{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T14:49:17Z","timestamp":1771166957095,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100008441","name":"CYTED Ciencia y Tecnolog\u00eda para el Desarrollo","doi-asserted-by":"publisher","award":["519RT0579"],"award-info":[{"award-number":["519RT0579"]}],"id":[{"id":"10.13039\/501100008441","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s10115-023-02023-0","type":"journal-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:02:11Z","timestamp":1702494131000},"page":"1503-1520","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Text-based paper-level classification procedure for non-traditional sciences using a machine learning approach"],"prefix":"10.1007","volume":"66","author":[{"given":"Daniela","family":"Moctezuma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"L\u00f3pez-V\u00e1zquez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucas","family":"Lopes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norton","family":"Trevisan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9","family":"P\u00e9rez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,13]]},"reference":[{"issue":"1","key":"2023_CR1","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/j.joi.2018.12.005","volume":"13","author":"F Shu","year":"2019","unstructured":"Shu F, Julien C-A, Zhang L, Qiu J, Zhang J, Larivi\u00e8re V (2019) Comparing journal and paper level classifications of science. J Inform 13(1):202\u2013225","journal-title":"J Inform"},{"issue":"12","key":"2023_CR2","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1002\/asi.22748","volume":"63","author":"L Waltman","year":"2012","unstructured":"Waltman L, van Eck NJ (2012) A new methodology for constructing a publication-level classification system of science. J Am Soc Inf Sci Technol 63(12):2378\u20132392","journal-title":"J Am Soc Inf Sci Technol"},{"key":"2023_CR3","unstructured":"Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: International conference on machine learning. PMLR, pp. 1188\u20131196"},{"key":"2023_CR4","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"2023_CR5","first-page":"1","volume":"128","author":"G Chen","year":"2022","unstructured":"Chen G, Chen J, Shao Y, Xiao L (2022) Automatic noise reduction of domain-specific bibliographic datasets using positive-unlabeled learning. Scientometrics 128:1\u201318","journal-title":"Scientometrics"},{"issue":"3","key":"2023_CR6","doi-asserted-by":"publisher","first-page":"2915","DOI":"10.1007\/s11192-020-03409-5","volume":"125","author":"CK Kreutz","year":"2020","unstructured":"Kreutz CK, Sahitaj P, Schenkel R (2020) Evaluating semantometrics from computer science publications. Scientometrics 125(3):2915\u20132954","journal-title":"Scientometrics"},{"issue":"7","key":"2023_CR7","doi-asserted-by":"publisher","first-page":"5881","DOI":"10.1007\/s11192-021-03984-1","volume":"126","author":"D Kozlowski","year":"2021","unstructured":"Kozlowski D, Dusdal J, Pang J, Zilian A (2021) Semantic and relational spaces in science of science: deep learning models for article vectorisation. Scientometrics 126(7):5881\u20135910","journal-title":"Scientometrics"},{"key":"2023_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11192-021-04216-2","volume":"127","author":"AH Roudsari","year":"2022","unstructured":"Roudsari AH, Afshar J, Lee W, Lee S (2022) PatentNet: multi-label classification of patent documents using deep learning based language understanding. Scientometrics 127:1\u201325","journal-title":"Scientometrics"},{"key":"2023_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11192-022-04380-z","volume":"127","author":"H Chen","year":"2022","unstructured":"Chen H, Nguyen H, Alghamdi A (2022) Constructing a high-quality dataset for automated creation of summaries of fundamental contributions of research articles. Scientometrics 127:1\u201315","journal-title":"Scientometrics"},{"issue":"2","key":"2023_CR10","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.joi.2016.02.003","volume":"10","author":"Q Wang","year":"2016","unstructured":"Wang Q, Waltman L (2016) Large-scale analysis of the accuracy of the journal classification systems of web of science and Scopus. J Informet 10(2):347\u2013364","journal-title":"J Informet"},{"issue":"8","key":"2023_CR11","doi-asserted-by":"publisher","first-page":"4847","DOI":"10.1007\/s11192-022-04419-1","volume":"127","author":"Y Lv","year":"2022","unstructured":"Lv Y, Xie Z, Zuo X, Song Y (2022) A multi-view method of scientific paper classification via heterogeneous graph embeddings. Scientometrics 127(8):4847\u20134872","journal-title":"Scientometrics"},{"key":"2023_CR12","first-page":"1","volume":"128","author":"S Shen","year":"2022","unstructured":"Shen S, Liu J, Lin L, Huang Y, Zhang L, Liu C, Feng Y, Wang D (2022) SsciBERT: a pre-trained language model for social science