@inproceedings{spangher-etal-2023-identifying,
title = "Identifying Informational Sources in News Articles",
author = "Spangher, Alexander and
Peng, Nanyun and
Ferrara, Emilio and
May, Jonathan",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.221",
doi = "10.18653/v1/2023.emnlp-main.221",
pages = "3626--3639",
abstract = "News articles are driven by the informational sources journalists use in reporting. Modeling when, how and why sources get used together in stories can help us better understand the information we consume and even help journalists with the task of producing it. In this work, we take steps toward this goal by constructing the largest and widest-ranging annotated dataset, to date, of informational sources used in news writing. We first show that our dataset can be used to train high-performing models for information detection and source attribution. Then, we introduce a novel task, source prediction, to study the compositionality of sources in news articles {--} i.e. how they are chosen to complement each other. We show good modeling performance on this task, indicating that there is a pattern to the way different sources are used \textit{together} in news storytelling. This insight opens the door for a focus on sources in narrative science (i.e. planning-based language generation) and computational journalism (i.e. a source-recommendation system to aid journalists writing stories). All data and model code can be found at https://github.com/alex2awesome/source-exploration.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spangher-etal-2023-identifying">
<titleInfo>
<title>Identifying Informational Sources in News Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Spangher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emilio</namePart>
<namePart type="family">Ferrara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>News articles are driven by the informational sources journalists use in reporting. Modeling when, how and why sources get used together in stories can help us better understand the information we consume and even help journalists with the task of producing it. In this work, we take steps toward this goal by constructing the largest and widest-ranging annotated dataset, to date, of informational sources used in news writing. We first show that our dataset can be used to train high-performing models for information detection and source attribution. Then, we introduce a novel task, source prediction, to study the compositionality of sources in news articles – i.e. how they are chosen to complement each other. We show good modeling performance on this task, indicating that there is a pattern to the way different sources are used together in news storytelling. This insight opens the door for a focus on sources in narrative science (i.e. planning-based language generation) and computational journalism (i.e. a source-recommendation system to aid journalists writing stories). All data and model code can be found at https://github.com/alex2awesome/source-exploration.</abstract>
<identifier type="citekey">spangher-etal-2023-identifying</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.221</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.221</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>3626</start>
<end>3639</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Informational Sources in News Articles
%A Spangher, Alexander
%A Peng, Nanyun
%A Ferrara, Emilio
%A May, Jonathan
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F spangher-etal-2023-identifying
%X News articles are driven by the informational sources journalists use in reporting. Modeling when, how and why sources get used together in stories can help us better understand the information we consume and even help journalists with the task of producing it. In this work, we take steps toward this goal by constructing the largest and widest-ranging annotated dataset, to date, of informational sources used in news writing. We first show that our dataset can be used to train high-performing models for information detection and source attribution. Then, we introduce a novel task, source prediction, to study the compositionality of sources in news articles – i.e. how they are chosen to complement each other. We show good modeling performance on this task, indicating that there is a pattern to the way different sources are used together in news storytelling. This insight opens the door for a focus on sources in narrative science (i.e. planning-based language generation) and computational journalism (i.e. a source-recommendation system to aid journalists writing stories). All data and model code can be found at https://github.com/alex2awesome/source-exploration.
%R 10.18653/v1/2023.emnlp-main.221
%U https://aclanthology.org/2023.emnlp-main.221
%U https://doi.org/10.18653/v1/2023.emnlp-main.221
%P 3626-3639
Markdown (Informal)
[Identifying Informational Sources in News Articles](https://aclanthology.org/2023.emnlp-main.221) (Spangher et al., EMNLP 2023)
ACL
- Alexander Spangher, Nanyun Peng, Emilio Ferrara, and Jonathan May. 2023. Identifying Informational Sources in News Articles. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3626–3639, Singapore. Association for Computational Linguistics.