Results – Dimstudio

New publications at the ECEL conference 2025

Posted on 10/22/2025by Daniele Di Mitri

Two new publications from our team expanding the Presentable (www.presentable.info) ecosystem!

First, led by the brilliant Nina Mouhammad, “From Nervous to Noteworthy: Evaluating SPEAKS, an Educational Software for Speech Content” explores the message composition component of Presentable. SPEAKS serves as a crucial pillar that distinguishes the platform from previous research on presentation training systems. Full paper available (Open Access): https://papers.academic-conferences.org/index.php/ecel/article/view/4104

Second, we are excited to share “Evaluating WEBPOSE, a Posture Feedback System for Oral Presentations”, research led by Stefan Hummel with contributions from Mohamad Alomari, Nina Mouhammad, Jan Schneider Barnes, and Roland Klemke.

Both papers, to be presented at the 24th European Conference on e‑Learning at the Technical University of Denmark (DTU) under the leadership of Md. Saifuddin Khalid, presents the first results of a web-based prototype for training presentation rehearsal.

WEBPOSE has already been integrated into the latest version of Presentable, further strengthening its multimodal feedback capabilities. Full paper available (Open Access): https://papers.academic-conferences.org/index.php/ecel/article/view/4285

Journal article

New pub: key technical features of automated feedback systems - a systematic feature analysis

Posted on 09/20/2025by Daniele Di Mitri

New publication alert from the HyTea project titled "Enhancing presentation skills: key technical features of automated feedback systems - a systematic feature analysis", led by PhD candidate Stefan Hummel

The article presents a systematic analysis of oral presentation automated feedback systems (OPAFs), which are designed to support public speaking through automated feedback mechanisms.

Our study assessed 14 existing systems across a comprehensive set of 83 functional features and 12 additional aspects. Although there is an increased interest in these systems, we found that the overall implementation rate of key features remains low at just 16%, with notable gaps in critical areas like verbal-nonverbal congruency, adaptive feedback, and content structuring.

Moreover, evaluation methodologies tend to focus heavily on usability and user experience, while aspects such as learning outcomes and pedagogical value are often overlooked. The majority of studies are lab-based, which raises concerns about the generalisability of findings to real-world educational environments.

Our findings emphasise the importance of improved feature integration, real-world testing, and closer collaboration with educators to help transition these tools from experimental prototypes to effective educational technologies.

This is the first journal article published about the HyTea project and contributed substantially to building a solid foundation for Presentable (www.presentable.info).

This milestone was especially significant as it marks my first article published as the last author. Well done, Stefan, thanks to my co-authors and everyone who supported this research.

Paper available Open Access 🔓 here
https://www.inderscienceonline.com/doi/abs/10.1504/IJTEL.2025.148593

Presentations

Talk at the CALRG group of the OUUK

Posted on 07/06/2025by Daniele Di Mitri

In this talk, I give an overview of "Presentable" (https://presentable.info), an AI-driven system that enhances presentation skills through automated feedback.

Presentable guides users in creating and rehearsing presentations, offering immediate corrective feedback on voice and body language. This system exemplifies how multimodal data and intelligent algorithms can provide retrospective feedback and intelligent support.

The talk was given at the Computers and Learning Research Group (CALRG) of The Open University in the UK. Thanks, Fridolin Wild, for inviting me.

About me Awards

My appointment speech at German UDS

Posted on 04/17/2025by Daniele Di Mitri

On the 16th April 2025, the appointment took place ceremony where I officially received my appointment as professor in Multimodal Learning Technologies.Here is the text of my speech

Ladies and gentlemen,

How will students at the German UDS learn in the future? Will they still be confined to desks and laptops, watching videos on our LMS? Or perhaps they will be in the metaverse campus? Or maybe they'll engage in individual interactions with Large Language Models?

In my research group on multimodal learning technologies, we are dedicated to creating authentic learning experiences that blend both physical and digital spaces. This includes engaging with the local, physical world—through movement, objects, and environments—while also exploring the possibilities offered by digital tools, AI tutors, and immersive virtual realities.

For instance, we explore tools like Presentable, an AI tutor that offers immediate feedback on presentation skills. We are equally interested in how virtual environments can support learners in expressing their desires, goals, and identities.

But as we stand at the frontier of educational technologies, we must ask: Are we simply chasing what’s technologically possible, or are we building what is truly desirable? As we envision the future of education, our focus must remain on key values—privacy, simplicity, accessibility, and affordability.

We should prioritise solutions that are scalable, low-cost, and inclusive.

To transform learning by 180 degrees means more than embracing innovation. It means using technology thoughtfully to support every learner's growth, well-being, and potential. The biggest challenge that we face in front of us in education is not just about going digital—it’s about staying human in a digital world.

Thank you.

Picture with the two presidents at German UDS, Prof Dr Mike Friedrichsen and Prof Dr Christoph Meinel

Newly appointed professors — The newly appointed professors with the two presidents (from left to right): Marco Bade, Mike Friedrichsen, Felix Weitkämper, Daniele Di Mitri, , Steven Ney, Georg Loscher, Tim Stuchtey, Thomas Staubitz, Julia Von Theinen, Christoph Meinel, Thomas Staubiz

Presentations Research visits

Guest Talk at Monash University

Posted on 11/07/2024by Daniele Di Mitri

During my recent research visit to Australia, I had the privilege of presenting at Monash University, specifically at the Centre for Learning Analytics Monash (COLAM). My talk, titled “The Quest for Automated Feedback,” explored the evolving role of AI in education, particularly in providing meaningful feedback to students.

As generative AI tools like ChatGPT become increasingly popular among students seeking feedback on their essays, a critical question arises: How effective is this feedback? My research delves into the complexities of generating automated feedback, emphasising that it is not a one-size-fits-all solution. Feedback is inherently context-dependent, influenced by various factors, including the learner’s needs, the task at hand, and the feedback modality.

The literature on feedback is vast and nuanced. I referenced several foundational models, including Hattie & Timperley (2007) and Winne’s Self-Regulated Learning Model (1996), to highlight that there is no universal definition of what constitutes good feedback. However, specific guidelines can help shape effective feedback practices.

AI’s increasing role in education presents both opportunities and challenges. My ongoing qualitative research sheds light on how AI-generated feedback can be tailored to different levels of detail—task-level, process-level, and self-regulation feedback. This differentiation is crucial for enhancing the learning experience.

I discussed various feedback modalities, such as audio, graphics, and haptic feedback, emphasizing that the choice of modality can significantly impact cognitive load. Additionally, the timing of feedback—whether immediate or delayed—plays a vital role in its effectiveness.

The integration of learning analytics with multimodal data collection is a key focus of my research. By leveraging data from both physical and digital learning environments, we can create richer, more personalized learning experiences. This approach aligns with the concept of embodied cognition, where learning is grounded in both the body and the environment.

My talk at Monash University was not just an opportunity to share my research; it was a chance to engage with fellow academics and practitioners who are equally passionate about the future of education. The discussions that followed my presentation were enlightening, and I left with new insights and collaborations in mind.