Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection

Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection. Wahle, J. P., Ashok, N., Ruas, T., Meuschke, N., Ghosal, T., & Gipp, B. In Information for a Better World: Shaping the Global Future, volume 13192, pages 381–392. Springer International Publishing, Cham, 2022. Series Title: Lecture Notes in Computer Science

Paper doi abstract bibtex 3 downloads

A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for ﬂagging online misinformation related to COVID-19. However, these methods predominantly target speciﬁc content types (e.g., news) or platforms (e.g., Twitter). The methods’ capabilities to generalize were largely unclear so far. We evaluate ﬁfteen Transformer-based models on ﬁve COVID-19 misinformation datasets that include social media posts, news articles, and scientiﬁc papers to ﬁll this gap. We show tokenizers and models tailored to COVID-19 data do not provide a signiﬁcant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will beneﬁt future research in developing misinformation detection systems.

@incollection{smits_testing_2022,
	address = {Cham},
	title = {Testing the {Generalization} of {Neural} {Language} {Models} for {COVID}-19 {Misinformation} {Detection}},
	volume = {13192},
	isbn = {978-3-030-96956-1 978-3-030-96957-8},
	url = {https://link.springer.com/10.1007/978-3-030-96957-8_33},
	abstract = {A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for ﬂagging online misinformation related to COVID-19. However, these methods predominantly target speciﬁc content types (e.g., news) or platforms (e.g., Twitter). The methods’ capabilities to generalize were largely unclear so far. We evaluate ﬁfteen Transformer-based models on ﬁve COVID-19 misinformation datasets that include social media posts, news articles, and scientiﬁc papers to ﬁll this gap. We show tokenizers and models tailored to COVID-19 data do not provide a signiﬁcant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will beneﬁt future research in developing misinformation detection systems.},
	language = {en},
	urldate = {2022-11-11},
	booktitle = {Information for a {Better} {World}: {Shaping} the {Global} {Future}},
	publisher = {Springer International Publishing},
	author = {Wahle, Jan Philip and Ashok, Nischal and Ruas, Terry and Meuschke, Norman and Ghosal, Tirthankar and Gipp, Bela},
	editor = {Smits, Malte},
	year = {2022},
	doi = {10.1007/978-3-030-96957-8_33},
	note = {Series Title: Lecture Notes in Computer Science},
	pages = {381--392},
}

Downloads: 3

{"_id":"YpwJapzZ9YgJqBNEn","bibbaseid":"wahle-ashok-ruas-meuschke-ghosal-gipp-testingthegeneralizationofneurallanguagemodelsforcovid19misinformationdetection-2022","author_short":["Wahle, J. P.","Ashok, N.","Ruas, T.","Meuschke, N.","Ghosal, T.","Gipp, B."],"bibdata":{"bibtype":"incollection","type":"incollection","address":"Cham","title":"Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection","volume":"13192","isbn":"978-3-030-96956-1 978-3-030-96957-8","url":"https://link.springer.com/10.1007/978-3-030-96957-8_33","abstract":"A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for ﬂagging online misinformation related to COVID-19. However, these methods predominantly target speciﬁc content types (e.g., news) or platforms (e.g., Twitter). The methods’ capabilities to generalize were largely unclear so far. We evaluate ﬁfteen Transformer-based models on ﬁve COVID-19 misinformation datasets that include social media posts, news articles, and scientiﬁc papers to ﬁll this gap. We show tokenizers and models tailored to COVID-19 data do not provide a signiﬁcant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will beneﬁt future research in developing misinformation detection systems.","language":"en","urldate":"2022-11-11","booktitle":"Information for a Better World: Shaping the Global Future","publisher":"Springer International Publishing","author":[{"propositions":[],"lastnames":["Wahle"],"firstnames":["Jan","Philip"],"suffixes":[]},{"propositions":[],"lastnames":["Ashok"],"firstnames":["Nischal"],"suffixes":[]},{"propositions":[],"lastnames":["Ruas"],"firstnames":["Terry"],"suffixes":[]},{"propositions":[],"lastnames":["Meuschke"],"firstnames":["Norman"],"suffixes":[]},{"propositions":[],"lastnames":["Ghosal"],"firstnames":["Tirthankar"],"suffixes":[]},{"propositions":[],"lastnames":["Gipp"],"firstnames":["Bela"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Smits"],"firstnames":["Malte"],"suffixes":[]}],"year":"2022","doi":"10.1007/978-3-030-96957-8_33","note":"Series Title: Lecture Notes in Computer Science","pages":"381–392","bibtex":"@incollection{smits_testing_2022,\n\taddress = {Cham},\n\ttitle = {Testing the {Generalization} of {Neural} {Language} {Models} for {COVID}-19 {Misinformation} {Detection}},\n\tvolume = {13192},\n\tisbn = {978-3-030-96956-1 978-3-030-96957-8},\n\turl = {https://link.springer.com/10.1007/978-3-030-96957-8_33},\n\tabstract = {A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for ﬂagging online misinformation related to COVID-19. However, these methods predominantly target speciﬁc content types (e.g., news) or platforms (e.g., Twitter). The methods’ capabilities to generalize were largely unclear so far. We evaluate ﬁfteen Transformer-based models on ﬁve COVID-19 misinformation datasets that include social media posts, news articles, and scientiﬁc papers to ﬁll this gap. We show tokenizers and models tailored to COVID-19 data do not provide a signiﬁcant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will beneﬁt future research in developing misinformation detection systems.},\n\tlanguage = {en},\n\turldate = {2022-11-11},\n\tbooktitle = {Information for a {Better} {World}: {Shaping} the {Global} {Future}},\n\tpublisher = {Springer International Publishing},\n\tauthor = {Wahle, Jan Philip and Ashok, Nischal and Ruas, Terry and Meuschke, Norman and Ghosal, Tirthankar and Gipp, Bela},\n\teditor = {Smits, Malte},\n\tyear = {2022},\n\tdoi = {10.1007/978-3-030-96957-8_33},\n\tnote = {Series Title: Lecture Notes in Computer Science},\n\tpages = {381--392},\n}\n\n","author_short":["Wahle, J. P.","Ashok, N.","Ruas, T.","Meuschke, N.","Ghosal, T.","Gipp, B."],"editor_short":["Smits, M."],"key":"smits_testing_2022","id":"smits_testing_2022","bibbaseid":"wahle-ashok-ruas-meuschke-ghosal-gipp-testingthegeneralizationofneurallanguagemodelsforcovid19misinformationdetection-2022","role":"author","urls":{"Paper":"https://link.springer.com/10.1007/978-3-030-96957-8_33"},"metadata":{"authorlinks":{}},"downloads":3},"bibtype":"incollection","biburl":"https://api.zotero.org/groups/2503580/items?key=9bMVo5bWhsSJ7a6YWgBxjXpk&format=bibtex&limit=100","dataSources":["hBAe6Z5DsNbrQtje2","Zp98Nuv7ftsXLefzT","bQwdfx3o8Q3vnsqfH","SzFkcrpurPzNHEyqX","6KJgnNtYZiwwFkcGq","XJBi8b8xDjDoWPzcZ","kHqqD8pzLteJJWS2X","hG7rv86o2PDG2z44d","aJH3D6QaHCDgg2JGg"],"keywords":[],"search_terms":["testing","generalization","neural","language","models","covid","misinformation","detection","wahle","ashok","ruas","meuschke","ghosal","gipp"],"title":"Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection","year":2022,"downloads":3}