@article{montoya_enlightenment_2021,
	title = {Enlightenment? {What} {Enlightenment}? {Reflections} on {Half} a {Million} {Books} ({British}, {French} and {Dutch} {Private} {Libraries}, 1665 – 1830)},
	volume = {54},
	doi = {10.1353/ecs.2021.0097},
	language = {en},
	number = {2},
	journal = {Eighteenth-Century Studies},
	author = {Montoya, Alicia C.},
	year = {2021},
	pages = {909--934},
}

@incollection{prescott_bibliographic_2013,
	address = {Piscatawy},
	title = {Bibliographic {Records} as {Humanities} {Big} {Data}},
	url = {https://doi.org/10.1109/BigData.2013.6691670},
	language = {en},
	booktitle = {2013 {IEEE} {International} {Conference} on {Big} {Data}},
	publisher = {NJ},
	author = {Prescott, Andrew},
	editor = {Hu, Xiaohua and Lin, Tsau Young and Raghavan, Vijay and Wah, Benjamin and Baeza-Yates, Ricardo and Fox, Geoffrey and Shahabi, Cyrus and Smith, Matthew and Yang, Qiang and Ghani, Rayid and Fan, Wei and Lempel, Ronny and Nambiar, Raghunath},
	year = {2013},
	pages = {55--58},
}

@book{prescott_big_2015,
	address = {Glasgow},
	title = {Big {Data} in the {Arts} and {Humanities}: {Some} {Arts} and {Humanities} {Research} {Council} {Projects}},
	language = {en},
	publisher = {University of Glasgow},
	author = {Prescott, Andrew},
	year = {2015},
}

@book{manning_introduction_2009,
	address = {Cambridge},
	title = {An {Introduction} to {Information} {Retrieval}},
	url = {https://nlp.stanford.edu/IR-book/pdf/irbookonlinereading.pdf},
	language = {en},
	publisher = {Cambridge University Press},
	author = {Manning, Christopher D. and Raghavan, Prabhakar and Schütze, Hinrich},
	year = {2009},
}

@article{edelstein_historical_2017,
	title = {Historical {Research} in a {Digital} {Age}: {Reflections} from the {Mapping} the {Republic} of {Letters} {Project}},
	volume = {122},
	url = {https://academic.oup.com/ahr/article/122/2/400/3096208},
	doi = {10.1093/ahr/122.2.400},
	language = {en},
	number = {2},
	journal = {American Historical Review},
	author = {Edelstein, Dan and Findlen, Paula and Ceserani, Giovanna and Winterer, Caroline and Coleman, Nicole},
	year = {2017},
	pages = {401--424},
}

@misc{dariah_bibliographical_data_working_group_analysis_2022,
	title = {An {Analysis} of the {Current} {Bibliographical} {Data} {Landscape} in the {Humanities}. {The} {Joint} {Bibliodata} {Agendas} of {Public} {Stakeholders}},
	url = {https://doi.org/10.5281/zenodo.6559857},
	language = {en},
	author = {{DARIAH Bibliographical Data Working Group}},
	year = {2022},
}

@misc{lindemann_zotero_nodate,
	title = {Zotero to {Wikidata} {Through} {Wikibase}: {A} {Workflow} for {Publication} {Metadata} {LOD}-ification {Using} {Free} {Software}},
	language = {en},
	author = {Lindemann, David and Klaes, Christiane},
}

@article{blei_latent_2003,
	title = {Latent {Dirichlet} {Allocation}},
	volume = {3},
	journal = {Journal of Machine Learning Research},
	author = {Blei, David M. and Ng, Andrew Y. and Jordan, Michael I.},
	year = {2003},
	pages = {993--1022},
}

@article{simpson_measurement_1949,
	title = {Measurement of {Diversity}},
	volume = {163},
	doi = {10.1038/163688a0},
	journal = {Nature},
	author = {Simpson, Edward H.},
	year = {1949},
	pages = {688},
}

