Confinement.bib

@article{duval_analyse_2016,
	title = {L'analyse automatisée du ton médiatique : construction et utilisation de la version française du \textit{{Lexicoder} {Sentiment} {Dictionary}}},
	volume = {49},
	issn = {0008-4239, 1744-9324},
	shorttitle = {L'analyse automatisée du ton médiatique},
	url = {https://www.cambridge.org/core/product/identifier/S000842391600055X/type/journal_article},
	doi = {10.1017/S000842391600055X},
	abstract = {Résumé
            
              Cet article introduit un nouveau dictionnaire permettant l'analyse automatisée du ton des médias francophones, que nous avons appelé
              Lexicoder Sentiment Dictionnaire Français
              (
              LSDFr
              ) en référence au lexique anglophone de Young et Soroka (2012),
              Lexicoder Sentiment Dictionary
              (
              LSD
              ) à partir duquel le
              LSDFr
              a été construit. Une fois construit, nous comparons le
              LSDFr
              au seul autre dictionnaire francophone existant de ce genre,
              Linguistic Inquiry and Word Count
              (
              LIWC
              ). Nous testons ensuite la validité interne du
              LSDFr
              en le comparant avec un corpus de textes codés manuellement. Nous testons enfin la validité externe du
              LSDFr
              en mesurant jusqu'où le ton médiatique, calculé à l'aide de notre dictionnaire, prédit les intentions de vote des Québécois lors des quatre dernières campagnes électorales. En développant cet outil, notre objectif est de permettre à d'autres chercheurs d'effectuer des analyses médiatiques dans un corpus de textes comparables en français.
            
          , 
            Abstract
            
              This article introduces a new dictionary for the automated analysis of the tone of French media. We named it the
              French Lexicoder Sentiment Dictionary
              (
              LSDFr
              ) in reference to the English lexicon developed by Young and Soroka (2012), the
              Lexicoder Sentiment Dictionary
              (
              LSD
              ), from which the
              LSDFr
              was built. We compare the
              LSDFr
              to the only other French sentiment lexicon,
              Linguistic Inquiry and Word Count
              (
              LIWC
              ). First, we detail the construction of the dictionary. We then test the internal validity of the
              LSDFr
              comparing it with a corpus of manually coded texts. Finally, we test the external validity of
              LSDFr
              by measuring how the media tone, calculated using our dictionary, predicts voting intentions in the last four Quebec elections. Our goal is to enable other researchers to conduct media analyses with a comparable corpus of texts in French.},
	language = {en},
	number = {2},
	urldate = {2019-05-24},
	journal = {Canadian Journal of Political Science},
	author = {Duval, Dominic and Pétry, François},
	month = jun,
	year = {2016},
	pages = {197--220}
}

@article{fruchterman_graph_1991,
	title = {Graph drawing by force-directed placement},
	volume = {21},
	issn = {00380644, 1097024X},
	url = {http://doi.wiley.com/10.1002/spe.4380211102},
	doi = {10.1002/spe.4380211102},
	language = {en},
	number = {11},
	urldate = {2019-08-11},
	journal = {Software: Practice and Experience},
	author = {Fruchterman, Thomas M. J. and Reingold, Edward M.},
	month = nov,
	year = {1991},
	pages = {1129--1164}
}

@article{arnold_tidy_2017,
	title = {A {Tidy} {Data} {Model} for {Natural} {Language} {Processing} using {cleanNLP}},
	volume = {9},
	issn = {2073-4859},
	url = {https://journal.r-project.org/archive/2017/RJ-2017-035/index.html},
	doi = {10.32614/RJ-2017-035},
	abstract = {Recent advances in natural language processing have produced libraries that extract lowlevel features from a collection of raw texts. These features, known as annotations, are usually stored internally in hierarchical, tree-based data structures. This paper proposes a data model to represent annotations as a collection of normalized relational data tables optimized for exploratory data analysis and predictive modeling. The R package cleanNLP, which calls one of two state of the art NLP libraries (CoreNLP or spaCy), is presented as an implementation of this data model. It takes raw text as an input and returns a list of normalized tables. Specific annotations provided include tokenization, part of speech tagging, named entity recognition, sentiment analysis, dependency parsing, coreference resolution, and word embeddings. The package currently supports input text in English, German, French, and Spanish.},
	language = {en},
	number = {2},
	urldate = {2019-08-11},
	journal = {The R Journal},
	author = {Arnold, Taylor},
	year = {2017},
	pages = {248}
}

