arXiv subjects

Donald Ruggiero Lo Sardo

Publications and source records attributed to Donald Ruggiero Lo Sardo.

4 recordsLinked to original sources

arXiv2025

Language bubbles in online social networks

Social media platforms have become essential spaces for public discourse. While political polarisation and limited communication across different groups are widely acknowledged, the connection between social network fragmentation and the language features and quality used by various communities has received insufficient attention. This study aims to fill this gap by examining the social structure and linguistic richness of the Italian debate on Twitter/X. We analyse tweets and retweets from Italian politicians and news outlets between 2018 and 2022, characterising the retweet network and evaluating the language used within different communities through various lexical metrics. Our analysis uncovers two systematic patterns: communities closer in the network tend to use more similar vocabulary, while isolated communities consistently demonstrate lower lexical diversity and richness. Together, these patterns illustrate what we call ``language bubbles''. These findings indicate that socially isolated communities interact less with others and develop distinct and poorer linguistic profiles, highlighting a structural link between social fragmentation and linguistic divergence.

physics.soc-ph↗

arXiv2025

From trust in news to disagreement: is misinformation more controversial?

The growing prevalence of fruitless disagreement threatens social cohesion and constructive public discourse. While polarised discussions often reflect distrust in the news, the link between disagreement and misinformation remains unclear. In this study, we used data from "Cartesio", an online experiment rating the trustworthiness of Italian news articles annotated for reliability by experts, to develop a disagreement metric that accounts for differences in mean trust values. Our findings show that while misinformation is rated as less trustworthy, it is not more controversial. Furthermore, disagreement correlates with increased commenting on Facebook. This suggests that combating misinformation alone may not reduce polarisation. Disagreement focuses more on the divergence of opinions, trust, and their effects on social cohesion. Our study lays the groundwork for unsupervised news analysis and highlights the need for platform design that promotes constructive interactions and reduces divisiveness.

physics.soc-ph↗

arXiv2023

Exploitation and exploration in text evolution. Quantifying planning and translation flows during writing

Writing is a complex process at the center of much of modern human activity. Despite it appears to be a linear process, writing conceals many highly non-linear processes. Previous research has focused on three phases of writing: planning, translation and transcription, and revision. While research has shown these are non-linear, they are often treated linearly when measured. Here, we introduce measures to detect and quantify subcycles of planning (exploration) and translation (exploitation) during the writing process. We apply these to a novel dataset that recorded the creation of a text in all its phases, from early attempts to the finishing touches on a final version. This dataset comes from a series of writing workshops in which, through innovative versioning software, we were able to record all the steps in the construction of a text. More than 60 junior researchers in science wrote a scientific essay intended for a general readership. We recorded each essay as a writing cloud, defined as a complex topological structure capturing the history of the essay itself. Through this unique dataset of writing clouds, we expose a representation of the writing process that quantifies its complexity and the writer's efforts throughout the draft and through time. Interestingly, this representation highlights the phases of "translation flow", where authors improve existing ideas, and exploration, where creative deviations appear as the writer returns to the planning phase. These turning points between translation and exploration become rarer as the writing process progresses and the author approaches the final version. Our results and the new measures introduced have the potential to foster the discussion about the non-linear nature of writing and support the development of tools that can support more creative and impactful writing processes.

cs.CL↗

arXiv2020

comp-syn: Perceptually Grounded Word Embeddings with Color

Popular approaches to natural language processing create word embeddings based on textual co-occurrence patterns, but often ignore embodied, sensory aspects of language. Here, we introduce the Python package comp-syn, which provides grounded word embeddings based on the perceptually uniform color distributions of Google Image search results. We demonstrate that comp-syn significantly enriches models of distributional semantics. In particular, we show that (1) comp-syn predicts human judgments of word concreteness with greater accuracy and in a more interpretable fashion than word2vec using low-dimensional word-color embeddings, and (2) comp-syn performs comparably to word2vec on a metaphorical vs. literal word-pair classification task. comp-syn is open-source on PyPi and is compatible with mainstream machine-learning Python packages. Our package release includes word-color embeddings for over 40,000 English words, each associated with crowd-sourced word concreteness judgments.

cs.CL↗