Target group Archives - Page 4 of 17

Jul12024 by Sebastian GombertNo Comments

New pub: Predicting Item Difficulty and Item Response Time with Scalar-mixed Transformer Encoder Models and Rational Network Regression Heads

Artificial Intelligence, Assessment, Computational Psychometrics, Conference, Higher Education, Publication, Workshop

In a contribution to the BEA 2024 Shared Task, we addressed the challenge of predicting the difficulty and response time of multiple-choice questions from the United States Medical Licensing Examination® (USMLE®). This exam is an important assessment for medical professionals. To predict these variables, we evaluated various BERT-like pre-trained transformer models. We combined these models with Scalar Mixing and two custom 2-layer classification heads, using learnable Rational Activations as the activation function. This multi-task setup allowed us to predict both item difficulty and response time. The results were noteworthy. Our models placed first out of 43 participants in predicting item difficulty and fifth out of 34 participants in predicting item response time. This demonstrates the potential of advanced AI techniques in improving the evaluation processes of critical exams like the…

Jun102024 by Atezaz AhmadNo Comments

New Pub: Emotional and motivational effects of automated and personalized feedback

Computer-supported collaborative learning, Empirical Study, Feedback, Higher Education, Journal, Learning Analytics, New Pub, Open access

With increasingly large student numbers, providing personalized teacher feedback becomes untenable. On the other hand, providing students feedback about their work is an integral part of ensuring student support throughout their learning trajectory. Fortunately, Learning Analytics now makes it feasible to automatically deploy feedback to many students at once. However, the design of effective feedback still remains an area of investigation Joshua Weidlich, Aron Fink, Ioana Jivet, Jane Yau, Tornike Giorgashvili, Hendrik Drachsler, and Andreas Frey's recently published paper in the Journal of Computer-Assisted Learning focused on one key design feature: the reference frame. Any feedback content must be formulated in reference to some performance level, be it the average of the student group (social comparison), the desired performance level (criterion-referenced comparison), or past performance. A longstanding literature on this…

May242024 by Heather WehnerNo Comments

FoLA supports Simulation-based Training for High-risk Clinical Situations

Assessment, Empirical Study, Feedback, Further Education, Higher Education, Learning Analytics, Learning Design, medical education, Multimodal Learning Analytics, Workshop

From May 16th to 17th, 2024, Hendrik Drachsler and Marcel Schmitz (TETRA AI, ZUYD University of Applied Science) had the pleasure of providing a FoLA workshop at the College of Anaesthesiologists of Ireland (CAI) in Dublin, Ireland, under the support of the Insight research centre. Together with members from CAI and from the ASSERT Centre, College of Medicine and Health, University College Cork (UCC), they used the FoLA tool to plan a simulation-based training for high-risk clinical situations using highly informative feedback. Data from these trainings will be collected and analyzed to determine how effective this training is in improving the performance of the attendees. The study is being planned to take place with around 100 doctors in training at two simulation training centers: at ASSERT Centre UCC and at…

May212024 by GianlucaNo Comments

How to Implement and Scale Learning Analytics Infrastructures in the Cloud @ #JTELSS24

Critical Online Reasoning, Higher Education, Learning Analytics, Summer School, Workshop

At the 18th EATEL Summer School on Technology-Enhanced Learning (JTELSS 2024) in Gabicce Mare, Pesaro, Italy, Gianluca Romano and Sebastian Gombert conducted the workshop "From Learner Behavior to Big Data: How to Implement and Scale Learning Analytics Infrastructures in the Cloud”. In the ever-evolving world of cloud computing, Azure stands out as a robust platform offering a myriad of services and tools to help businesses innovate and scale. Recently, we had the chance to delve deep into Azure's ecosystem, exploring its billing structures, infrastructure capabilities, and budgeting models. Here's a glimpse into what we learned and how you can leverage Azure for tracking user behavior and managing costs effectively. One of the foundational aspects of working with Azure is understanding its billing structure, which is organized into tenants, subscriptions, and…