texts. Scientometrics 128:1\u201323","journal-title":"Scientometrics"},{"issue":"1","key":"2023_CR13","doi-asserted-by":"publisher","first-page":"20","DOI":"10.14512\/tatup.12.1.20","volume":"12","author":"AV Raan","year":"2003","unstructured":"Raan AV (2003) The use of bibliometric analysis in research performance assessment and monitoring of interdisciplinary scientific developments. TATuP-Z Technikfolgenabsch\u00e4tzung Theorie Praxis 12(1):20\u201329","journal-title":"TATuP-Z Technikfolgenabsch\u00e4tzung Theorie Praxis"},{"key":"2023_CR14","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1126\/science.149.3683.510","volume":"149","author":"DJ de Solla Price","year":"1965","unstructured":"de Solla Price DJ (1965) Networks of scientific papers. Science 149:510\u2013515","journal-title":"Science"},{"issue":"3","key":"2023_CR15","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1002\/asi.4630240406","volume":"24","author":"H Small","year":"1973","unstructured":"Small H (1973) Co-citation in the scientific literature: a new measure of the relationship between two documents. J Am Soc Inf Sci 24(3):265\u2013269","journal-title":"J Am Soc Inf Sci"},{"key":"2023_CR16","first-page":"984","volume":"68","author":"R Klavans","year":"2017","unstructured":"Klavans R, Boyack K (2017) Which type of citation analysis generates the most accurate taxonomy of scientific and technical knowledge? J Am Soc Inf Sci 68:984\u2013998","journal-title":"J Am Soc Inf Sci"},{"key":"2023_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/asi.24655","volume":"73","author":"G Pech","year":"2022","unstructured":"Pech G, Delgado C, Sorella SP (2022) Classifying papers into subfields using abstracts, titles, keywords and keywords plus through pattern detection and optimization procedures: an application in physics. J Assoc Inf Sci Technol 73:1\u201316","journal-title":"J Assoc Inf Sci Technol"},{"issue":"3","key":"2023_CR18","first-page":"707","volume":"67","author":"L Leydesdorff","year":"2016","unstructured":"Leydesdorff L, Bornmann L (2016) The operationalization of \u201cfields\u2019\u2019 as WoS subject categories (WC s) in evaluative bibliometrics: the cases of \u201clibrary and information science\u2019\u2019 and \u201cscience & technology studies\u2019\u2019. J Am Soc Inf Sci 67(3):707\u2013714","journal-title":"J Am Soc Inf Sci"},{"issue":"3","key":"2023_CR19","doi-asserted-by":"publisher","first-page":"18029","DOI":"10.1371\/journal.pone.0018029","volume":"6","author":"KW Boyack","year":"2011","unstructured":"Boyack KW, Newman D, Duhon RJ, Klavans R, Patek M, Biberstine JR, Schijvenaars B, Skupin A, Ma N, B\u00f6rner K (2011) Clustering more than two million biomedical publications: comparing the accuracies of nine text-based similarity approaches. PLoS ONE 6(3):18029","journal-title":"PLoS ONE"},{"issue":"11","key":"2023_CR20","doi-asserted-by":"publisher","first-page":"6581","DOI":"10.1007\/s11192-022-04282-0","volume":"127","author":"S Wang","year":"2022","unstructured":"Wang S, Mao J, Cao Y, Li G (2022) Integrated knowledge content in an interdisciplinary field: identification, classification, and application. Scientometrics 127(11):6581\u20136614","journal-title":"Scientometrics"},{"key":"2023_CR21","unstructured":"Liu B, Lee WS, Yu PS, Li X (2002) Partially supervised classification of text documents. In: International conference on machine learning, ICML. Sydney, NSW, vol 2, pp 387\u2013394"},{"key":"2023_CR22","unstructured":"Priem J, Piwowar H, Orr R (2022) Openalex: A fully-open index of scholarly works, authors, venues, institutions, and concepts. arXiv preprint arXiv:2205.01833"},{"key":"2023_CR23","doi-asserted-by":"publisher","first-page":"178","DOI":"10.3103\/S0005105521040075","volume":"55","author":"IV Selivanova","year":"2021","unstructured":"Selivanova IV, Kosyakov DV, Dubovitskii DA, Guskov AE (2021) Expert, journal, and automatic classification of full texts and annotations of scientific articles. Autom Doc Math Linguist 55:178\u2013189","journal-title":"Autom Doc Math Linguist"},{"key":"2023_CR24","doi-asserted-by":"crossref","unstructured":"Muller M, Wolf C, Andres J, Desmond M, Joshi NN, Ashktorab Z, Sharma A, Brimijoin K, Pan Q, Duesterwald E (2021) Designing ground truth and the social life of labels. In: Proceedings of ACM human factors in computing systems (CHI\u201921), Article No 94, pp 1\u201316","DOI":"10.1145\/3411764.3445402"},{"issue":"1","key":"2023_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41651-021-00098-3","volume":"6","author":"W Huang","year":"2022","unstructured":"Huang W (2022) What were GIScience scholars interested in during the past decades? J Geovis Spat Anal 6(1):1\u201321","journal-title":"J Geovis Spat Anal"},{"key":"2023_CR26","doi-asserted-by":"publisher","first-page":"19926","DOI":"10.1109\/ACCESS.2022.3150869","volume":"10","author":"C