This week, we attempted to modify the machine learning model so that it would include the source of the article when categorizing the article as fake or real. We also changed the Real/Fake tag to Biased/Not Biased as to make it more neutral and objective.
we ran into some problems with the modification though. The type of model that we were using only takes one input matrix which has been taken as the “text” part of the article. now we need to at another input as the “source” part of the article, but we cant input a second matrix as that is not how the model we are using is built. We are still looking for ways to solve this problem and we will hopefully have it working by next week.