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
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
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
New Pub: Toward a comprehensive framework of social presence

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…
Read More
PhD defense on Technological Responses to Distracting Media Multitasking in Digital Learning Environments

PhD defense on Technological Responses to Distracting Media Multitasking in Digital Learning Environments

Award, Higher Education, Learning Analytics, PhD defense, School, Self-Regulation
Today, we proudly acknowledge the remarkable achievement of our team member, Daniel Biedermann, in successfully defending his PhD thesis to become Dr. Biedermann. Woohoo, congratulations! In our modern world, the reality of digital distractions through the attention economy cannot be denied. Countries like the Netherlands, for instance, are planning to ban mobiles from classrooms starting from 2024. Daniel's PhD work centered on the complex challenges of digital media distraction, a phenomenon that's prevalent largely due to our pervasive use of social media and notification systems on our phones, PCs, and tablets. Presented in his disputation, Daniel argued the need for a context-sensitive system to gain a more profound understanding of digital media distraction. In addition, Daniel addressed the crucial subject of digital self-control tools (DSCTs). His research, which provided a…
Read More
Kickoff meeting of the DFG Research Group CORE

Kickoff meeting of the DFG Research Group CORE

Artificial Intelligence, Critical Online Reasoning, Event, Higher Education, Project meeting
The Johannes Gutenberg University Mainz (JGU Mainz) hosted a two-day kickoff meeting from 05-06.12.23 for the DFG-Research Group CORE, a project dedicated to the study of critical online reasoning (COR) skills in higher education. The CORE project aims to explore the online learning behaviors and online information landscapes that students in medicine, physics, economics, and social sciences use for their studies.The event brought together a the CORE project partners as well as the international advisory board to discuss the project's goals, achievements so far, and future directions. Inclusion of International Advisory Board Members The kickoff meeting was enriched by the presence of members of the CORE project's international advisory board, these esteemed members provided valuable insights and recommendations for the project's advancement, stressing the importance of interdisciplinary cooperation in the study…
Read More
3rd IMPACT consortium meeting, a deep-dive into the rollout of Learning Analytics in the times of generative AI

3rd IMPACT consortium meeting, a deep-dive into the rollout of Learning Analytics in the times of generative AI

Artificial Intelligence, Event, Higher Education, Learning Analytics, Project
The IMPACT project held its third project meeting in Hagen, Germany, from 30.11-01.12.2023. The IMPACT project seeks to enhance higher education through the sizable implementation of Artificial Intelligence procedures for (partially) automated text analysis. Along the Student Life Cycle, prospective and current students receive highly informative, personalized feedback based on text during the orientation and entry phases, throughout the course of their studies (formative assessment), and upon the completion of academic performances (summative assessment). Supported by change management based on the SHEILA process model, five German universities are implementing text-based AI procedures. These include chatbots, personalized feedback systems for formative and summative assessments. The interdisciplinary consortium leverages internationally-tested open-source software solutions, along with shared standards for interoperability in higher education with learning management systems like Moodle, Stud.IP, ILIAS, Online Study…
Read More
Enhancing Learning with Data-enriched Activities: Insights from the HIKOF/IMPACT Workshop at eLearning Netzwerktag 2023

Enhancing Learning with Data-enriched Activities: Insights from the HIKOF/IMPACT Workshop at eLearning Netzwerktag 2023

Conference, Event, Feedback, Higher Education, Learning Analytics, Learning Design, Project, Workshop
At the 16te eLearning Netzwerktag 2023, participants had the opportunity to engage in various thought-provoking workshops. One workshop that stood out was the HIKOF/IMPACT session, where the edutec.science members from these AI projects shed light on the development of Data-enriched Learning Activities (DeLAs). This interactive workshop showcased how DeLAs offer valuable insights into students' competency development within digital learning activities. Let's delve into the details of how the HIKOF/IMPACT projects, part of the HILA research program, are revolutionizing eLearning through the implementation of DeLAs. The HIKOF/IMPACT workshop focused on exploring the concept and implementation of Data-enriched Learning Activities. Through DeLAs, educators gain unique insights into students' competency development during digital learning processes. These activities represent a powerful approach that leverages AI to analyze real-time data and provide highly informative feedback…
Read More
Recap on the webinar on Highly-Informative Learning Analytics at the DGHD

Recap on the webinar on Highly-Informative Learning Analytics at the DGHD

Event, Higher Education, Keynote, Learning Analytics, Learning Design, Webinar
Following the successful execution of the dghd series on Learning Analytics in higher education, and based on the decided community interest, we were excited to have announced the continuation of the lecture series focusing on Learning Analytics. The series, which was organized jointly by the dghd working groups "Digital Media in Higher Education Didactics (dmhd)" and "Psychology and Teaching-Learning Research," along with the dghd board, aimed to shed light on the capabilities of Learning Analytics and how it could be implemented across various university projects. Among the presentations, the edutec.science group contributed an presentation entitled "Hochinformatives Feedback mit Learning Analytics" by Prof. Dr. Hendrik Drachsler on November 23, 2023. This presentation kicked off by introducing the code of conduct for the application of Learning Analytics. At a time when data…
Read More