Erasmo Purificato

Otto von Guericke University Magdeburg. Universitätsplatz 2, 39106 Magdeburg, Germany
Leibniz Institute for Educational Media | Georg Eckert Institute. Freisestraße 1, 38118 Brunswick, Germany
propic_erasmo_v2.jpg

Based in Magdeburg

I am a Research Assistant and a Ph.D. student at the Faculty of Computer Science of the Otto von Guericke University Magdeburg (OVGU), working with Prof. Dr.-Ing. Ernesto W. De Luca in the Human-Centred Artificial Intelligence research group. Starting from the analysis of the fairness capabilities of state-of-the-art user profiling Graph Neural Network-based models, my doctoral research focuses on presenting innovative human-centred approaches for bias detection and mitigation on this specific domain and technological architectures, by also providing ways for monitoring the results via novel explainable user interfaces, which are a crucial concept of any Human-Centred Artificial Intelligence (HCAI) system.

I am also employed as a Research Fellow in the Human-Centred Technologies for Educational Media department of the Leibniz Institute for Educational Media | Georg Eckert Institute (GEI), where I co-coordinate the development of the institute’s Usability Lab and am involved in the establishment of a systematic user monitoring process for the digital infrastructures and services.

Before I joined OVGU and GEI, I worked for three as an IT Consultant at Blue Reply with project management and AI systems development roles. Previously, I received my Bachelor and Master degree in Computer Engineering at University of Naples and a 2nd level Master degree in Artificial Intelligence at University of Turin.

I’m a technology enthusiast and a great football passionate.
My life is marked by Muhammad Ali’s quote “Impossible is nothing”.

news

2023-11-08

Attending AIxIA 2023 for presenting our discussion paper “Recent Advances in Fairness Analysis of User Profiling Approaches in E-Commerce with Graph Neural Networks”.

2023-10-21

Attending CIKM 2023 for presenting our tutorial “Leveraging Graph Neural Networks for User Profiling: Recent Advances and Open Challenges” (check the website).

2023-06-26

Attending UMAP 2023 for presenting our “Tutorial on User Profiling with Graph Neural Networks and Related Beyond-Accuracy Perspectives” (check the website).

2023-04-01

Our demo paper “FairUP: a Framework for Fairness Analysis of Graph Neural Network-Based User Profiling Models” has been accepted at SIGIR 2023.