Zobrazeno 1 - 10
of 325
pro vyhledávání: '"Stella, Massimo"'
Machine psychology aims to reconstruct the mindset of Large Language Models (LLMs), i.e. how these artificial intelligences perceive and associate ideas. This work introduces PhDGPT, a prompting framework and synthetic dataset that encapsulates the m
Externí odkaz:
http://arxiv.org/abs/2411.10473
Autor:
Rossetti, Giulio, Stella, Massimo, Cazabet, Rémy, Abramski, Katherine, Cau, Erica, Citraro, Salvatore, Failla, Andrea, Improta, Riccardo, Morini, Virginia, Pansanella, Valentina
In this paper we introduce Y, a new-generation digital twin designed to replicate an online social media platform. Digital twins are virtual replicas of physical systems that allow for advanced analyses and experimentation. In the case of social medi
Externí odkaz:
http://arxiv.org/abs/2408.00818
Large language models are becoming increasingly integrated into our lives. Hence, it is important to understand the biases present in their outputs in order to avoid perpetuating harmful stereotypes, which originate in our own flawed ways of thinking
Externí odkaz:
http://arxiv.org/abs/2305.18320
Semantic networks provide a useful tool to understand how related concepts are retrieved from memory. However, most current network approaches use pairwise links to represent memory recall patterns. Pairwise connections neglect higher-order associati
Externí odkaz:
http://arxiv.org/abs/2304.06375
Publikováno v:
Commun Phys 6, 349 (2023)
Polarization, understood as a division into mutually hostile groups, is a common feature of social systems. It is studied in Structural Balance Theory (SBT) in terms of semicycles in signed networks. However, enumerating semicycles is computationally
Externí odkaz:
http://arxiv.org/abs/2303.16774
Autor:
Stella, Massimo, Citraro, Salvatore, Rossetti, Giulio, Marinazzo, Daniele, Kenett, Yoed N., Vitevitch, Michael S.
The mental lexicon is a complex cognitive system representing information about the words/concepts that one knows. Decades of psychological experiments have shown that conceptual associations across multiple, interactive cognitive levels can greatly
Externí odkaz:
http://arxiv.org/abs/2210.00500
Autor:
Marinazzo, Daniele, Van Roozendaal, Jan, Rosas, Fernando E., Stella, Massimo, Comolatti, Renzo, Colenbier, Nigel, Stramaglia, Sebastiano, Rosseel, Yves
Publikováno v:
Behavior Research Methods, 2024
Psychological network approaches propose to see symptoms or questionnaire items as interconnected nodes, with links between them reflecting pairwise statistical dependencies evaluated cross-sectional, time-series, or panel data. These networks consti
Externí odkaz:
http://arxiv.org/abs/2205.01035
Publikováno v:
In Computers in Human Behavior September 2024 158
Publikováno v:
Scientific Reports volume 12, Article number: 14445 (2022)
Since their announcement in November 2020, COVID-19 vaccines were largely debated by the press and social media. With most studies focusing on COVID-19 disinformation in social media, little attention has been paid to how mainstream news outlets fram
Externí odkaz:
http://arxiv.org/abs/2201.07538
Knowledge in the human mind exhibits a dualistic vector/network nature. Modelling words as vectors is key to natural language processing, whereas networks of word associations can map the nature of semantic memory. We reconcile these paradigms - frag
Externí odkaz:
http://arxiv.org/abs/2201.05061