Evolving linguistic divergence on polarizing social media

Humanities and Social Sciences Communications, Год журнала: 2024, Номер 11(1)

Опубликована: Март 15, 2024

Abstract Language change is influenced by many factors, but often starts from synchronic variation, where multiple linguistic patterns or forms coexist, different speech communities use language in increasingly ways. Besides regional economic reasons, may form and segregate based on political alignment. The latter, referred to as polarization, of growing societal concern across the world. Here we map quantify divergence partisan left-right divide United States, using social media data. We develop a general methodology delineate (social) users their preference, which (potentially biased) news accounts they do not follow given platform. Our data consists 1.5M short posts 10k (about 20M words) platform Twitter (now “X”). Delineating this sample involved mining for lists followers ( n = 422M) 72 large accounts. topics conversation word frequencies, messaging sentiment, lexical semantics words emoji. find signs all these aspects, especially themes conversation, line with previous research. While US American English remains largely intelligible within its community, our findings point at areas miscommunication eventually arise ongoing polarization therefore potential divergence. flexible — combining mining, lexicostatistics, machine learning, models systematic human annotation approach agnostic. In other words, while focus here divides English, same applicable countries, languages, platforms.

Язык: Английский

---

De “love” a “sad”: sintonía afectiva en el debate digital de las elecciones generales españolas 2023

Palabra Clave, Год журнала: 2025, Номер 28(1), С. 1 - 31

Опубликована: Фев. 25, 2025

En este artículo, se analiza el nivel de emotivismo en debate político digital Facebook las elecciones generales españolas 2023 a partir cuentas oficiales y verificadas partidos, líderes políticos, medios comunicación, usuarios usuarias. Se han descargado 34 968 mensajes durante periodo oficial campaña electoral ha realizado una clasificación estos tres grupos agentes: partidos conectivos, comunicación otros actores acción conectiva. utilizado técnicas big data para analizar los aplicado NRC Emotion Lexicon medir emociones presentes. Los hallazgos muestran la alta congruencia afectiva debido que tienen bajo contenido emocional. La presencia emoción “me divierte” reacciones asciende casi mitad. Esto puede ser un indicador ironía descontento hacia publicados proceso electoral. casos con baja sintonía afectiva, destaca sobredimensionalidad divierte”. Estos resultados son relevantes desde enfoque emotivista porque arrojan luz sobre tipo debates movilizan opinión pública y, ocasiones, otras dinámicas negativas alejan del ideal democrático.

---

Relative engagement with sources of climate misinformation is growing across social media platforms

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 28, 2025

Язык: Английский

---

The Koo Dataset: An Indian Microblogging Platform with Global Ambitions

Proceedings of the International AAAI Conference on Web and Social Media, Год журнала: 2024, Номер 18, С. 1991 - 2002

Опубликована: Май 28, 2024

Increasingly, alternative platforms are playing a key role in the social media ecosystem. Koo, microblogging platform based India, has emerged as major new network hosting high profile politicians from several countries (India, Brazil, Nigeria) and many internationally renowned celebrities. This paper presents largest publicly available Koo dataset, spanning platform’s founding early 2020 to September 2023, providing detailed metadata for 72M posts, 75M comments, 40M shares, 284M likes 1.4M user profiles. Along with release of we provide an overview including discussion news ecosystem on platform, hashtag usage, engagement. Our results highlight pivotal that play shaping online communities emerging economies Global South, connecting local public figures their followers. With Koo’s ambition become town hall diverse non-English speaking communities, our dataset offers opportunities studying beyond Western context.

Язык: Английский

---

Trends and topics: Characterizing echo chambers’ topological stability and in-group attitudes

PLOS complex systems., Год журнала: 2024, Номер 1(2), С. e0000008 - e0000008

Опубликована: Окт. 3, 2024

Язык: Английский

---