1 code implementation • 3 Mar 2024 • Alba Aguilera, Nieves Montes, Georgina Curto, Carles Sierra, Nardine Osman
We classify policies as discriminatory or non-discriminatory against the poor, with the support of specialized NGOs, and we observe the results in the AABM in terms of the impact on wealth inequality.
no code implementations • 1 Mar 2024 • Thiago Freitas dos Santos, Nardine Osman, Marco Schorlemmer
This paper conducts a user study to assess whether three machine learning (ML) interpretability layouts can influence participants' views when evaluating sentences containing hate speech, focusing on the "Misogyny" and "Racism" classes.
no code implementations • 9 Feb 2024 • Nardine Osman, Mark d'Inverno
Taking as our starting point the wealth of research investigating the nature of human values from social psychology over the last few decades, we set out to provide such a formal model.
no code implementations • 20 Sep 2023 • Nardine Osman, Bruno Rosell i Gui, Carles Sierra
This paper addresses the issue of connecting people online to help them find support with their day-to-day problems.
no code implementations • 4 May 2023 • Nardine Osman, Mark d'Inverno
In the diverse array of work investigating the nature of human values from psychology, philosophy and social sciences, there is a clear consensus that values guide behaviour.
no code implementations • 4 May 2023 • Nardine Osman, Mark d'Inverno
One of the major challenges we face with ethical AI today is developing computational systems whose reasoning and behaviour are provably aligned with human values.
no code implementations • 17 Feb 2023 • Nieves Montes, Nardine Osman, Carles Sierra, Marija Slavkovik
We argue that this type of normative reasoning, where agents are endowed with an understanding of norms' moral implications, leads to value-awareness in autonomous agents.
no code implementations • 26 Jan 2023 • Nardine Osman, Bruno Rosell, Carles Sierra, Marco Schorlemmer, Jordi Sabater-Mir, Lissette Lemus
uHelp's intelligent search for volunteers is based on a number of AI technologies: (1) a novel trust-based flooding algorithm that navigates one's social network looking for appropriate trustworthy volunteers; (2) a novel trust model that maintains the trustworthiness of peers by learning from their similar past experiences; and (3) a semantic similarity model that assesses the similarity of experiences.
no code implementations • 18 Oct 2021 • Carles Sierra, Nardine Osman, Pablo Noriega, Jordi Sabater-Mir, Antoni Perelló
Value alignment is then defined, and computed, for a given norm with respect to a given value through the increase/decrease that it results in the preferences of future states of the world.
no code implementations • 30 Apr 2021 • Thiago Freitas dos Santos, Nardine Osman, Marco Schorlemmer
In this paper, we focus on normative systems for online communities.