P
Panagiotis Mavridis
Researcher at Delft University of Technology
Publications - 13
Citations - 184
Panagiotis Mavridis is an academic researcher from Delft University of Technology. The author has contributed to research in topics: Crowdsourcing & Framing (social sciences). The author has an hindex of 5, co-authored 13 publications receiving 133 citations. Previous affiliations of Panagiotis Mavridis include VU University Amsterdam & University of Rennes.
Papers
More filters
Proceedings ArticleDOI
Using Hierarchical Skills for Optimized Task Assignment in Knowledge-Intensive Crowdsourcing
TL;DR: This paper proposes to finely model tasks and participants using a skill tree, that is a taxonomy of skills equipped with a similarity distance within skills, that enables to map participants to tasks in a way that exploits the natural hierarchy among the skills.
Journal ArticleDOI
A survey of crowdsourcing in medical image analysis
Silas Nyboe Ørting,Andrew Doyle,Matthias Hirth,Arno van Hilten,Oana Inel,Oana Inel,Christopher R. Madan,Panagiotis Mavridis,Helen Spiers,Veronika Cheplygina +9 more
TL;DR: This survey reviews studies applying crowdsourcing to the analysis of medical images, published prior to July 2018, and identifies common approaches, challenges and considerations, providing guidance of utility to researchers adopting this approach.
Proceedings ArticleDOI
Chatterbox: Conversational Interfaces for Microtask Crowdsourcing
TL;DR: It is shown that conversational interfaces can be used effectively for crowdsourcing microtasks, resulting in a high satisfaction from workers, and without having a negative impact on task execution time or work quality.
Posted Content
A Survey of Crowdsourcing in Medical Image Analysis
Silas Nyboe Ørting,Andrew Doyle,Arno van Hilten,Matthias Hirth,Oana Inel,Christopher R. Madan,Panagiotis Mavridis,Helen Spiers,Veronika Cheplygina +8 more
TL;DR: In this article, the authors provide guidance to researchers considering using crowdsourcing methodologies in their own medical imaging analysis, identifying common approaches, challenges and considerations, providing guidance of utility to researchers adopting this approach.
Characterising and Mitigating Aggregation-Bias in Crowdsourced Toxicity Annotations
Agathe Balayn,Agathe Balayn,Panagiotis Mavridis,Alessandro Bozzon,Benjamin Timmermans,Zoltán Szlávik +5 more
TL;DR: The preliminary results point out that you can mitigate the majority-bias and get increased prediction accuracy for the minority opinions if you take into account the different labels from annotators when training adapted models, rather than rely on the aggregated labels.