id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-197474-2wzf7nzz	Baly, Ramy	We Can Detect Your Bias: Predicting the Political Ideology of News Articles	2020-10-11		.txt	text/plain	5359	259	54	We further use a challenging experimental setup where the test examples come from media that were not seen during training, which prevents the model from learning to detect the source of the target news article instead of predicting its political ideology. Furthermore, in order to ensure that we are actually modeling the political ideology as it is expressed in the language of the news, we created evaluation splits in two different ways: (i) randomly, which is what is typically done (for comparison only), and (ii) based on media, where all articles by the same medium appear in either the training, the validation, or the testing dataset. The task of predicting the political ideology of news articles is typically formulated as a classification problem, where the textual content of the articles is encoded into a vector representation that is used to train a classifier to predict one of C classes (in our case, C = 3: left, center, and right).	./cache/cord-197474-2wzf7nzz.txt	./txt/cord-197474-2wzf7nzz.txt