Learning analytics is the use of data-based methods to analyze and optimize learning behavior and the contexts in which it occurs. This is usually done on very large amounts of data, so learning analytics are often referred to as "Big data for university teaching." Goals include refining didactic methods, empowering active learning, targeting students at all achievement levels, and measuring factors that impact graduation rates and student success.
A specific area of learning analytics is assessment analytics, which deals with data-driven optimization of testing scenarios. Educational data mining is the term used to describe the analysis of large amounts of data at more of an administrative level to derive decisions for degree programs or the university as a whole. All three terms – learning analytics, assessment analytics, and educational data mining – are grouped under the umbrella term academic analytics.
The RWTHanalytics project aims to establish a RWTH-wide service offering in the field of academic analytics for students, teachers, and the institutions supporting teaching. Our goal is to further develop studies and teaching in an evidence-based and data-driven way. To this end, our team works both within and outside RWTH in diverse alliances in order to involve all stakeholders from the outset in the spirit of the "Aachen Way" and to be able to jointly create a sustainable offering. The project results are consistently published as open resources, for example as open source software or as open educational resources.
Data-based course analysis and planning using AI for students as well as for course designers.
Innovative cluster E-Examinations – Designing electronic examinations to be competency-oriented and diversity-friendly
Didactics, ethics, and technology of learning analytics and AI in higher education.
Building cross-disciplinary bridges to AI - assessing, using and developing artificial intelligence in a meaningful and responsible way.