@article{kobayashi_text_2018,
	title = {Text {Mining} in {Organizational} {Research}},
	volume = {21},
	issn = {1094-4281, 1552-7425},
	url = {http://journals.sagepub.com/doi/10.1177/1094428117722619},
	doi = {10.1177/1094428117722619},
	abstract = {Despite the ubiquity of textual data, so far few researchers have applied text mining to answer organizational research questions. Text mining, which essentially entails a quantitative approach to the analysis of (usually) voluminous textual data, helps accelerate knowledge discovery by radically increasing the amount data that can be analyzed. This article aims to acquaint organizational researchers with the fundamental logic underpinning text mining, the analytical stages involved, and contemporary techniques that may be used to achieve different types of objectives. The specific analytical techniques reviewed are (a) dimensionality reduction, (b) distance and similarity computing, (c) clustering, (d) topic modeling, and (e) classification. We describe how text mining may extend contemporary organizational research by allowing the testing of existing or new research questions with data that are likely to be rich, contextualized, and ecologically valid. After an exploration of how evidence for the validity of text mining output may be generated, we conclude the article by illustrating the text mining process in a job analysis setting using a dataset composed of job vacancies.},
	language = {en},
	number = {3},
	urldate = {2019-09-16},
	journal = {Organizational Research Methods},
	author = {Kobayashi, Vladimer B. and Mol, Stefan T. and Berkers, Hannah A. and Kismihók, Gábor and Den Hartog, Deanne N.},
	month = jul,
	year = {2018},
	pages = {733--765},
	file = {Kobayashi et al. - 2018 - Text Mining in Organizational Research.pdf:C\:\\Users\\chris\\Zotero\\storage\\3NLIDHUY\\Kobayashi et al. - 2018 - Text Mining in Organizational Research.pdf:application/pdf}
}

@article{van_der_maaten_laurens_visualizing_2008,
	title = {Visualizing {Data} using t-{SNE}},
	journal = {Journal of Machine learning},
	author = {{Van der Maaten, Laurens} and Hinton, Geoffrey},
	year = {2008},
	pages = {2579--2605},
	file = {vandermaaten08a.pdf:C\:\\Users\\chris\\Zotero\\storage\\MPFL4CFZ\\vandermaaten08a.pdf:application/pdf}
}

@article{shirdastian_using_2019,
	title = {Using big data analytics to study brand authenticity sentiments: {The} case of {Starbucks} on {Twitter}},
	volume = {48},
	issn = {02684012},
	shorttitle = {Using big data analytics to study brand authenticity sentiments},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0268401217302657},
	doi = {10.1016/j.ijinfomgt.2017.09.007},
	language = {en},
	urldate = {2019-10-08},
	journal = {International Journal of Information Management},
	author = {Shirdastian, Hamid and Laroche, Michel and Richard, Marie-Odile},
	month = oct,
	year = {2019},
	pages = {291--307}
}

@article{plutchik_psychoevolutionary_1982,
	title = {A psychoevolutionary theory of emotions},
	volume = {21},
	issn = {0539-0184, 1461-7412},
	url = {http://journals.sagepub.com/doi/10.1177/053901882021004003},
	doi = {10.1177/053901882021004003},
	language = {en},
	number = {4-5},
	urldate = {2019-01-18},
	journal = {Social Science Information},
	author = {Plutchik, Robert},
	month = jul,
	year = {1982},
	pages = {529--553}
}

