Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning

OPEN ARCHIVE

Union Jack
Dannebrog

Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning

Show simple item record

dc.contributor.author Hardt, Daniel
dc.contributor.author Hovy, Dirk
dc.contributor.author Sotiris, Lamprinidis
dc.date.accessioned 2018-11-08T15:14:51Z
dc.date.available 2018-11-08T15:14:51Z
dc.date.issued 2018-11-08
dc.identifier.uri http://hdl.handle.net/10398/9683
dc.description.abstract Newspapers need to attract readers with headlines, anticipating their readers’ preferences. These preferences rely on topical, structural, and lexical factors. We model each of these factors in a multi-task GRU network to predict headline popularity. We find that pre-trained word embeddings provide significant improvements over untrained embeddings, as do the combination of two auxiliary tasks, newssection prediction and part-of-speech tagging. However, we also find that performance is very similar to that of a simple Logistic Regression model over character n-grams. Feature analysis reveals structural patterns of headline popularity, including the use of forward-looking deictic expressions and second person pronouns. en_US
dc.format.extent 6 en_US
dc.language eng en_US
dc.title Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning en_US
dc.type cp en_US
dc.accessionstatus modt18nov08 soma en_US
dc.contributor.corporation Copenhagen Business School. CBS en_US
dc.contributor.department Institut for Digitalisering en_US
dc.contributor.departmentshort DIGI en_US
dc.contributor.departmentuk Department of Digitalization en_US
dc.contributor.departmentukshort DIGI en_US
dc.description.notes Paper presented at the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP2018). October 31 - November 4 2018, Brussels, Belgium en_US
dc.publisher.year 2018 en_US


Creative Commons License This work is licensed under a Creative Commons License.

Files Size Format View
Hardt_Hovy_Lamprinidis.pdf 1.261Mb PDF View/Open Paper

This item appears in the following Collection(s)

Show simple item record