Skip to main content

Search NYU Steinhardt

Stacked books with open book at top

Favorite Readings

In addition to compiling introductory resources for those getting started in learning analytics (LA 101) and showcasing the great work by our own LEARN team (Published Research) we wanted to share some reflections on resources each of us have found especially valuable in our pursuit of LA. Keep reading to find out more about the ideas that have inspired us over the years!

Alyssa Wise

Intelligent Learning Analytics Dashboards is really thoughtful work by Hassan Khosravi and colleagues looking at applications of Artificial Intelligence in Education to guide data exploration in Learning Analytics dashboards while maintaining space for instructor agency. I like how this work both contributes technical advances and raises important considerations for Fairness, Accountability, Transparency and Ethics (FATE).

Alyssa Wise, LEARN Director
headshot

I love the design research in The Classroom as a Dashboard by Holstein and collaborators that combines learning analytics with human-computer interaction in the K-12 classroom. Mixed-reality smart glasses make a human-AI hybrid superteacher. Now we just need source information to move beyond tutoring system data!

Yoav Bergner, LEARN Core Faculty
Faculty Xavier Ochoa

I like Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data by Echeverria and colleagues because it embodies what Learning Analytics is for me: using varied technological means to capture data from an educational activity, analyzing this data to estimate stakeholder-generated pedagogically-relevant constructs, and finally using human-computer interaction approaches to provide actionable feedback that help students and teachers reflect on the activity.

Xavier Ochoa, LEARN Core Faculty
Qiujie Li, LEARN Postdoctoral Scholar

The literature review paper, Awareness is Not Enough, from Jivet and colleagues is a great starting point to understand the state-of-art in student-facing dashboard design! Unlike previous reviews that focus mainly on the technical aspects of student-facing dashboards, such as data sources, they dive deeper to provide a comprehensive summary of the key educational concepts underlying the design of the dashboards.

Qiujie Li, LEARN Postdoctoral Scholar
Yeonji Jung

The Linking Learning Behavior Analytics and Learning Science Concepts paper written by Sedrakyan and colleagues that links self-regulated concepts to learning analytics design is one of my favorites. It demonstrates a great example of how learning sciences can meet with analytics theoretically and empirically.

Yeonji Jung, LEARN Doctoral Scholar
Juan Pablo Sarmiento

I recommend Working Together in Learning Analytics Towards the Co-creation of Value by Dollinger and colleagues. While there has been a lot of talk about the importance of human-centered design in Learning Analytics, this inspiring paper shares one of the few examples of a years-long, large-scale project where the feedback and ideas of a learning community were incorporated into the design of a tool.

Juan Pablo Sarmiento, LEARN Doctoral Scholar
Sameen Reza, Doctoral Scholar

I like the review in The Journey of Learning Analytics by Joksimovic and colleagues as it not only provides an easy introduction to the field of learning analytics but also provides a summary of its developments and promising future directions for research. I recommend this to a beginner researcher in the field to get a sense of the multidisciplinary nature of the field and to help identify their own areas of interest within it.

Sameen Reza, LEARN Doctoral Scholar
Fabio Campos

Take a look at Exploratory Versus Explanatory Visual Learning Analytics, it gives a fresh perspective on LA and educational dashboards theory! Echeverria and colleagues make the case for exploratory-focused data dashboards, made available by utilizing data-storytelling techniques, and argue that dashboard designers and researchers need to go beyond UX to include issues of data interpretation.

Fabio Campos, LEARN Doctoral Scholar
Ofer Chen

In What’s the Problem with Learning Analytics?Neil Selwyn takes a critical perspective on the implementation of Learning Analytics. He explores how Learning Analytics (LA) is shaped by broad socio-cultural and political factors and suggests changes in the ways LA is implemented to mitigate ineffective or potentially harmful uses of LA.

Ofer Chen, LEARN Doctoral Scholar