New Pub: Feedback sources in essay writing: peer-generated or AI-generated feedback?

New Pub: Feedback sources in essay writing: peer-generated or AI-generated feedback?

Artificial Intelligence, Empirical Study, Feedback, Further Education, Journal, Publication
A newly published article discusses the use of peer feedback as a learning strategy, particularly in large classes where teachers face heavy workloads. For complex tasks like writing argumentative essays, peers may struggle to provide high-quality feedback due to the cognitive demands involved. The emergence of Artificial Intelligence (AI) tools, like ChatGPT, raises the question of whether AI can serve as a new feedback source for such tasks. To investigate this, a study compared ChatGPT-generated feedback with peer feedback on argumentative essays written by 74 graduate students from a Dutch university. The study collected essay data, peer feedback and ChatGPT-generated feedback, and then analyzed them using coding schemes. Results showed significant differences between ChatGPT and peer feedback, with ChatGPT offering more descriptive feedback while peers focused on identifying essay problems.…
Read More
Team led by Sebastian Gombert wins one of two tracks at BEA 2024 shared task on predicting Item Difficulty and Item Response Time

Team led by Sebastian Gombert wins one of two tracks at BEA 2024 shared task on predicting Item Difficulty and Item Response Time

Artificial Intelligence, Assessment, Award, Computational Psychometrics, Conference, Higher Education, New Pub, Workshop
For standardized exams to be fair and reliable, they must include a diverse range of question difficulties to accurately assess test taker abilities. Additionally, it's crucial to balance the time allotted per question to avoid making the test unnecessarily rushed or sluggish. The goal of this year's BEA shared task (competition) was to build systems which could predict Item Difficulty and Item Response Time for items taken from the United States Medical Licensing Examination (USMLE). EduTec member Sebastian Gombert designed systems which are able to predict both variables simultaneously. These placed first out of 43 for predicting Item Difficulty and fitfth out of 34 for predicting Item Response Time. They use modified versions of established transformer language models in a multitask setup. A corresponding system description paper titled Predicting Item…
Read More
Didacta Presentation in Cologne: Key Questions to Find Fitting AI Solutions For Student Feedback

Didacta Presentation in Cologne: Key Questions to Find Fitting AI Solutions For Student Feedback

Artificial Intelligence, Feedback, General education, Invited talk, School
What are the goals of AI in education for student feedback? How can teachers make sure that their AI-assisted feedback goes beyond simple right/wrong statements and instead provides not only correct solutions, but also possibilities for improvement, hints on competence development and effective learning strategies? To find a fitting AI solution, there are key questions one should know to ask in advance. These questions were outlined by Hendrik Drachsler in his presentation at the didacta 2024 in Cologne on 20.02.2024 titled “Ihr KI-Anbieter-Test - 3 Schlüsselfragen die Sie kennen sollten.” The key questions: Question 1: What indicators does your AI product use to analyze learning outcomes? --> Look for AI products that provide relevant indicators for measuring learning progress and skills acquisition. These indicators are important to accurately assess learning…
Read More
Podcast “Sitzenbleiben” About AI in Education

Podcast “Sitzenbleiben” About AI in Education

Artificial Intelligence, General education, School
In a special edition of the DIPF podcast "Sitzenbleiben", Kai Maaz (Executive Director of DIPF) and Hendrik Drachsler discuss the potentials and hurdles of integrating artificial intelligence (AI) into education. The conversation surrounding AI's capabilities and constraints has been rapidly gaining traction. Especially the emergence of large language models like ChatGPT has revolutionized the text creation process, which showcase the vast opportunities that AI technologies can bring to the education sector. Questions abound regarding AI's impact on education: How can AI impact tasks such as homework or exams? How can AI enrich lessons? Which data protection issues need to be considered? How can students and educators receive adequate support in navigating AI's integration into learning environments? These questions serve as focal points which are examined in this newly available podcast…
Read More
SWK-Talk: Large Language Models and their potential in the education system

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

Artificial Intelligence, Event, School
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…
Read More
New Pub: From the Automated Assessment of Student Essay Content to Highly Informative Feedback: a Case Study

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

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

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…
Read More
Exciting New BildungPLUS Podcast: Learning Analytics in the Age of AI

Exciting New BildungPLUS Podcast: Learning Analytics in the Age of AI

Artificial Intelligence, Learning Analytics
The studiumdigitale Podcast BildungPLUS invites listeners on a riveting journey into the dynamic world of educational research in the new episode titled “Learning Analytics in the Age of AI”. Prof. Dr. Hendrik Drachsler, Prof. Dr. Bart Rienties and Dr. Eyal Rabin unveil their recent experiences in Learning Analytics, sharing firsthand accounts of breakthroughs and challenges. With a keen focus on AI, the episode delves into anticipations surrounding artificial intelligence's transformative role in shaping personalized learning experiences. Stay tuned for a brief but insightful exploration of the future of education through the lens of Learning Analytics research and innovative AI applications. https://open.spotify.com/episode/5MMqdLhJoJcnwy9jSFDIN2?si=0d64ada4b61e4017&nd=1&dlsi=44dc68d0ceb445fa
Read More