (6) resource, (7) user (profile), and (8) social relations. For now, I’d like to look more into the user context. This can include basic personal information, knowledge and performance, interests, learning goals, learning and cognitive styles, affects (or emotion), and background.

Something I am definitely curious about is regarding learning goals. There is so much work that requires measuring student performance and success, but grades often define this. I’ve wondered for a while now if and how students’ learning goals (and achieving their own goals) could be used to measure “success” rather than just grades. But perhaps this is a bit off-topic, so I digress. (‘:

I will end this post for now, and next time look into the user context in more detail and what current works use it for learning.

Here is a link to the next post.


  1. Verbert, Katrien, et al. “Context-aware recommender systems for learning: a survey and future challenges.” IEEE Transactions on Learning Technologies 5.4 (2012): 318-335.
  2. Dey, Anind K., Gregory D. Abowd, and Daniel Salber. “A conceptual framework and a toolkit for supporting the rapid prototyping of context-aware applications.” Human–Computer Interaction 16.2-4 (2001): 97-166.

1 Comment

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s