Metadata Representations for Queryable Repositories of Machine Learning Models

Autor: Ziyu Li, Henk Kant, Rihan Hai, Asterios Katsifodimos, Marco Brambilla, Alessandro Bozzon

Publikováno v: IEEE Access, Vol 11, Pp 125616-125630 (2023)

Machine learning (ML) practitioners and organizations are building model repositories of pre-trained models, referred to as model zoos. These model zoos contain metadata describing the properties of the ML models and datasets. The metadata serves cru

Externí odkaz: https://doaj.org/article/13af14ddc45849acb55322d083d9408c

An Analysis of Music Perception Skills on Crowdsourcing Platforms

Autor: Ioannis Petros Samiotis, Sihang Qiu, Christoph Lofi, Jie Yang, Ujwal Gadiraju, Alessandro Bozzon

Publikováno v: Frontiers in Artificial Intelligence, Vol 5 (2022)

Music content annotation campaigns are common on paid crowdsourcing platforms. Crowd workers are expected to annotate complex music artifacts, a task often demanding specialized skills and expertise, thus selecting the right participants is crucial f

Externí odkaz: https://doaj.org/article/6cddb2146e944705bf61ee867b38eff5

Automatic Processing of User-Generated Content for the Description of Energy-Consuming Activities at Individual and Group Level

Autor: Roos de Kok, Andrea Mauri, Alessandro Bozzon

Publikováno v: Energies, Vol 12, Iss 1, p 15 (2018)

Understanding and improving the energy consumption behavior of individuals is considered a powerful approach to improve energy conservation and stimulate energy efficiency. To motivate people to change their energy consumption behavior, we need to ha

Externí odkaz: https://doaj.org/article/212be195709d4a288a30e76de21a29f4

Disentangling Fairness Perceptions in Algorithmic Decision-Making: the Effects of Explanations, Human Oversight, and Contestability

Autor: Mireia Yurrita, Tim Draws, Agathe Balayn, Dave Murray-Rust, Nava Tintarev, Alessandro Bozzon

Publikováno v: CHI 2023-Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

Recent research claims that information cues and system attributes of algorithmic decision-making processes affect decision subjects’ fairness perceptions. However, little is still known about how these factors interact. This paper presents a user

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::608aa42a308244e965e6a2c31eeb3a96
https://doi.org/10.1145/3544548.3581161

Are Female Chatbots More Empathic? - Discussing Gendered Conversational Agent through Empathic Design

Autor: Ji-Youn Jung, Alessandro Bozzon

Publikováno v: Proceedings of the 2nd Empathy-Centric Design Workshop, EmpathiCH 2023-Collocated with ACM CHI Conference on Human Factors in Computing Systems

Studies have shown that feminine chatbots are perceived as warmer (e.g., likable, friendly) and imbue more humanness to a machine than masculine or gender-androgynous chatbots. As chatbots are being widely deployed in various empathic contexts (e.g.,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f49990571635a9dc3ce0266fd03329f7
http://resolver.tudelft.nl/uuid:a14cf8e2-e79e-492b-8ae0-4a0c9a2090b8