@article{tweedie_how_1998,
	title = {How {Variable} {May} a {Constant} {Be}? {Measures} of {Lexical} {Richness} in {Perspective}},
	volume = {32},
	doi = {10.1023/A:1001749303137},
	language = {en},
	number = {5},
	journal = {Computers and the Humanities},
	author = {Tweedie, Fiona J. and Baayen, R.Harald},
	year = {1998},
	pages = {323--352},
}

@book{moretti_distant_2013,
	address = {London; New York},
	title = {Distant {Reading}},
	publisher = {Verso},
	author = {Moretti, Franco},
	year = {2013},
}

@book{yule_statistical_1944,
	address = {Cambridge},
	title = {The {Statistical} {Study} of {Literary} {Vocabulary}},
	language = {en},
	publisher = {Cambridge University Press},
	author = {Yule, George Udny},
	year = {1944},
}

@book{schiuma_big_2018,
	address = {Boca Raton, FL},
	title = {Big {Data} in the {Arts} and {Humanities}: {Theory} and {Practice}},
	language = {en},
	publisher = {Taylor and Francis},
	author = {Schiuma, Giovanni and Carlucci, Daniela},
	year = {2018},
}

@article{herdan_new_1955,
	title = {A {New} {Derivation} and {Interpretation} of {Yule}’s ’{Characteristic}’ {K}},
	volume = {6},
	doi = {10.1007/BF01587632},
	number = {4},
	journal = {Zeitschrift für angewandte Mathematik und Physik},
	author = {Herdan, Gustav},
	year = {1955},
	pages = {332--334},
}

@incollection{orosz_huspacy_2022,
	address = {Szeged},
	title = {{HuSpaCy}: {An} {Industrial}-{Strength} {Hungarian} {Natural} {Language} {Processing} {Toolkit}},
	url = {https://rgai.inf.u-szeged.hu/file/427},
	booktitle = {{XVIII}. {Magyar} {Számítógépes} {Nyelvészeti} {Konferencia}},
	publisher = {JATEPress},
	author = {Orosz, György and Szántó, Zsolt and Berkecz, Péter and Szabó, Gergő and Farkas, Richárd},
	editor = {Berend, Gábor and Gosztolya, Gábor and Vincze, Veronika},
	year = {2022},
	pages = {59--73},
}

@article{maas_uber_1972,
	title = {Über den {Zusammenhang} zwischen {Wortschatzumfang} und {Länge} eines {Textes}},
	volume = {2},
	language = {de},
	number = {8},
	journal = {Zeitschrift für Literaturwissenschaft und Linguistik},
	author = {Maas, Heinz Dieter},
	year = {1972},
	pages = {73--96},
}

@incollection{varlamis_visualizing_2011,
	address = {Piscatawy, NJ},
	title = {Visualizing {Bibliographic} {Databases} as {Graphs} and {Mining} {Potential} {Research} {Synergies}},
	url = {https://doi.org/10.1109/ASONAM.2011.52},
	language = {en},
	booktitle = {2011 {International} {Conference} on {Advances} in {Social} {Networks} {Analysis} and {Mining}},
	publisher = {The Institute of Electrical and Electronics Engineers},
	author = {Varlamis, Iraklis and Tsatsaronis, George},
	editor = {Bilof, Randall},
	year = {2011},
	pages = {53--60},
}

@misc{moreux_innovative_2016,
	title = {Innovative {Approaches} of {Historical} {Newspapers}: {Data} {Mining}, {Data} {Visualization}, {Semantic} {Enrichment}: {Facilitating} {Access} for various {Profiles} of {Users}},
	url = {https://hal-bnf.archives-ouvertes.fr/hal-01389455/document},
	language = {en},
	author = {Moreux, Jean-Philippe},
	month = aug,
	year = {2016},
	note = {IFLA News Media Section, Lexington, August 2016, At Lexington, USA 1–16},
}