@article{blei_latent_2003,
	title = {Latent {Dirichlet} {Allocation}},
	volume = {3},
	issn = {1532-4435},
	url = {http://dl.acm.org/citation.cfm?id=944919.944937},
	journal = {J. Mach. Learn. Res.},
	author = {Blei, David M. and Ng, Andrew Y. and Jordan, Michael I.},
	month = mar,
	year = {2003},
	pages = {993--1022}
}

@article{gunter_sentiment_2014,
	title = {Sentiment {Analysis}: {A} {Market}-{Relevant} and {Reliable} {Measure} of {Public} {Feeling}?},
	volume = {56},
	issn = {1470-7853, 2515-2173},
	shorttitle = {Sentiment {Analysis}},
	url = {http://journals.sagepub.com/doi/10.2501/IJMR-2014-014},
	doi = {10.2501/IJMR-2014-014},
	abstract = {This paper critically examines emergent research with sentiment analysis tools to assess their current status and relevance to applied opinion and behaviour measurement. The rapid spread of online news and online chatter in blogs, micro-blogs and social media sites has created a potentially rich source of public opinion. Waves of public feeling are vented spontaneously on a wide range of issues on a minute-by-minute basis in the online world. These online discourses are continually being refreshed, and businesses and advertisers, governments and policy makers have woken up to the fact that this universe of self-perpetuating human sentiment could represent a valuable resource to guide political and business decisions. The massive size of this repository of emotional content renders manual analysis of it feasible only for tiny portions of its totality, and even then can be labour intensive. Computer scientists have however produced software tools that can apply linguistic rules to provide electronic readings of meanings and emotions. These tools are now being utilised by applied social science and market researchers to yield sentiment profiles from online discourses created within specific platforms that purport to represent reliable substitutes for more traditional, offline measures of public opinion. This paper considers what these tools have demonstrated so far and where caution in their application is still called for.},
	language = {en},
	number = {2},
	urldate = {2019-10-20},
	journal = {International Journal of Market Research},
	author = {Gunter, Barrie and Koteyko, Nelya and Atanasova, Dimitrinka},
	month = mar,
	year = {2014},
	pages = {231--247}
}

@article{abdaoui_feel:_2017,
	title = {{FEEL}: a {French} {Expanded} {Emotion} {Lexicon}},
	volume = {51},
	issn = {1574-020X, 1574-0218},
	shorttitle = {{FEEL}},
	url = {http://link.springer.com/10.1007/s10579-016-9364-5},
	doi = {10.1007/s10579-016-9364-5},
	language = {en},
	number = {3},
	urldate = {2019-10-21},
	journal = {Language Resources and Evaluation},
	author = {Abdaoui, Amine and Azé, Jérôme and Bringay, Sandra and Poncelet, Pascal},
	month = sep,
	year = {2017},
	pages = {833--855},
	file = {Version soumise:C\:\\Users\\chris\\Zotero\\storage\\TFEGCKHW\\Abdaoui et al. - 2017 - FEEL a French Expanded Emotion Lexicon.pdf:application/pdf}
}

@article{kralj_novak_sentiment_2015,
	title = {Sentiment of {Emojis}},
	volume = {10},
	issn = {1932-6203},
	url = {https://dx.plos.org/10.1371/journal.pone.0144296},
	doi = {10.1371/journal.pone.0144296},
	language = {en},
	number = {12},
	urldate = {2019-10-21},
	journal = {PLOS ONE},
	author = {Kralj Novak, Petra and Smailović, Jasmina and Sluban, Borut and Mozetič, Igor},
	editor = {Perc, Matjaz},
	month = dec,
	year = {2015},
	pages = {e0144296},
	file = {Texte intégral:C\:\\Users\\chris\\Zotero\\storage\\LKA5WBBN\\Kralj Novak et al. - 2015 - Sentiment of Emojis.pdf:application/pdf}
}

