Author: Daniele Di Mitri

Daniele Di Mitri is a research group leader at the DIPF - Leibniz Institute for Research and Information in Education and a lecturer at the Goethe University of Frankfurt, Germany. Daniele received his PhD entitled "The Multimodal Tutor" at the Open University of The Netherlands (2020) in Learning Analytics and wearable sensor support. His research focuses on collecting and analysing multimodal data during physical interactions for automatic feedback and human behaviour analysis. Daniele's current research focuses on designing responsible Artificial Intelligence applications for education and human support. He is a "Johanna Quandt Young Academy" fellow and was elected "AI Newcomer 2021" at the KI Camp by the German Informatics Society. He is a member of the editorial board of Frontiers in Artificial Intelligence journal, a member of the CrossMMLA, a special interest group of the Society of Learning Analytics Research, and chair of the Learning Analytics Hackathon (LAKathon) series.

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

Education MSc Advanced Digital Reality Teaching courses

Webinar about MSc Advanced Digital Reality at German UDS

Posted on 08/26/2025by Daniele Di Mitri

Last week I presented in a free webinar on our new MSc Advanced Digital Reality at the German UDS

The characteristics of this master are

Master immersive technologies (AR, VR, MR & 3D modelling)
It allows you to explore what matters - you are free to pick examples from your industry and explore how immersive technologies can best support what you love
You have the freedom to build creative, research-driven digital solutions
You will thrive with our flexible, project-based online learning model

Conferences

AIED'25 conference in Palermo

Posted on 08/01/2025by Daniele Di Mitri

From 21st to 25th July, I attended the 26th International Conference on Artificial Intelligence in Education, which was held in Palermo, Italy. There, I mainly had two contributions.

I led the organisation of the Second International Workshop on Multimodal Artificial Intelligence in Education (MAIEd’25) – a collaborative space exploring how voice, gestures, and multimodal data can enrich learning experiences through AI. The workshop website can be found here https://maied.edutec.science/ whereas the workshop publication is available in the proceedings of the conference.

I gave an interactive demonstration of Presentable - our web-based presentation trainer, which is the outcome of the HyTea project.

AIED 2025 has gathered more than 750 attendees from all over the world. Researchers and interested participants could chose among several parallel sessions, including full and short paper presentations, interactive events, tutorials, workshops, doctoral consortium, panels etc.

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.