@book{edmond_trouble_2021,
	address = {London},
	title = {The {Trouble} {With} {Big} {Data}: {How} {Datafication} {Displaces} {Cultural} {Practices}},
	url = {https://doi.org/10.5040/9781350239654},
	language = {en},
	publisher = {Bloomsbury Academic},
	editor = {Edmond, Jennifer and Horsley, Nicola and Lehmann, Jörg and Priddy, Mike},
	year = {2021},
}

@article{torruella_lexical_2013,
	title = {Lexical {Statistics} and {Tipological} {Structures}: {A} {Measure} of {Lexical} {Richness}},
	volume = {95},
	doi = {10.1016/j.sbspro.2013.10.668},
	language = {en},
	journal = {Procedia: Social and Behavioral Sciences},
	author = {Torruella, Joan and Capsada, Ramon},
	year = {2013},
	pages = {447--454},
}

@article{bradley_digital_2019,
	title = {Digital {Tools} in the {Humanities}: {Some} {Fundamental} {Provocations}?},
	volume = {34},
	doi = {10.1093/llc/fqy033},
	language = {en},
	number = {1},
	journal = {Digital Scholarship in the Humanities},
	author = {Bradley, John},
	year = {2019},
	pages = {13--20},
}

@misc{unsworth_scholarly_nodate,
	title = {Scholarly {Primitives}: {What} {Methods} {Do} {Huma}- nities {Researchers} {Have} in {Common}, and {How} {Might} {Our} {Tools} {Reflect} {This}?},
	url = {https://johnunsworth.name/Kings.5-00/primitives.html},
	language = {en},
	author = {Unsworth, John},
	note = {hozzáférés: 2021.12.15},
}

@article{bode_why_2020,
	title = {Why {You} {Can}’t {Model} {Away} {Bias}?},
	volume = {81},
	doi = {10.1215/00267929-7933102},
	language = {en},
	number = {1},
	journal = {Modern Language Quarterly},
	author = {Bode, Katherine},
	year = {2020},
	pages = {95--124},
}

@article{fenlon_tooling_2012,
	title = {Tooling the {Aggregator}’s {Workbench}: {Metadata} {Visualization} through {Statistical} {Text} {Analysis}},
	volume = {49},
	doi = {10.1002/meet.14504901161},
	language = {en},
	number = {1},
	journal = {Proceedings of the American Society for Information Science and Technology},
	author = {Fenlon, Katrina and Efron, Miles and Organisciak, Peter},
	year = {2012},
	pages = {1--10},
}

@incollection{labadi_tanit_2018,
	address = {Szeged},
	title = {{TANIT}: {Magyar} nyelvű szövegeket elemző eszköz összehasonlító digitális bölcsészeti feladatokhoz},
	url = {http://real.mtak.hu/86149/1/teljesB5-460-465.pdf},
	language = {hu},
	booktitle = {{XIV}. {Magyar} {Számítógépes} {Nyelvészeti} {Konferencia}},
	publisher = {JATEPress},
	author = {Labádi, Gergely and Farkas, Richárd and Nagy, Roland and Péter, Róbert},
	editor = {Vincze, Veronika},
	year = {2018},
	pages = {450--455},
}

@article{lahti_bibliographic_2019,
	title = {Bibliographic {Data} {Science} and the {History} of the {Book} (c. 1500–1800)},
	volume = {57},
	doi = {10.1080/01639374.2018.1543747},
	language = {en},
	number = {1},
	journal = {Cataloging \& Classification Quarterly},
	author = {Lahti, Leo and Marjanen, Jani and Roivainen, Hege and Tolonen, Mikko},
	year = {2019},
	pages = {5--23},
}

@misc{wang_covid-19_2020,
	title = {{COVID}-19 {Open} {Research} {Dataset} and {AVOBMAT} {Text} {Mining} {Tool}},
	url = {https://www.youtube.com/watch?v=GivUfb8KhZY},
	language = {en},
	author = {Wang, Lucy and Lo, Kyle and Péter, Róbert},
	year = {2020},
	note = {New York NLP Meet-up, 2020. ápr. 27.},
}