@article{may_design_2018,
	title = {The design of civic technology: factors that influence public participation and impact},
	volume = {61},
	issn = {0014-0139, 1366-5847},
	shorttitle = {The design of civic technology},
	url = {https://www.tandfonline.com/doi/full/10.1080/00140139.2017.1349939},
	doi = {10.1080/00140139.2017.1349939},
	language = {en},
	number = {2},
	urldate = {2019-11-07},
	journal = {Ergonomics},
	author = {May, Andrew and Ross, Tracy},
	month = feb,
	year = {2018},
	pages = {214--225},
	file = {Texte intégral:C\:\\Users\\chris\\Zotero\\storage\\BNBEYS5K\\May et Ross - 2018 - The design of civic technology factors that influ.pdf:application/pdf}
}

@article{meng_statistical_2018,
	title = {Statistical paradises and paradoxes in big data ({I}): {Law} of large populations, big data paradox, and the 2016 {US} presidential election},
	volume = {12},
	issn = {1932-6157},
	shorttitle = {Statistical paradises and paradoxes in big data ({I})},
	url = {https://projecteuclid.org/euclid.aoas/1532743473},
	doi = {10.1214/18-AOAS1161SF},
	language = {en},
	number = {2},
	urldate = {2019-11-07},
	journal = {The Annals of Applied Statistics},
	author = {Meng, Xiao-Li},
	month = jun,
	year = {2018},
	pages = {685--726}
}

@article{tausczik_psychological_2010,
	title = {The {Psychological} {Meaning} of {Words}: {LIWC} and {Computerized} {Text} {Analysis} {Methods}},
	volume = {29},
	issn = {0261-927X, 1552-6526},
	shorttitle = {The {Psychological} {Meaning} of {Words}},
	url = {http://journals.sagepub.com/doi/10.1177/0261927X09351676},
	doi = {10.1177/0261927X09351676},
	language = {en},
	number = {1},
	urldate = {2019-11-07},
	journal = {Journal of Language and Social Psychology},
	author = {Tausczik, Yla R. and Pennebaker, James W.},
	month = mar,
	year = {2010},
	pages = {24--54}
}

@inproceedings{nielsen_new_2011,
	series = {{CEUR} {Workshop} {Proceedings}},
	title = {A {New} {ANEW}: {Evaluation} of a {Word} {List} for {Sentiment} {Analysis} in {Microblogs}.},
	volume = {718},
	url = {http://dblp.uni-trier.de/db/conf/msm/msm2011.html#Nielsen11},
	booktitle = {\#{MSM}},
	publisher = {CEUR-WS.org},
	author = {Nielsen, Finn Årup},
	editor = {Rowe, Matthew and Stankovic, Milan and Dadzie, Aba-Sah and Hardey, Mariann},
	year = {2011},
	keywords = {dblp},
	pages = {93--98}
}

@inproceedings{ding_holistic_2008,
	address = {New York, NY, USA},
	series = {{WSDM} '08},
	title = {A {Holistic} {Lexicon}-based {Approach} to {Opinion} {Mining}},
	isbn = {978-1-59593-927-2},
	url = {http://doi.acm.org/10.1145/1341531.1341561},
	doi = {10.1145/1341531.1341561},
	booktitle = {Proceedings of the 2008 {International} {Conference} on {Web} {Search} and {Data} {Mining}},
	publisher = {ACM},
	author = {Ding, Xiaowen and Liu, Bing and Yu, Philip S.},
	year = {2008},
	note = {event-place: Palo Alto, California, USA},
	keywords = {context dependent opinions, opinion mining, sentiment analysis},
	pages = {231--240}
}

