Hi. I'm Burcu Sayin Günel.

I'm a postdoctoral researcher in the Structured Machine Learning Group at University of Trento, in Italy. My main research is hybrid intelligence where we use humans in the loop of machine learning models to improve trustworthiness. I am also interested in active learning to build intelligent systems with fewer labeled data.

I received my PhD from University of Trento in 2022, and my thesis focused on building reliable hybrid human-machine classifiers. During my PhD program, I did an internship in the Web Information Systems (WIS) group at TU Delft. Previously, I received my MSc in Computer Engineering from Izmir Institute of Technology, and I worked on information dissemination and privacy issues on social networks. During my master program, I spent some time in CoNSeRT lab at University of West Attica.

My publications

Here's some of my recent publications.

Rethinking and Recomputing the Value of ML Models

We argue that the way we have been evaluating ML models has forgotten the fact that they provide value to people. We show that with this perspective we fundamentally change how we evaluate, select and deploy ML models.

The Science of Rejection: A Research Area for Human Computation

We motivate why the science of learning to reject model predictions is central to ML, and what is the role of humans.

Crowd-Powered Hybrid Classification Services: Calibration is all you need

We take the first steps toward a science for hybrid classification services, discussing key concepts, challenges, and architectures, and then focusing on a central aspect, that of ML calibration and how it can be achieved with crowdsourced labels.

Here’s my recent activities.

F+Cube Week 2022

I was invited to the F+Cube Week 2022 on November 15-23, 2022 at TU Delft. It was a pleasure to present my research and attend training from inspirational teaching to personal development.

New job alert

As of November 2022, I started a new position as Postdoctoral Researcher at Università di Trento! I will be working on cooperative human-machine intelligence.

PhD graduation

On September 26, I became a Doctor (Cum laude) in Information and Communication Technology at Università di Trento with my PhD thesis titled “Towards reliable hybrid human-machine classifiers”.

Blue Sky Best Paper Award

Our paper "The Science of Rejection: A Research Area for Human Computation” received the Blue Sky Best Paper Award at the 9th AAAI Conference on Human Computation and Crowdsourcing (HCOMP), Nov. 2021.

Methods Recognition

Our paper "On the state of reporting in crowdsourcing experiments and a checklist to aid current practices” received the Methods Recognition award from ACM Computer-Supported Cooperative Work & Social Computing (CSCW 2021), in Oct. 2021.

Best Paper Award

Our paper "A Novel Approach to Information Spreading Models for Social Networks” received the Best Paper award at The Sixth International Conference on Data Analytics (Data Analytics 2017), in Nov. 2017.