Quality of science journalism in the age of Artificial Intelligence explored with a mixed methodology

• Published in: PloS one 2024-06, Vol.19 (6), p.e0303367
• Main Authors: Dijkstra, Anne M, de Jong, Anouk, Boscolo, Marco
• Format: Article
• Language: English
• Subjects: Accessibility; Artificial Intelligence; Biology and Life Sciences; Chatbots; Communication; Computational linguistics; Computer and Information Sciences; Content analysis; Ecology and Environmental Sciences; Ecosystems; Europe; False information; Generative artificial intelligence; Humans; Italy; Journalism; Journalists; Language processing; Mass Media; Methods; Natural language interfaces; News; Pandemics; People and places; Portugal; Public domain; Quality control; Science; Social networks; Social Sciences; Translations
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0303367

Science journalists, traditionally, play a key role in delivering science information to a wider audience. However, changes in the media ecosystem and the science-media relationship are posing challenges to reliable news production. Additionally, recent developments such as ChatGPT and Artificial Intelligence (AI) more generally, may have further consequences for the work of (science) journalists. Through a mixed-methodology, the quality of news reporting was studied within the context of AI. A content analysis of media output about AI (news articles published within the time frame 1 September 2022-28 February 2023) explored the adherence to quality indicators, while interviews shed light on journalism practices regarding quality reporting on and with AI. Perspectives from understudied areas in four European countries (Belgium, Italy, Portugal, and Spain) were included and compared. The findings show that AI received continuous media attention in the four countries. Furthermore, despite four different media landscapes, the reporting in the news articles adhered to the same quality criteria such as applying rigour, including sources of information, accessibility, and relevance. Thematic analysis of the interview findings revealed that impact of AI and ChatGPT on the journalism profession is still in its infancy. Expected benefits of AI related to helping with repetitive tasks (e.g. translations), and positively influencing journalistic principles of accessibility, engagement, and impact, while concerns showed fear for lower adherence to principles of rigour, integrity and transparency of sources of information. More generally, the interviewees expressed concerns about the state of science journalism, including a lack of funding influencing the quality of reporting. Journalists who were employed as staff as well as those who worked as freelancers put efforts in ensuring quality output, for example, via editorial oversight, discussions, or memberships of associations. Further research into the science-media relationship is recommended.