@article{ordenes_unveiling_2017,
	title = {Unveiling {What} {Is} {Written} in the {Stars}: {Analyzing} {Explicit}, {Implicit} and {Discourse} {Patterns} of {Sentiment} in {Social} {Media}},
	issn = {0093-5301, 1537-5277},
	shorttitle = {Unveiling {What} {Is} {Written} in the {Stars}},
	url = {https://academic.oup.com/jcr/article-lookup/doi/10.1093/jcr/ucw070},
	doi = {10.1093/jcr/ucw070},
	language = {en},
	urldate = {2019-01-15},
	journal = {Journal of Consumer Research},
	author = {Ordenes, Francisco Villarroel and Ludwig, Stephan and De Ruyter, Ko and Grewal, Dhruv and Wetzels, Martin},
	month = jan,
	year = {2017},
	pages = {ucw070}
}

@article{puschmann_turning_2018,
	title = {Turning {Words} {Into} {Consumer} {Preferences}: {How} {Sentiment} {Analysis} {Is} {Framed} in {Research} and the {News} {Media}},
	volume = {4},
	issn = {2056-3051, 2056-3051},
	shorttitle = {Turning {Words} {Into} {Consumer} {Preferences}},
	url = {http://journals.sagepub.com/doi/10.1177/2056305118797724},
	doi = {10.1177/2056305118797724},
	language = {en},
	number = {3},
	urldate = {2019-01-15},
	journal = {Social Media + Society},
	author = {Puschmann, Cornelius and Powell, Alison},
	month = jul,
	year = {2018},
	pages = {205630511879772}
}

@book{lebraty_crowdsourcing:_2015,
	address = {London},
	title = {Crowdsourcing: porté par la foule},
	isbn = {978-1-78405-008-5},
	shorttitle = {Crowdsourcing},
	abstract = {La 4eme de couv. indique : "Le crowdsourcing consiste pour une organisation à externaliser une ou plusieurs de ses activités, non pas auprès d'un fournisseur préalablement sélectionné, mais auprès de la foule des internautes. Cette nouvelle forme d'externalisation n'a cessé d'évoluer en s'amplifiant et en se diversifiant pour, par exemple, donner naissance au crowdfunding ou au crowdtesting. A la différence d'une externalisation classique, le crowdsourcing bénéficie de la synergie entre la foule et les technologies Internet, ce qui lui confère des potentialités immenses. Se fondant à la fois sur des approches théoriques en management et sur des exemples concrets, cet ouvrage présente en détail onze types distincts d'opérations de crowdsourcing. Il montre comment cette nouvelle externalisation peut être utilisée pour créer de la valeur et de nouvelles opportunités pour les entreprises. Pour en mesurer les effets, une analyse présente un modèle original qui lie types de valeur, types de foule, motivations et incitations. Les aspects critiques du crowdsourcing, son éthique et son avenir sont discutés avec notamment une ouverture sur les synergies potentiellement importantes entre crowdsourcing, impression 3D et monnaie virtuelle."},
	language = {French},
	publisher = {ISTE editions},
	author = {Lebraty, Jean Fabrice and Lobre-Lebraty, Katia},
	year = {2015}
}

@article{noji_disasters_2005,
	title = {Disasters: {Introduction} and {State} of the {Art}},
	volume = {27},
	issn = {1478-6729, 0193-936X},
	shorttitle = {Disasters},
	url = {http://academic.oup.com/epirev/article/27/1/3/520821/Disasters-Introduction-and-State-of-the-Art},
	doi = {10.1093/epirev/mxi007},
	language = {en},
	number = {1},
	urldate = {2020-04-10},
	journal = {Epidemiologic Reviews},
	author = {Noji, Eric K.},
	month = jul,
	year = {2005},
	pages = {3--8},
	file = {Noji - 2005 - Disasters Introduction and State of the Art.pdf:C\:\\Users\\chris\\Zotero\\storage\\MDNL9HN7\\Noji - 2005 - Disasters Introduction and State of the Art.pdf:application/pdf}
}

