Date of Award
Fake news or the distribution of disinformation has become one of the most challenging issues in society. News and information are churned out across online websites and platforms in real-time, with little or no way for the viewing public to determine what is real or manufactured. But an awareness of what we are consuming online is becoming apparent and efforts are underway to explore how we separate fake content from genuine and truthful information.
The most challenging part of fake news is determining how to spot it. In technology, there are ways to help us do this. Supervised machine learning helps us to identify in a labelled dataset if a piece of information is fake or not. However, machine learning can be a black-box tool - a device, system or object which can be viewed in terms of its inputs and outputs – that focuses on one aspect of the problem and in doing so, isn’t addressing the bigger picture. To solve this issue, it is very important to understand how it works. The process of data pre-processing and the dataset labelling is part of this understanding. It is also worth knowing the algorithms mechanisms in order to choose the best one for the proposed project.
Evaluating machine learning algorithms model is one way to get better results. Changing paths within algorithms is not a bad thing if it is addressing the limitations within. With this project, we have done just this, changing from Sports news detection using Twitter API to labelled datasets and as a result we have an original Gofaas dataset, Gofaas library R package and Gofaas WebApp. Machine Learning is a demanding subject but fascinating at the same time. We hope this modest project helps people to face these challenges and learn from our findings accordingly.
Group, Gofaas; Lopez, Andrea; Vieira, Adelo; Ahsan, Zafar; Saqib, Farooq; and Marinho, Shirley, "Supervised Machine Learning Models for Fake News Detection" (2019). ICT. 8.