Three questions have stirred controversies, fueled perpetual debates, and polarized educators, parents and students for as long as educational institutions have existed: What constitutes good teaching? What are effective learning practices? And, perhaps most importantly, what does “student achievement” mean? Attempts to answer these questions have evolved from philosophical musings to data-based modern educational research. Today, with Big Data research in learning and education taking flight, we are ready to unravel the secret of successful learning and teaching by leveraging massive and complex learning data and incorporating a large number of factors that differentially influence individual students’ learning success.

The Center for Data-Intensive Learning Analytics Research at MIDAS is a new addition to U-M’s nationally renowned research in learning analytics, propelled by the Learning Analytics Task Force launched in 2012. The two initial core research projects at the Center are funded by MIDAS’ Challenge Initiative. One project, ” LEAP: analytics for LEarners As People,” led by Rada Mihalcea in the College of Engineering, will create a new generation of learning analytics tools to understand the link between learning success and personal attributes such as values, beliefs, interests, behaviors, background, and emotional state. The other project, ” Holistic Modeling of Education (HOME),” led by Stephanie Teasley in the School of Information, will build a holistic learning model based on existing data and knowledge on the relationship of learner behaviors and outcomes, the interconnected semantics that make up knowledge, and evidence-based representations of learning.  In addition to these two projects, the Center for Data-Intensive Learning Analytics is incorporating other research projects as the opportunities arise.

Starting from the initial set of research projects, the continuing efforts of the Center for Data-Intensive Learning Analytics Research will focus on:

  • Disseminating tools and methods, as soon as they become available, to empower campus-wide learning analytics research.
  • Building a collaborative network of Big Data learning analytics researchers, and helping UM stay at the forefront of learning analytics research in the nation.
  • Forming industry partnerships and transform research findings into the next generation of learning systems.

If you are interested in finding out more about collaboration, partnership and resources, please contact us:

Research Areas

LEAP: analytics for LEarners As People

The goal of this project is to build a new generation of learning analytics tools which integrate our understanding of “student as a person” and “student as a learner”.  The research team will develop language, speech, and sensor-based machine learning tools that translate input data (academic performance, social media streams, WiFi access data and survey data from 1000 students) into attributes that will form a student profile.  They will explicitly link academic performance and mental health with the personal attributes the students’ values, beliefs, interests, behaviors, background, and emotional state.

Learn more…

Holistic Modeling of Education (HOME)

The research team aims to bring revolutionary changes in our understanding of education and learning through the holistic modeling of learners, impact the development and deployment of effective learning tools and methods, and greatly enhance U-M’s research capability in learning analytics.

The holistic models examine the relationship of learner behavior, learner interaction with learning systems, and outcomes, the interconnected semantics as knowledge representation, and data on learner activities, artifacts and achievements.

Learn more…

Closing the Loop: New Data Tools for Measuring Changes in the Quality of Nursing Education and the value of New Approaches to Instruction

Competency-based assessment of academic performance has been gaining momentum as it provides better measurements of knowledge and skills directly related to job performance, professional conduct and judgment, and other soft skills that traditional tests can’t measure. This project will use modern data-science tools to address a series of research questions, in order to understand the correlation between traditional tests and student skills and competence when they enter the workforce, and whether simulations coupled with debriefing sessions translate into improvements in skills and in test outcomes.

Learn more…