AUTHOR=Elareshi Mokhtar , Al Shami Ahmad , Ziani Abdulkrim , Chaudhary Shubhda , Youssef Noora TITLE=Predicting the level of social media use among journalists: machine learning analysis JOURNAL=Frontiers in Communication VOLUME=9 YEAR=2024 URL=https://www.frontiersin.org/journals/communication/articles/10.3389/fcomm.2024.1369961 DOI=10.3389/fcomm.2024.1369961 ISSN=2297-900X ABSTRACT=

Within the long-drawn of COVID-19, the impact of social media is important for the public and journalists to re-engage with each other due to the relentless churning out of information. This paper investigates Arab journalists' use of social media during COVID-19 through Machine Learning (ML) models to predict future use and the main factor(s) deriving the respondents to such use. It aims to analyze the relationship between Arab journalists' online activity and their use of social media platforms during the COVID-19 pandemic. To assess the frequency of social media usage among Arab journalists and its correlation with their primary tasks and accomplishments. To test the accuracy of these models, we collected 1,443 Arab journalists via an online survey in 2020 using a random sampling approach. Key variables like online active journalists, Facebook group usage, and frequency of usage were studied. The received responses were subjected to ML analysis such as K-Nearest Neighbors (KNN), Decision Tree, and Ensemble Bagged Tree (EBT). The EBT predicted that Arab journalists would continue to rely on social media to various degrees as a viable source to fulfill their main tasks and accomplishments.