@book{agren_science_2011,
	address = {Strasbourg},
	title = {Science {Policy} {Briefing}: {Research} {Infrastructures} in the {Digital} {Humanities}},
	url = {https://www.esf.org/fileadmin/user_upload/esf/RI_DigitalHumanities_B42_20},
	language = {en},
	publisher = {European Science Foundation},
	author = {Ågren, Maria and Moulin, Claudine and Tadic, Marko and Nyhan, Julianne and Ciula, Arianna and Kelleher, Margaret and Mittler, Elmar and Bozzi, Andrea and Kuutma, Kristin},
	year = {2011},
}

@article{koolen_toward_2019,
	title = {Toward a {Model} for {Digital} {Tool} {Criticism}: {Reflection} as {Integrative} {Practice}},
	volume = {34},
	doi = {10.1093/llc/fqy048},
	language = {en},
	number = {2},
	journal = {Digital Scholarship in the Humanities},
	author = {Koolen, Marijn and van Gorp, Jasmijn and van Ossenbruggen, Jacco},
	year = {2019},
	pages = {368--385},
}

@inproceedings{hill_reconstructing_2019,
	address = {Copenhagen},
	title = {Reconstructing {Intellectual} {Networks}: {From} the {ESTC}’s {Bibliographic} {Metadata} to {Historical} {Material}},
	url = {https://ceur-ws.org/Vol-2364/19_paper.pdf},
	language = {en},
	booktitle = {Proceedings of the {Digital} {Humanities} in the {Nordic} {Countries}},
	publisher = {CEUR-WS.org},
	author = {Hill, Mark J. and Vaara, Ville and Säily, Tanja and Lahti, Leo and Tolonen, Mikko},
	year = {2019},
	pages = {201-- 219},
}

@incollection{towsey_book_2016,
	address = {Leiden},
	title = {Book {Use} and {Sociability} in {Lost} {Libraries} of the {Eighteenth} {Century}: {Towards} a {Union} {Catalogue}},
	url = {https://doi.org/10.1163/9789004311824_021},
	language = {en},
	booktitle = {Lost {Books}: {Reconstructing} the {Print} {World} of {Pre}-{Industrial} {Europe}},
	publisher = {Brill},
	author = {Towsey, Mark},
	editor = {Bruni, Flavis and Pettegree, Andrew},
	year = {2016},
	pages = {414-- 438},
}

@article{jursic_lemmagen_2010,
	title = {Lemmagen: {Multilingual} {Lemmatisation} with {Induced} {Ripple}-down {Rules}},
	volume = {16},
	language = {en},
	number = {9},
	journal = {Journal of Universal Computer Science},
	author = {Juršic, Matjaž and Mozetic, Igor and Erjavec, Tomaž and Lavrac, Nada},
	year = {2010},
	pages = {1190--1214},
}

@article{romanello_impresso_2020,
	title = {The {Impresso} {System} {Architecture} in a {Nutshell}},
	volume = {16},
	url = {https://pro.europeana.eu/page/issue-16-newspapers#the-impresso-system-architecture-in-a-nutshell},
	language = {en},
	journal = {Technical Report, EuropeanaTech Insights},
	author = {Romanello, Matteo and Ehrmann, Maud and Clematide, Simon and Guido, Daniele},
	year = {2020},
}

@book{jockers_macroanalysis_2013,
	address = {Champaign, IL},
	title = {Macroanalysis: {Digital} {Methods} and {Literary} {History}},
	language = {en},
	publisher = {University of Illinois Press},
	author = {Jockers, Matthew L.},
	year = {2013},
}

@article{covington_cutting_2010,
	title = {Cutting the {Gordian} {Knot}: the {Moving}-{Average} {Type}- {Token} {Ratio} ({MATTR})},
	volume = {17},
	doi = {10.1080/09296171003643098},
	language = {en},
	number = {2},
	journal = {Journal of Quantitative Linguistics},
	author = {Covington, Michael A. and McFall, Joe D.},
	year = {2010},
	pages = {94--100},
}

