We introduce and study the task of clickbait spoiling: generating a short text that satisfies the curiosity induced by a clickbait post. Clickbait links to a web page and advertises its contents by arousing curiosity instead of providing an informative summary. Our contributions are approaches to classify the type of spoiler needed (i.e., a phrase or a passage), and to generate appropriate spoilers. A large-scale evaluation and error analysis on a new corpus of 5,000 manually spoiled clickbait posts -- the Webis Clickbait Spoiling Corpus 2022 -- shows that our spoiler type classifier achieves an accuracy of 80\%, while the question answering model DeBERTa-large outperforms all others in generating spoilers for both types.
%0 Journal Article
%1 Hagen2022-eu
%A Hagen, Matthias
%A Fröbe, Maik
%A Jurk, Artur
%A Potthast, Martin
%D 2022
%I arXiv
%K
%T Clickbait spoiling via question answering and passage retrieval
%X We introduce and study the task of clickbait spoiling: generating a short text that satisfies the curiosity induced by a clickbait post. Clickbait links to a web page and advertises its contents by arousing curiosity instead of providing an informative summary. Our contributions are approaches to classify the type of spoiler needed (i.e., a phrase or a passage), and to generate appropriate spoilers. A large-scale evaluation and error analysis on a new corpus of 5,000 manually spoiled clickbait posts -- the Webis Clickbait Spoiling Corpus 2022 -- shows that our spoiler type classifier achieves an accuracy of 80\%, while the question answering model DeBERTa-large outperforms all others in generating spoilers for both types.
@article{Hagen2022-eu,
abstract = {We introduce and study the task of clickbait spoiling: generating a short text that satisfies the curiosity induced by a clickbait post. Clickbait links to a web page and advertises its contents by arousing curiosity instead of providing an informative summary. Our contributions are approaches to classify the type of spoiler needed (i.e., a phrase or a passage), and to generate appropriate spoilers. A large-scale evaluation and error analysis on a new corpus of 5,000 manually spoiled clickbait posts -- the Webis Clickbait Spoiling Corpus 2022 -- shows that our spoiler type classifier achieves an accuracy of 80\%, while the question answering model DeBERTa-large outperforms all others in generating spoilers for both types.},
added-at = {2024-09-10T11:56:37.000+0200},
author = {Hagen, Matthias and Fr{\"o}be, Maik and Jurk, Artur and Potthast, Martin},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/22cb156b2bd3cd5b4d60b1c8353f1c950/scadsfct},
interhash = {09ae7fa19fe5a44880b0b726d3038d67},
intrahash = {2cb156b2bd3cd5b4d60b1c8353f1c950},
keywords = {},
publisher = {arXiv},
timestamp = {2024-09-10T15:15:57.000+0200},
title = {Clickbait spoiling via question answering and passage retrieval},
year = 2022
}