Mark Boukes

TL;DR: An exhaustive comparison of sentiment analysis methods using a validation set of Dutch economic headlines to compare the performance of manual annotation, crowd coding, numerous dictionaries and machine learning using both traditional and deep learning algorithms concludes that the best performance is still attained with trained human or crowd coding.

TL;DR: The authors showed that political satire positively affects the attitude toward the satirized subject via perceived funniness; this was particularly strong among those who held views congruent with the satire or lacked background knowledge.

TL;DR: The authors introduced a multilevel framework model of softening of journalistic political communication, which showed that the four most prominent concepts of political communication can be distinguished in a hierarchical model. But despite the scholarly popularity of important developments of political communications, concepts like soft news or infotainment lack conceptual clarity.

TL;DR: In this paper, the authors investigated how the use of Twitter and Facebook affects citizens' knowledge acquisition, and whether this effect is conditional upon people's political interest, using a panel survey design with repeated measures of knowledge acquisition.

TL;DR: The rationales for linkage studies are reviewed, different types of linkage Studies are outlined, the state-of-the-art in this area is reviewed, which survey and content items to use in an analysis is discussed, various types of analyses are reviewed; considerations for alternative specifications are outlined.