Lisette Espín-Noboa

Lisette Espín-Noboa is a Visiting Professor at the Institute of Human-Centred Computing at Graz University of Technology and a senior postdoctoral researcher at the Complexity Science Hub (CSH) in Vienna and the Department of Network and Data Science at Central European University (CEU). Her work bridges computational social science, network science, and AI for social good, with a focus on fairness and inequality.

Her research centers on algorithmic fairness in network-based systems, particularly how social structures bias ranking and recommendation algorithms. She investigates when such biases are deemed unfair, aligning with UN SDGs 5 (Gender Equality), 10 (Reduced Inequalities), and 16 (Peace, Justice and Strong Institutions). At CEU, she collaborates on generating high-resolution poverty maps using satellite imagery, mobility data, and machine learning to address SDGs 1 (No Poverty), 3 (Good Health), and 11 (Sustainable Cities). Her methodological expertise includes multimodal data fusion, graph neural networks, and network modeling.

The recent articles reflect a strong trend in using computational methods to address societal challenges—particularly poverty estimation, algorithmic bias, and public health insights from digital traces. Her work consistently applies network science and machine learning to promote equity and transparency in AI systems.

Scientific Awards:

• No awards mentioned in the provided text.

Lisette has been actively involved in major research projects such as Humanized Algorithms and MAMMOth, focusing on mitigating algorithmic biases in social networks. She has led survey initiatives on network fairness in academic hiring and academic careers in Europe, indicating engagement with systemic equity issues in science. She mentors through teaching and open science, sharing materials on GitHub and launching a podcast to make her research accessible.

She is affiliated with research teams at CSH, CEU, and TU Graz, contributing to collaborative efforts in algorithmic fairness and network inequality. Her work with the netin package and open-source teaching materials demonstrates a commitment to reproducible and inclusive science.