@article{tolonen_quantitative_2015,
	title = {A {Quantitative} {Study} of {History} in the {English} {Short}-{Title} {Catalogue} ({ESTC}), 1470-1800},
	volume = {25},
	doi = {10.18352/lq.10112},
	language = {en},
	number = {2},
	journal = {Liber Quarterly},
	author = {Tolonen, Mikko and Lahti, Leo and Ilomäki, Niko},
	year = {2015},
	pages = {87--116},
}

@incollection{scrivner_interactive_2017,
	address = {Bloomington},
	title = {Interactive {Text} {Mining} {Suite}: {Data} {Visualization} for {Literary} {Studies}},
	url = {http://ceur-ws.org/Vol-1786/scrivner.pdf},
	language = {en},
	booktitle = {Proceedings of the {Workshop} on {Corpora} in the {Digital} {Humanities}, 29–38},
	author = {Scrivner, Olga and Davis, Jefferson},
	editor = {Declerck, Thierry and Kübler, Sandra},
	year = {2017},
}

@incollection{kiraly_bemerkungen_2021,
	address = {Berlin},
	title = {Bemerkungen zu der {Qualitätsbewertung} von {MARC}-21-{Datensätzen}},
	url = {https://doi.org/10.1515/9783110691597-011},
	language = {de},
	booktitle = {Qualität in der {Inhaltserschließung}},
	publisher = {De Gruyter Saur},
	author = {Király, Péter and Ungváry, Rudolf},
	editor = {Franke-Maier, Michael and Kasprzik, Anna and Ledl, Andreas and Schürmann, Hans},
	year = {2021},
	note = {https://github.com/pkiraly},
	pages = {177--228},
}

@article{peter_digitalis_2015,
	title = {Digitális és módszertani fordulat a sajtókutatásban: {A} 17–18. századi magyar vonatkozású angol újságcikkek »távolságtartó olvasása«},
	volume = {29},
	url = {http://acta.bibl.u-szeged.hu/35222/},
	language = {hu},
	number = {1},
	journal = {Aetas},
	author = {Péter, Róbert},
	year = {2015},
	pages = {5--30},
}

@article{mccarthy_vocd_2007,
	title = {vocd: {A} {Theoretical} and {Empirical} {Evaluation}},
	volume = {24},
	doi = {10.1177/0265532207080767},
	language = {en},
	number = {4},
	journal = {Language Testing},
	author = {McCarthy, Philip M. and Jarvis, Scott},
	year = {2007},
	pages = {459--488},
}

@article{mccarthy_mtld_2010,
	title = {{MTLD}, vocd-{D}, and {HD}-{D}: {A} {Validation} {Study} of {Sophisticated} {Approaches} to {Lexical} {Diversity} {Assessment}},
	volume = {42},
	doi = {10.3758/BRM.42.2.381},
	language = {en},
	number = {2},
	journal = {Behaviour Research Methods},
	author = {McCarthy, Philip M. and Jarvis, Scott},
	year = {2010},
	pages = {381--392},
}

@article{robert_researching_2011,
	title = {Researching ({British} {Digital}) {Press} {Archives} with {New} {Quantitative} {Methods}},
	volume = {17},
	url = {https://www.jstor.org/stable/43487818},
	language = {en},
	number = {2},
	journal = {Hungarian Journal for English and American Studies},
	author = {Róbert, Péter},
	year = {2011},
	pages = {283--300},
}

@incollection{peter_avobmat_2020,
	address = {Szeged},
	title = {{AVOBMAT} : {A} {Digital} {Toolkit} for {Analysing} and {Visualizing} {Bibliographic} {Metadata} and {Texts}},
	url = {http://acta.bibl.u-szeged.hu/67682/},
	booktitle = {{XVI}. {Magyar} {Számítógépes} {Nyelvészeti} {Konferencia}},
	publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
	author = {Péter, Róbert and Szántó, Zsolt and Seres, József and Bilicki, Vilmos and Berend, Gábor},
	editor = {Berend, Gábor and Gosztolya, Gábor and Vincze, Veronika},
	year = {2020},
	pages = {43--55},
}

