Predicting News Values from Headline Text and Emotions

Maria Pia di Buono, Jan Šnajder, Bojana Dalbelo Bašić, Goran Glavaš, Martin Tutek, Natasa Milic-Frayling


Abstract
We present a preliminary study on predicting news values from headline text and emotions. 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 – an SVM and a CNN – 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.
Anthology ID:
W17-4201
Volume:
Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Octavian Popescu, Carlo Strapparava
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–6
Language:
URL:
https://aclanthology.org/W17-4201
DOI:
10.18653/v1/W17-4201
Bibkey:
Cite (ACL):
Maria Pia di Buono, Jan Šnajder, Bojana Dalbelo Bašić, Goran Glavaš, Martin Tutek, and Natasa Milic-Frayling. 2017. Predicting News Values from Headline Text and Emotions. In Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism, pages 1–6, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Predicting News Values from Headline Text and Emotions (di Buono et al., 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-4201.pdf