Abstract

This study investigates the dissemination of disinformation on social media platforms during the DANA event (DANA is a Spanish acronym for Depresion Aislada en Niveles Altos ´ , translating to high-altitude isolated depression) that resulted in extremely heavy rainfall and devastating floods in Valencia, Spain, on October 29, 2024. We created a novel dataset of 650 TikTok and X posts, which was manually annotated to differentiate between disinformation and trustworthy content. Additionally, a Few-Shot annotation approach with GPT-4o achieved substantial agreement (Cohen’s kappa of 0.684) with manual labels. Emotion analysis revealed that disinformation on X is mainly associated with increased sadness and fear, while on TikTok, it correlates with higher levels of anger and disgust. Linguistic analysis using the LIWC dictionary showed that trustworthy content utilizes more articulate and factual language, whereas disinformation employs negations, perceptual words, and personal anecdotes to appear credible. Audio analysis of TikTok posts highlighted distinct patterns: trustworthy audios featured brighter tones and robotic or monotone narration, promoting clarity and credibility, while disinformation audios leveraged tonal variation, emotional depth, and manipulative musical elements to amplify engagement. In detection models, SVM+TF-IDF achieved the highest F1-Score, excelling with limited data. Incorporating audio features into roberta-large-bne improved both Accuracy and F1-Score, surpassing its text-only counterpart and SVM in Accuracy. GPT-4o Few-Shot also performed well, showcasing the potential of large language models for automated disinformation detection. These findings demonstrate the importance of leveraging both textual and audio features for improved disinformation detection on multimodal platforms like TikTok.

Abstract

The use of analytical tools to measure the size and behaviour of the audience has become a hallmark of digital media. In the past, print media, radio and television used audience measurement systems primarily for advertising and sales-related purposes. In today’s digital ecosystem, however, data analysis has become more sophisticated and has begun to shape news production, giving rise to metrics-driven news. Based on a historical review of the use of audience and data measurement systems by the media, this chapter describes the current uses of analytical tools in newsrooms, through examples of their recent implementation in international media. The effects of web analytics on news agenda and the roles of these technologies in the current developments of automated, AI-driven journalism are theoretically discussed. All in all, this chapter explores the far-reaching impact of digital metrics, pointing out the opportunities and challenges the new analytical tools pose to journalism, as well as their ethical implications.

Book abstract

El libro La inteligencia artificial y la transformación del periodismo realiza un diagnóstico de las herramientas y aplicaciones que utiliza la inteligencia artificial (IA) para crear nuevas narrativas y generar contenido.

Integrado por nueve capítulos que aportan nuevas visiones sobre las posibles aplicaciones transformadoras de esta nueva disciplina, este libro ofrece una visión estructurada y bien documentada que compone una excelente muestra de los últimos avances científicos respecto al uso de la IA en el periodismo desde diversas perspectivas teóricas y metodológicas, entre ellas:
—La regulación de la IA en la Unión Europea.
—La preparación de los periodistas y las redacciones frente al desarrollo de los modelos de IA.
—Oportunidades y riesgos derivados de la implementación de la IA en los medios públicos europeos.
—Las posibilidades de futuro de la IA en el campo periodístico desde la óptica de la lingüística computacional.
—Los discursos periodisticos sobre la IA.
—La curación de contenidos orientada a la creación de textos periodísticos de calidad apoyados en modelos de IA.
—El funcionamiento de los chatbots de IA generativa para mejorar la distribución de información verificada.

Abstract

Disinformation has influenced public trust in democratic institutions, particularly the media. Through examples from countries with varying levels of democratic quality, it is demonstrated how disinformation is used to polarize and politically mobilize. The role of the media in this context is crucial, as trust in them depends on multiple interrelated factors, such as the impact of disinformation on news consumption and public trust, the psychological and sociocultural factors that affect vulnerability to disinformation, and technological advances, especially generative artificial intelligence. Based on this diagnosis, mechanisms of self-regulation and increased transparency are proposed as foundations to improve trust. Additionally, the need for academic research on the role of digital platforms and algorithms in the spread of dis­information and its impact on trust and democratic quality is emphasized.