XAIvsDisinfo: eXplainable AI Methods for Categorisation and Analysis of COVID-19 Vaccine Disinformation and Online Debates

点击翻译按钮获取中文摘要

UK vaccination rates are in decline and experts believe that vaccine disinformation, widely spreadin social media, may be one of the reasons. Recent surveys have established that vaccinedisinformation is impacting negatively citizen trust in COVID-19 vaccination specifically. As aresponse, the UK Government agreed with Twitter, Facebook, and YouTube measures to limit thespread of disinformation. However, simply removing disinformation from platforms is not enough,as the government also needs to monitor and respond to the concerns of vaccine hesitant citizens.Moreover, manual detection and tracking of disinformation, as currently practiced by manyjournalists, is infeasible, given the scale of social media.XAIvsDinfo aims to address these gaps through novel research on explainable AI-based models forlarge-scale analysis of vaccine disinformation. Specifically, vaccine disinformation will be classifiedautomatically into the six narrative types defined by First Draft. A second model will categorisevaccine statements as pro-vaccine, anti-vaccine, vaccine-hesitant, or other.We will investigate explainable machine learning approaches that are human interpretable: bothin detecting errors and weaknesses of the models and in providing human-readable explanationsof the models' decisions.XAIvsDisinfo will also create two new multi-platform datasets and organise a new communityresearch challenge on cross-platform analysis of vaccine disinformation, as follow-up from ourRumourEval one.Our XAI models and tools will be integrated into the open-source InVID-WeVerify plugin, for takeup by journalists and fact-checkers. The project outputs will also contribute to evidence-basedpolicy activities by the UK government on improving citizen perception of COVID-19 vaccines.