@article{nojavan_conceptual_2018,
	title = {Conceptual change of disaster management models: {A} thematic analysis},
	volume = {10},
	issn = {2072-845X, 1996-1421},
	shorttitle = {Conceptual change of disaster management models},
	url = {https://jamba.org.za/index.php/jamba/article/view/451},
	doi = {10.4102/jamba.v10i1.451},
	abstract = {Different models have been proposed for disaster management by researchers and agencies. Despite their efficiency in some locations, disasters are still a fundamental challenge in the way of sustainable development. The purpose of this research is developing a comprehensive conceptual model for disaster management using thematic analysis. In this regard, first, disaster management models are collected. In the next stage, the themes of each model are extracted and categorised in three phases. In the first phase that is descriptive coding, available elements in each model are extracted as code and the basic themes are recognised. Then, in the phase of interpretive coding, basic themes are classified in three categories that are called organising themes (i.e. hazard assessment, risk management and management actions). In the final phase, strategic management is selected as the global or overarching theme to integrate all the other themes. Based on thematic analysis, it can be concluded that disaster management has three main elements that are the three organising themes. Therefore, comprehensive model of disaster management should include these three elements and their sub-basic themes that is called the ideal or criterion type. Results showed that some scientists have looked at disaster management one dimensionally (one theme). Even in two-dimensional models, one dimension has advantage over the other one. While the proposed typology in this study showed that the comprehensive model should include all the three mentioned elements.},
	number = {1},
	urldate = {2020-04-10},
	journal = {Jàmbá: Journal of Disaster Risk Studies},
	author = {Nojavan, Mehdi and Salehi, Esmail and Omidvar, Babak},
	month = apr,
	year = {2018},
	file = {Texte intégral:C\:\\Users\\chris\\Zotero\\storage\\M66L852Z\\Nojavan et al. - 2018 - Conceptual change of disaster management models A.pdf:application/pdf}
}

@article{math_disaster_2015,
	title = {Disaster management: {Mental} health perspective},
	volume = {37},
	issn = {0253-7176},
	shorttitle = {Disaster management},
	url = {http://www.ijpm.info/text.asp?2015/37/3/261/162915},
	doi = {10.4103/0253-7176.162915},
	language = {en},
	number = {3},
	urldate = {2020-04-10},
	journal = {Indian Journal of Psychological Medicine},
	author = {Math, SureshBada and Nirmala, MariaChristine and Moirangthem, Sydney and Kumar, NaveenC},
	year = {2015},
	pages = {261}
}

@article{duval_analyse_2016-1,
	title = {L'analyse automatisée du ton médiatique : construction et utilisation de la version française du \textit{{Lexicoder} {Sentiment} {Dictionary}}},
	volume = {49},
	issn = {0008-4239, 1744-9324},
	shorttitle = {L'analyse automatisée du ton médiatique},
	url = {https://www.cambridge.org/core/product/identifier/S000842391600055X/type/journal_article},
	doi = {10.1017/S000842391600055X},
	abstract = {Résumé
            
              Cet article introduit un nouveau dictionnaire permettant l'analyse automatisée du ton des médias francophones, que nous avons appelé
              Lexicoder Sentiment Dictionnaire Français
              (
              LSDFr
              ) en référence au lexique anglophone de Young et Soroka (2012),
              Lexicoder Sentiment Dictionary
              (
              LSD
              ) à partir duquel le
              LSDFr
              a été construit. Une fois construit, nous comparons le
              LSDFr
              au seul autre dictionnaire francophone existant de ce genre,
              Linguistic Inquiry and Word Count
              (
              LIWC
              ). Nous testons ensuite la validité interne du
              LSDFr
              en le comparant avec un corpus de textes codés manuellement. Nous testons enfin la validité externe du
              LSDFr
              en mesurant jusqu'où le ton médiatique, calculé à l'aide de notre dictionnaire, prédit les intentions de vote des Québécois lors des quatre dernières campagnes électorales. En développant cet outil, notre objectif est de permettre à d'autres chercheurs d'effectuer des analyses médiatiques dans un corpus de textes comparables en français.
            
