January 2024 - EduTec Science

Jan312024 by Heather WehnerNo Comments

SWK-Talk: Large Language Models and their potential in the education system

In the SWK Talk Special "Large Language Models and their potential in the education system" on 18.01.2024, the SWK (Standing Conference of the Ministers of Education and Cultural Affairs) presented its impulse paper on Large Language Models. For the impulse paper, the SWK consulted external experts, including members of the EduTec Team, on teaching and learning with AI and LLM. The aim was to contribute to the current debate on the potential of LLM in the education system. The key conclusion is that the German education system currently faces the task of trying to utilize the potentials of generative AI technologies such as LLM, while at the same time recognizing their limitations and finding a way to responsibly deal with their restrictions. The paper also emphasizes the importance of a…

Jan292024 by Sebastian GombertNo Comments

New Pub: From the Automated Assessment of Student Essay Content to Highly Informative Feedback: a Case Study

Artificial Intelligence, Assessment, Computational Psychometrics, Empirical Study, Feedback, Higher Education, Journal, Publication, Special Issue, Technical paper

How can we give students highly informative feedback on their essays using natural language processing? In our new paper, led by Sebastian Gombert, we present a case study on using GBERT and T5 models to generate feedback for educational psychology students. In this paper: ➡ We implemented a two-step pipeline that segments the essays and predicts codes from the segments. The codes are used to generate feedback texts informing the students about the correctness of their solutions and the content areas they need to improve. ➡ We used 689 manually labelled essays as training data for our models. We compared GBERT, T5, and bag-of-words baselines for both steps. The results showed that the transformer-based models outperformed the baselines in both steps. ➡ We evaluated the feedback with a learner cohort…

Jan202024 by Daniele Di MitriNo Comments

Interview: A Controlled Way to Better Teaching and Learning with AI

Artificial Intelligence, Press

DIPFblog Interview with Dr. Daniele Di Mitri about the project "HyTea – Model for Hybrid Teaching“ Artificial intelligence (AI) has the potential to support teaching and learning in many automated ways. However, the contributions of the new technology do not always match the expectations and values of human users. The research and development project „HyTea – Model for Hybrid Teaching“ is investigating how this problem can be addressed. In the interview, project leader Dr. Daniele Di Mitri explains in more detail the project and how he and his team are proceeding. The interview on the DIPFblog – in English and German

Jan152024 by Dana KubeNo Comments

New Article – Gender diversity dynamics in a Computer Supported Collaborative Learning

Artificial Intelligence, Computer-supported collaborative learning, Digitalisation, Empirical Study, Gender, Higher Education, Journal, Learning Design, New Pub, Open access, Publication, Special Issue, Team

🎉 Exciting News! Our article has just been published in the magazine of Computer Assisted Learning! 📰 We delved into the fascinating world of online group learning among adults, unravelling the mysteries of emergent team roles and their intricate connection to gender dynamics in communication. 🌐👥 Have you ever wondered how team roles subtly surface and evolve in online group learning discussions? We did, too! Our research explores the subtle nuances of team roles and their subversive emergence, especially when viewed through the lens of gender diversity, in order to understand how to support more productive learning for all participants. Gender and gender diversity are group features affecting social interaction and are critical for gender-inclusive and equitable education. As such, the role of gender and gender diversity is of particular…

Jan122024 by Joshua WeidlichNo Comments

New Pub: Toward a comprehensive framework of social presence

Computer-supported collaborative learning, Higher Education, Journal, Literature review, New Pub, Open access, Special Issue

Today, students in higher education likely come into contact with different modes of learning, e.g. online learning, blended learning, and, increasingly, hybrid learning. To the extent that communication is mediated by technology in these learning modes, students can experience varying degrees of social presence with regard to their peers. Social presence refers to the feeling that others are 'real' and 'close' despite the physical separation. Especially in learning scenarios that require communication and collaboration, social presence is a crucial consideration. Despite this, research on social presence is fragmented and many other relevant theoretical accounts, while potentially informative, have been neglected. This paper, coauthored by Karel Kreijns, Jane Yau, Joshua Weidlich, and Armin Weinberger, published in Frontiers in Education, Section Digital Education, attempts to provide a comprehensive account of social presence…

Jan42024 by Daniele Di MitriNo Comments

How to improve Knowledge Tracing with hybrid machine learning techniques

Journal, New Pub

Knowledge Tracing is a well-known problem in AI for Education. It consists of monitoring how the student's knowledge changes during the learning process and accurately predicting their performance in future exercises. But how can we improve the current methods and overcome their limitations? In recent years, many advances have been made thanks to various machine learning and deep learning techniques. However, they have some pitfalls, such as modelling one skill at a time, ignoring the relationships between different skills, or inconsistent predictions, i.e. sudden spikes and falls across time steps. In our recently published systematic literature review, we aim to illustrate the state of the art in this field. Specifically, we want to identify the potential and the frontiers in integrating prior knowledge sources in the traditional machine learning pipeline…