To assist European universities to become more mature users and custodians of digital data about their students as they learn online, the SHEILA project will build a policy development framework that promotes formative assessment and personalized learning, by taking advantage of direct engagement of stakeholders in the development process.
More colleges and universities are exploring how to better use the trove of data they're collecting on their students to improve teaching and learning.
The Analytics Workench is a tool for performing different kinds of analyses. It combines a web-based frontend for designing analysis workflows with server-side computation of the designed analysis processes. The workflows are represented using a visual language.
The workbench was designed as an extensible analysis framework. Extensibility includes both the possibility to connect different frontends to the computational backend as well as the possibility to extend the available analysis features. As the workbench is still in development, new analysis features are added regularly.
The version offered here is a demo version, which is restricted to a selection of analysis features from the field of Social Network Analysis. Please be aware that the version offered here is not intended for productive use. Thus created analysis workflows and results may be deleted from time to time without further warning!
As a result of the project, the following two tools have been developed:
SiSOB workbench: This is an analysis tool that has been designed as a knowledge worker’s workbench. Its user interface allows the user to combine different components for data conversion, analysis and visual representation. More information.
Download source code
Download user manual
Access workbench
SiSOB data extractor: This system can be used for information crawling and extraction. It can be feed with either bibliographic data sources, such as Scopus or Web of Knowledge, or crawling information directly from the web through search engines. Its main goal is to extract curricular items from a set of researchers from their full names and expertise area. More information.
Download source code
Access data extractor
SISOB Data Exchange Format:
Download API
SISOB Visualization Tool:
Download visualization tool
The project LeMo (monitoring of learning processes on personalizing and non-personalizing learning management systems) aims to develop a prototype of a web based Learning Analytics application, which provides detailed information on user navigational patterns within learning management systems and identifies needs for enhancement and revision of the learning offer. Target groups are content-provider, teacher and researcher. The prototype will support personalizing learning management systems that require a login for access as well as online encyclopedias that are non-personalizing, where neither login nor registration is needed to access content. In this project three Berlin universities cooperate with four partners in the elearning sector.
The ASSISTments Platform ASSISTS students in learning while it gives teachers assessMENT of their students' progress. The ASSISTments platform is a generic system for any subject from math to English to science. Different researcher teams have funding to build libraries of content in ASSISTments. Currently ASSISTments is best known for the mathematic content inside of ASSISTments, but increasingly individual teachers are using ASSISTments to write their own content which they can share with the other teachers. More than half of the questions in ASSISTments have been built by teachers, and that number is growing fast.
E. Hakami, and D. Hernandez-Leo. LAK21: 11th International Learning Analytics and Knowledge Conference, page 269–279. New York, NY, USA, Association for Computing Machinery, (2021)
V. Rivera-Pelayo, J. Munk, V. Zacharias, and S. Braun. Proceedings of the Third International Conference on Learning Analytics and Knowledge, page 23–27. New York, NY, USA, Association for Computing Machinery, (2013)
V. Rivera-Pelayo, V. Zacharias, L. Müller, and S. Braun. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge, page 111–114. New York, NY, USA, Association for Computing Machinery, (2012)