Predicting User Views in Online News

Daniel Hardt, Owen Rambow

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

We analyze user viewing behavior on anonline news site. We collect data from64,000 news articles, and use text featuresto predict frequency of user views.We compare predictiveness of the headlineand “teaser” (viewed before clicking) andthe body (viewed after clicking). Both arepredictive of clicking behavior, with thefull article text being most predictive.
We analyze user viewing behavior on anonline news site. We collect data from64,000 news articles, and use text featuresto predict frequency of user views.We compare predictiveness of the headlineand “teaser” (viewed before clicking) andthe body (viewed after clicking). Both arepredictive of clicking behavior, with thefull article text being most predictive.
LanguageEnglish
Title of host publicationProceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism
EditorsOctavian Popescu, Carlo Strapparava
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics
Date2017
Pages7-12
ISBN (Electronic)9781945626883
StatePublished - 2017
EventNatural Language Processing Meets Journalism: EMNLP 2017 Workshop - København, Denmark
Duration: 7 Sep 20177 Sep 2017

Workshop

WorkshopNatural Language Processing Meets Journalism
CountryDenmark
CityKøbenhavn
Period07/09/201707/09/2017

Cite this

Hardt, D., & Rambow, O. (2017). Predicting User Views in Online News. In O. Popescu, & C. Strapparava (Eds.), Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism (pp. 7-12). Stroudsburg, PA: Association for Computational Linguistics.
Hardt, Daniel ; Rambow, Owen. / Predicting User Views in Online News. Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism. editor / Octavian Popescu ; Carlo Strapparava. Stroudsburg, PA : Association for Computational Linguistics, 2017. pp. 7-12
@inproceedings{ae7178f822b0440f89074dc7fd27b730,
title = "Predicting User Views in Online News",
abstract = "We analyze user viewing behavior on anonline news site. We collect data from64,000 news articles, and use text featuresto predict frequency of user views.We compare predictiveness of the headlineand “teaser” (viewed before clicking) andthe body (viewed after clicking). Both arepredictive of clicking behavior, with thefull article text being most predictive.",
author = "Daniel Hardt and Owen Rambow",
year = "2017",
language = "English",
pages = "7--12",
editor = "Popescu, {Octavian } and Strapparava, {Carlo }",
booktitle = "Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism",
publisher = "Association for Computational Linguistics",
address = "United States",

}

Hardt, D & Rambow, O 2017, Predicting User Views in Online News. in O Popescu & C Strapparava (eds), Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism. Association for Computational Linguistics, Stroudsburg, PA, pp. 7-12, København, Denmark, 07/09/2017.

Predicting User Views in Online News. / Hardt, Daniel; Rambow, Owen.

Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism. ed. / Octavian Popescu; Carlo Strapparava. Stroudsburg, PA : Association for Computational Linguistics, 2017. p. 7-12.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Predicting User Views in Online News

AU - Hardt,Daniel

AU - Rambow,Owen

PY - 2017

Y1 - 2017

N2 - We analyze user viewing behavior on anonline news site. We collect data from64,000 news articles, and use text featuresto predict frequency of user views.We compare predictiveness of the headlineand “teaser” (viewed before clicking) andthe body (viewed after clicking). Both arepredictive of clicking behavior, with thefull article text being most predictive.

AB - We analyze user viewing behavior on anonline news site. We collect data from64,000 news articles, and use text featuresto predict frequency of user views.We compare predictiveness of the headlineand “teaser” (viewed before clicking) andthe body (viewed after clicking). Both arepredictive of clicking behavior, with thefull article text being most predictive.

M3 - Article in proceedings

SP - 7

EP - 12

BT - Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism

PB - Association for Computational Linguistics

CY - Stroudsburg, PA

ER -

Hardt D, Rambow O. Predicting User Views in Online News. In Popescu O, Strapparava C, editors, Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism. Stroudsburg, PA: Association for Computational Linguistics. 2017. p. 7-12.