          , 
            Abstract
            
              This article introduces a new dictionary for the automated analysis of the tone of French media. We named it the
              French Lexicoder Sentiment Dictionary
              (
              LSDFr
              ) in reference to the English lexicon developed by Young and Soroka (2012), the
              Lexicoder Sentiment Dictionary
              (
              LSD
              ), from which the
              LSDFr
              was built. We compare the
              LSDFr
              to the only other French sentiment lexicon,
              Linguistic Inquiry and Word Count
              (
              LIWC
              ). First, we detail the construction of the dictionary. We then test the internal validity of the
              LSDFr
              comparing it with a corpus of manually coded texts. Finally, we test the external validity of
              LSDFr
              by measuring how the media tone, calculated using our dictionary, predicts voting intentions in the last four Quebec elections. Our goal is to enable other researchers to conduct media analyses with a comparable corpus of texts in French.},
	language = {en},
	number = {2},
	urldate = {2020-04-10},
	journal = {Canadian Journal of Political Science},
	author = {Duval, Dominic and Pétry, François},
	month = jun,
	year = {2016},
	pages = {197--220}
}

@misc{banda_juan_m_large-scale_2020,
	title = {A large-scale {COVID}-19 {Twitter} chatter dataset for open scientific research - an international collaboration},
	copyright = {Open Access},
	url = {https://zenodo.org/record/3757272},
	abstract = {{\textless}strong{\textgreater}Due to the relevance of the COVID-19 global pandemic, we are releasing our dataset of tweets acquired from the Twitter Stream related to COVID-19 chatter. Since our first release we have received additional data from our new collaborators, allowing this resource to grow to its current size. Dedicated data gathering started from March 11th yielding over 4 million tweets a day. We have added additional data provided by our new collaborators from January 27th to March 27th, to provide extra longitudinal coverage.{\textless}/strong{\textgreater} {\textless}strong{\textgreater}The data collected from the stream captures all languages, but the higher prevalence are: English, Spanish, and French. We release all tweets and retweets on the full\_dataset.tsv file (205,409,413 unique tweets), and a cleaned version with no retweets on the full\_dataset-clean.tsv file (44,726,568{\textless}/strong{\textgreater}{\textless}strong{\textgreater} unique tweets). There are several practical reasons for us to leave the retweets, tracing important tweets and their dissemination is one of them. For NLP tasks we provide the top 1000 frequent terms in frequent\_terms.csv, the top 1000 bigrams in frequent\_bigrams.csv, and the top 1000 trigrams in frequent\_trigrams.csv. Some general statistics per day are included for both datasets in the statistics-full\_dataset.tsv and statistics-full\_dataset-clean.tsv files. {\textless}/strong{\textgreater} {\textless}strong{\textgreater}More details can be found (and will be updated faster at: https://github.com/thepanacealab/covid19\_twitter) and our pre-print about the dataset (https://arxiv.org/abs/2004.03688) {\textless}/strong{\textgreater} {\textless}strong{\textgreater}As always, the tweets distributed here are only tweet identifiers (with date and time added) due to the terms and conditions of Twitter to re-distribute Twitter data ONLY for research purposes. The need to be hydrated to be used. {\textless}/strong{\textgreater}},
	language = {en},
	urldate = {2020-04-25},
	publisher = {Zenodo},
	author = {Banda, Juan M. and Tekumalla, Ramya and Wang, Guanyu and Yu, Jingyuan and Liu, Tuo and Ding, Yuning and Chowell, Gerardo},
	month = apr,
	year = {2020},
	doi = {10.5281/ZENODO.3757272},
	note = {type: dataset},
	keywords = {covid-19, covid19, nlp, social media, twitter}
}