Methodology for identifying and tracking social media misinformation in tweets about the impact of the COVID-19 pandemic on reproductive health

Abstract

Abstract The purpose of the study was to develop the methodology identifying and tracking social media misinformation in tweets about the impact of the coronavirus and COVID-vaccine on reproductive health, one of the reasons for which is the lack of awareness about aspects of the coronavirus infection. We use a combination of machine and expert methods, and use the latest scientific articles as the standard for detecting disinformation. The proposed methodology includes the study of scientific articles as a source of reliable truthful information about the topic (information standard) and Twitter messages (assessment of information compliance with the standard). The result of the study is a methodology for detecting disinformation in the messages of social network users. Based on this methodology, the following aspects of the problem have been developed: 1) the formation of a scientific standard; 2) the principle of comparing the directions of scientific research and discussions on Twitter; 3) the principle of contextual comparison of user and scientific ideas about problems. An original methodology for identifying disinformation in social networks is proposed. In contrast to existing works, principles based on the processing of information from the content of scientific articles and messages from social networks are formulated.