@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.",
}

{"_id":"aNq4nXPJGoAGZysQ8","bibbaseid":"spangher-peng-ferrara-may-identifyinginformationalsourcesinnewsarticles-2023","author_short":["Spangher, A.","Peng, N.","Ferrara, E.","May, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Identifying Informational Sources in News Articles","author":[{"propositions":[],"lastnames":["Spangher"],"firstnames":["Alexander"],"suffixes":[]},{"propositions":[],"lastnames":["Peng"],"firstnames":["Nanyun"],"suffixes":[]},{"propositions":[],"lastnames":["Ferrara"],"firstnames":["Emilio"],"suffixes":[]},{"propositions":[],"lastnames":["May"],"firstnames":["Jonathan"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Bouamor"],"firstnames":["Houda"],"suffixes":[]},{"propositions":[],"lastnames":["Pino"],"firstnames":["Juan"],"suffixes":[]},{"propositions":[],"lastnames":["Bali"],"firstnames":["Kalika"],"suffixes":[]}],"booktitle":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","month":"December","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 <i>together</i> 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.","bibtex":"@inproceedings{spangher-etal-2023-identifying,\n title = \"Identifying Informational Sources in News Articles\",\n author = \"Spangher, Alexander and\n Peng, Nanyun and\n Ferrara, Emilio and\n May, Jonathan\",\n editor = \"Bouamor, Houda and\n Pino, Juan and\n Bali, Kalika\",\n booktitle = \"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing\",\n month = dec,\n year = \"2023\",\n address = \"Singapore\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://aclanthology.org/2023.emnlp-main.221\",\n doi = \"10.18653/v1/2023.emnlp-main.221\",\n pages = \"3626--3639\",\n 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.\",\n}\n\n","author_short":["Spangher, A.","Peng, N.","Ferrara, E.","May, J."],"editor_short":["Bouamor, H.","Pino, J.","Bali, K."],"key":"spangher-etal-2023-identifying","id":"spangher-etal-2023-identifying","bibbaseid":"spangher-peng-ferrara-may-identifyinginformationalsourcesinnewsarticles-2023","role":"author","urls":{"Paper":"https://aclanthology.org/2023.emnlp-main.221"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://jonmay.github.io/webpage/cutelabname/cutelabname.bib","dataSources":["j3Qzx9HAAC6WtJDHS","5eM3sAccSEpjSDHHQ"],"keywords":[],"search_terms":["identifying","informational","sources","news","articles","spangher","peng","ferrara","may"],"title":"Identifying Informational Sources in News Articles","year":2023}