Pirinen Trond Trosterud. Jack Rueter. Tyers Mariya Sheyanova. Taboada I. Maziero P. Cardoso J. Antonio M. Antonio Ana Carolina L. Alonso Gracian Trivino. Radu Tudor Ionescu Marius Popescu. Astudillo Alberto Abad. Phillips Barbara McKenzie. Tendulkar Sutanu Chakraborti. Ireland Kate Loveys. Florian Jaeger. Marcus Charles Yang. X ung Amanda Miller Micha Elsner. Anton Rytting Julie Yelle. Bender Fei Xia Kristen Howell. A Dependency-based Analysis Ruochen Niu. Raising in E nglish. Bender Michael Strube Hanna Wallach.
Leidner Vassilis Plachouras. S Rajesha N. Maria Keet Brian DeRenzi. Johan Bos. Buddhika K. Pathirage Don. Bhat Irshad Bhat Dipti Sharma. Dinu Ana Sabina Uban. Writers vs. We perform a multivariate analysis on a dataset manually annotated with news values and emotions, discovering interesting correlations among them.
We then train two competitive machine learning models β an SVM and a CNN β to predict news values from headline text and emotions as features. We find that, while both models yield a satisfactory performance, some news values are more difficult to detect than others, while some profit more from including emotion information. We analyze user viewing behavior on an online news site. We collect data from 64, news articles, and use text features to predict frequency of user views.
Both are predictive of clicking behavior, with the full article text being most predictive. This paper addresses the task of identifying the bias in news articles published during a political or social conflict. We create a silver-standard corpus based on the actions of users in social media. Specifically, we reconceptualize bias in terms of how likely a given article is to be shared or liked by each of the opposing sides.
We apply our methodology to a dataset of links collected in relation to the Russia-Ukraine Maidan crisis from We show that on the task of predicting which side is likely to prefer a given article, a Naive Bayes classifier can record The best accuracy of We also apply our methodology to gold-labeled set of articles annotated for bias, where the aforementioned Naive Bayes classifier records In this paper we present a recommender system, What To Write and Why, capable of suggesting to a journalist, for a given event, the aspects still uncovered in news articles on which the readers focus their interest.
