Firstly, a novel ranking-based approach leveraging the scalable information retrieval infrastructure is applied to detect misinformation from a huge collection of unlabelled tweets based on a related but very small labelled misinformation data set. This paper proposes a two-step ranking-based misinformation detection (RMiD) technique. The spread of misinformation is unavoidable in an extraordinary situation like Covid-19, and the consequences can be dreadful. Unfortunately, people commonly use these platforms to share misinformation which can influence other people adversely. Social media platforms like Twitter have become an easy portal for billions of people to connect and exchange their thoughts. We showcase the efficacy of the proposed method in hate speech and fear detection on the tweets collection during COVID-19 where the labelled information is unavailable. To address this problem, we propose a novel concept of unsupervised progressive domain adaptation based on a deep-learning language model generated through multiple text datasets. However, the predictive accuracy of these hate detection models decreases significantly if the data distribution of the target domain, where the prediction will be applied, is different.
Related labelled hate data from other domains or previous incidents may be available. However, obtaining the labelled data in suddenly changed circumstances as a pandemic is expensive and acquiring them in a short time is impractical. Developing the fear and hate detection methods based on machine learning requires labelled data.
Monitoring and control of abuse on social media, especially during pandemics such as COVID-19, can help in keeping the public sentiment and morale positive. In this world of information and experience era, microblogging sites have been commonly used to express people feelings including fear, panic, hate and abuse.
0 kommentar(er)