@article{cilibrasi_google_2007,
	title = {The {Google} {Similarity} {Distance}},
	volume = {19},
	url = {https://arxiv.org/pdf/cs/0412098v3.pdf},
	doi = {10.1109/TKDE.2007.48},
	language = {en},
	number = {3},
	journal = {IEEE Transactions on Knowledge and Data Engineering},
	author = {Cilibrasi, Rudi L. and Vitányi, Paul M.B.},
	year = {2007},
	pages = {370--383},
}

@book{graham_exploring_2016,
	address = {London},
	title = {Exploring {Big} {Historical} {Data}: the {Historian}’s {Macroscope}},
	url = {https://doi.org/10.1142/p981},
	language = {en},
	publisher = {Imperial College Press},
	author = {Graham, Shawn and Milligan, Ian and Weingart, Scott},
	year = {2016},
}

@incollection{burrows_charting_2020,
	address = {New York},
	title = {Charting {Cultural} {History} {Through} {Histo}- rical {Bibliometric} {Research}: {Methods}, {Concepts}, {Challenges}, {Results}},
	url = {https://doi.org/10.4324/9780429777028-9},
	language = {en},
	booktitle = {Routledge {International} {Handbook} of {Research} {Methods} in {Digital} {Humanities}},
	publisher = {Routledge},
	author = {Burrows, Simon and Nurmikko-Fuller, Terhi},
	editor = {Schuster, Kristen and Dunn, Stuart},
	year = {2020},
	pages = {109--124},
}

@book{burrows_french_2018,
	address = {London},
	title = {The {French} {Book} {Trade} in {Enlightenment} {Europe} {II} : {Enlightenment} {Bestsellers}},
	language = {en},
	publisher = {Bloomsbury Academic},
	author = {Burrows, Simon},
	year = {2018},
}

@incollection{janicke_visualization_2017,
	title = {On the {Visualization} of {Hierarchical} {Relations} and {Tree} {Structures} with {TagSpheres}},
	url = {https://doi.org/10.1007/978-3-319-64870-5_10},
	language = {en},
	booktitle = {Computer {Vision}, {Imaging} and {Computer} {Graphics} {Theory} and {Applications}, 199–219},
	publisher = {Cham Springer International Publishing},
	author = {Jänicke, Stefan and Scheuermann, Gerik},
	editor = {Braz, José and Magnenat-Thalmann, Nadia and Richard, Paul and Linsen, Lars and Telea, Alexandru and Battiato, Sebastiano and Imai, Francisco},
	year = {2017},
}

@incollection{blanke_dealing_2016,
	address = {Edinburgh},
	title = {Dealing {With} {Big} {Data}},
	url = {https://doi.org/10.1515/9781474409629-012},
	language = {en},
	booktitle = {Research {Methods} for {Reading} {Digital} {Data} in the {Digital} {Humanities}},
	publisher = {Edinburgh University Press},
	author = {Blanke, Tobias and Prescott, Andrew},
	editor = {Griffin, Gabriele and Hayler, Matt},
	year = {2016},
	pages = {184--205},
}

@misc{szanto_introducing_nodate,
	title = {Introducing the {AVOBMAT} ({Analysis} and {Visualization} of {Bibliographic} {Metadata} and {Texts}) {Multilingual} {Research} {Tool}},
	url = {https://www.virtualdariah2020.dariah.eu/posters/#lightbox-gallery-1/7/},
	language = {en},
	author = {Szántó, Zsolt and Seres, József and Bilicki, Vilmos and Bendicsek, Bendegúz M. and Berend, Gábor and Péter, Róbert},
	note = {DA- RIAH: Virtual Annual Event 2020. Poster Exhibition, hozzáférés: 2021.12.15},
}