May132024 by Sebastian WollnyNo Comments

Dr. Diana Gayol Visits the EduTec Team

Artificial Intelligence, Higher Education, Transfer Activity

Last week we had the pleasure of welcoming Dr. Diana Gayol, Director of Diploma in Didactics and Pedagogy in Health Areas at the Faculty of Medicine of the Fundación Barceló in Buenos Aires (Argentina), to DIPF. Dr. Gayol's research focuses on psychological studies of Argentinean students and shows parallels with various activities of the TBA Center. On her research trip, she was able to make a stop at Campus Westend, where she was particularly interested in an exchange about future AI applications in argentinian education with Sebastian Wollny and Sebastian Gombert. Collaborative Discussions During her visit, Dr. Gayol engaged in dynamic discussions with our researchers. We explored topics ranging from personalized learning through Intelligent Tutoring Systems (ITS) to Chatbots and AI-driven analytics. Dr. Gayol emphasized the importance of bridging the…

May102024 by Heather WehnerNo Comments

Recap of the MODUS conference in Karlsruhe

Artificial Intelligence, Conference, Higher Education

As the echoes of insightful discussions and the energy of networking gradually settle, it's time to revisit the highlights of the German Rectors’ MODUS Conference which took place an April 10th and 11th 2024 in Karlsruhe. The conference titled “Recognition Culture in Higher Education. International Perspectives on Lifelong Learning and Student Mobility” brought together around 200 experts and interested parties from universities and research institutions, including Hendrik Drachsler and other representatives from the Goethe University. The conference produced a wealth of insights into the integration of artificial intelligence (AI) at universities. Discussions highlighted both opportunities and challenges, especially in the context of the digitalization of administration and teaching organizations. Instruments for various areas of application were presented, including information and communication tools such as chatbots and recommendation systems, as well…

May92024 by Atezaz AhmadNo Comments

New Pub: I don’t have time! But keep me in the loop: Co-designing requirements for a learning analytics cockpit with teachers

Empirical Study, Learning Analytics, New Pub, Research Methods, School

Teacher dashboards can help secondary school teachers manage online learning activities and inform instructional decisions by visualising information about class learning. However, when designing teacher dashboards, it is not trivial to choose which information to display, because not all of the vast amount of information retrieved from digital learning environments is useful for teaching. Information elicited from formative assessment (FA), though, is a strong predictor for student performance and can be a useful data source for effective teacher dashboards. Especially in the secondary education context, FA and feedback on FA, have been extensively studied and shown to positively affect student learning outcomes. Moreover, secondary teachers struggle to make sense of the information displayed in dashboards and decide on pedagogical actions, such as providing feedback to students. Objectives: To facilitate the…

May72024 by Atezaz AhmadNo Comments

New Pub: Students Want to Experiment While Teachers Care More About Assessment! Exploring How Novices and Experts Engage in Course Design

Computer-supported collaborative learning, Conference, Conference, Higher Education, Learning Analytics, Learning Design, New Pub, Open access, Open science, Publication, Technical paper

Abstract: Learning Design (LD) is the strategic orchestration of educational components to create a rewarding experience for students and educators. Adapting it to real-world scenarios with evolving technologies, like learning analytics (LA), adds complexity but offers the potential for enhanced learning outcomes and engagement. Prior research highlights the growing importance of LA in informing LD decisions. The FoLA2 method offers a collaborative approach to course design considering LA implications. This study pursues two primary objectives. Firstly, to enhance the FoLA2 method by granting course designers access to the Open Learning Analytics Indicator Repository (OpenLAIR) that facilitates visual connections between LD pedagogies, LDLA activities, LA indicators and their metrics. Secondly, to explore how novice and expert groups utilize the FoLA2 methodology to design a course in Technology Enhanced Learning. The findings…

Apr162024 by Heather WehnerNo Comments

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.…

Apr112024 by Sebastian GombertNo Comments

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…