.
The COVID-19 pandemic has been defined by persistent false news about the coronavirus’s behaviour and symptoms, the impact of social isolation, lockdowns, quarantine, and the medical response in terms of vaccines and medications. Indeed, several international leaders misled the public with illogical discoveries and advice about how to deal with the SARS-CoV-2 situation.
Given that the epidemic is still a concern, a study published in the International Journal of Artificial Intelligence and Soft Computing proposes a computer chatbot that detects false news using an ensemble learning approach. The chatbot, nicknamed CovFakeBot, was created by a team from India’s University of Delhi and was taught using well-known machine-learning methods. On the microblogging network, Twitter can distinguish between true and fraudulent news on the COVID-19 epidemic.
Hunar Batra, Gunjan Kanwar Palawan, Kanika Gupta, Priadarshana, Supragya, Deepali Bajaj, and Urmil Bharti of the Department of Computer Science at the Shaheed Rajguru College of Applied Sciences for Women explain that their chatbot combines a well-known messenger app’s application programming interface (API), specifically the WhatsApp Business API, with another communications technology, Twilio, to create a conversational user On a Twitter dataset, the researchers evaluated the chatbot with 10 different machine learning and ensemble learning classifiers. The most accurate model was shown to be a soft-voting model.
The CovFakeBot, according to the researchers, might become a highly valuable tool for social media users looking to rapidly determine if an item of concern is legitimate news or false news.
They go on to say that expanding the system to other areas where false news is a problem would be a simple matter of training a new instance of the chatbot with a new dataset in the area of interest. They expect that CovFakeBot and its relatives will be effective in reducing the propagation of false news on social media in the long term.