L\u00f3pez-V\u00e1zquez","year":"2022","unstructured":"L\u00f3pez-V\u00e1zquez C, Gonzalez-Campos ME, Bernab\u00e9-Poveda MA, Moctezuma D, Hochsztain E, Barrera MA, Granell-Canut C, Le\u00f3n-Pazmi\u00f1o MF, L\u00f3pez-Ram\u00edrez P, Morocho-Zurita V et al (2022) Building a gold standard dataset to identify articles about geographic information science. IEEE Access 10:19926\u201319936","journal-title":"IEEE Access"},{"key":"2023_CR27","unstructured":"Clark S, Pulman S (2007) Combining symbolic and distributional models of meaning. Retrieved from https:\/\/www.aaai.org\/Papers\/Symposia\/Spring\/2007\/SS-07-08\/SS07-08-008.pdf"},{"key":"2023_CR28","doi-asserted-by":"crossref","unstructured":"Bender EM, Koller A (2020) Climbing towards NLU: on meaning, form, and understanding in the age of data. In: Proceedings of the 58th annual meeting of the association for computational linguistics (ACL2020). ACL, pp 5185\u20135198","DOI":"10.18653\/v1\/2020.acl-main.463"},{"key":"2023_CR29","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781"},{"key":"2023_CR30","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, vol 30"},{"key":"2023_CR31","unstructured":"Gonz\u00e1lez-Carvajal, S, Garrido-Merch\u00e1n EC (2020) Comparing BERT against traditional machine learning text classification. arXiv preprint arXiv:2005.13012"},{"key":"2023_CR32","doi-asserted-by":"crossref","unstructured":"Rodrigues J, Gomes L, Silva J, Branco A, Santos R, Cardoso HL, Os\u00f3rio T (2023) Advancing neural encoding of Portuguese with transformer Albertina PT","DOI":"10.1007\/978-3-031-49008-8_35"},{"key":"2023_CR33","unstructured":"Ca\u00f1ete J, Chaperon G, Fuentes R, Ho J-H, Kang H, P\u00e9rez J (2020) Spanish pre-trained BERT model and evaluation data. In: PML4DC at ICLR 2020"},{"key":"2023_CR34","unstructured":"Akhtar Z (2020) BERT base vs BERT large. https:\/\/iq.opengenus.org\/bert-base-vs-bert-large\/. Accessed on 10 Nov 2022"},{"key":"2023_CR35","unstructured":"Briggs J (2021) BERT For next sentence prediction. https:\/\/towardsdatascience.com\/bert-for-next-sentence-prediction-466b67f8226f. Accessed on 10 Nov 2022"},{"key":"2023_CR36","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1080\/13658816.2022.2119476","volume":"37","author":"X Wu","year":"2022","unstructured":"Wu X, Dong W, Wu L, Liu Y (2022) Research themes of geographical information science during 1991\u20132020: a retrospective bibliometric analysis. Int J Geogr Inf Sci 37:243","journal-title":"Int J Geogr Inf Sci"},{"key":"2023_CR37","doi-asserted-by":"crossref","unstructured":"Wiebe J, Bruce R, O\u2019Hara TP (1999) Development and use of a gold-standard data set for subjectivity classifications. In: Proceedings of the 37th annual meeting of the association for computational linguistics, pp 246\u2013253","DOI":"10.3115\/1034678.1034721"},{"key":"2023_CR38","doi-asserted-by":"crossref","unstructured":"McCulloh I, Burck J, Behling J, Burks M, Parker J (2018) Leadership of data annotation teams. In: 2018 International workshop on social sensing (SocialSens). IEEE, pp. 26\u201331","DOI":"10.1109\/SocialSens.2018.00018"},{"issue":"9","key":"2023_CR39","doi-asserted-by":"publisher","first-page":"e2021EA001896","DOI":"10.1029\/2021EA001896","volume":"8","author":"EB Goldstein","year":"2021","unstructured":"Goldstein EB, Buscombe D, Lazarus ED, Mohanty SD, Rafique SN, Anarde KA, Ashton AD, Beuzen T, Castagno KA, Cohn N et al (2021) Labeling poststorm coastal imagery for machine learning: measurement of interrater agreement. Earth Space Sci 8(9):e2021EA001896","journal-title":"Earth Space Sci"},{"key":"2023_CR40","unstructured":"Boesser CT (2020) Comparing human and machine learning classification of human factors in incident reports from aviation. PhD thesis, University of Central Florida"},{"key":"2023_CR41","unstructured":"Krippendorff K (2009) Testing the reliability of content analysis data. The content analysis reader, 350\u2013357"},{"issue":"2","key":"2023_CR42","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1080\/19312458.2011.568376","volume":"5","author":"K Krippendorff","year":"2011","unstructured":"Krippendorff K (2011) Agreement and information in the reliability of coding. Commun Methods Meas 5(2):93\u2013112","journal-title":"Commun Methods Meas"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-023-02023-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-023-02023-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-023-02023-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T14:13:32Z","timestamp":1705500812000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-023-02023-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["2023"],"URL":"https:\/\/doi.org\/10.1007\/s10115-023-02023-0","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,13]]},"assertion":[{"value":"21 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}