Predicting news values from headline text and emotions

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationEMNLP 2017 - 2nd Workshop on Natural Language Processing Meets Journalism, NLPmJ 2017 - Proceedings of the Workshop
EditorsOctavian Popescu, Carlo Strapparava
PublisherAssociation for Computational Linguistics (ACL)
Pages1-6
Number of pages6
ISBN (Electronic)9781945626883
Publication statusPublished - 2017
Externally publishedYes
EventEMNLP 2017 2nd Workshop on Natural Language Processing Meets Journal., NLPmJ 2017 - Copenhagen, Denmark
Duration: 7 Sept 2017 → …

Publication series

NameEMNLP 2017 - 2nd Workshop on Natural Language Processing Meets Journalism, NLPmJ 2017 - Proceedings of the Workshop

Conference

ConferenceEMNLP 2017 2nd Workshop on Natural Language Processing Meets Journal., NLPmJ 2017
Country/TerritoryDenmark
CityCopenhagen
Period7/09/17 → …

Fingerprint

Dive into the research topics of 'Predicting news values from headline text and emotions'. Together they form a unique fingerprint.

Cite this