{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T11:45:09Z","timestamp":1777895109499,"version":"3.51.4"},"reference-count":75,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Johannes Kepler University Linz"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Scientometrics"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Subject classification is essential for navigating scientific literature, yet the influential All Science Journal Classification (ASJC) has limited practical applicability. Its limitations stem from reliance on an incomplete source list restricted to Scopus content, and from journal-level classifications that often misrepresent individual documents. The most significant recent development in ASJC-based classification is OpenAlex, but it narrows the framework by reducing the number of categories and enforcing single-label assignments\u2014both of which diminish classification accuracy. In response, this study introduces the first open, multi-label, implementation of the ASJC taxonomy that more accurately classifies individual documents, including those published in general science or interdisciplinary journals. We develop a fine-tuned SciBERT model for multi-label classification across 307 ASJC subjects, trained on a large-scale Crossref dataset using title, abstract, and source title metadata. The model achieves a weighted F1-score of 0.892 on 307 subjects and 0.934 on its 26 parent subjects on a Crossref test set with full metadata. It maintains respectable performance-0.532 and 0.694, respectively\u2014even without the source title information that ASJC classification relies upon. Our fine-tuning strategy includes selective metadata omission to mitigate overfitting and data augmentation for underrepresented categories. In addition, we introduce a tailored label-averaging method that enables assessment of the disciplinary orientation and comparison of individual documents and larger collections\u2014such as researcher portfolios, institutions, and entire databases. To promote transparency, reproducibility, and further research, we openly release our model via Hugging Face\u00a0(\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/huggingface.co\/asjc-classification\" ext-link-type=\"uri\">https:\/\/huggingface.co\/asjc-classification<\/jats:ext-link>\n                    ), providing ready-to-use ASJC-based subject classification.\n                  <\/jats:p>","DOI":"10.1007\/s11192-025-05490-0","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T06:23:47Z","timestamp":1764570227000},"page":"2401-2438","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Fine-tuning SciBERT to enable ASJC-based assessments of the disciplinary orientation of research collections"],"prefix":"10.1007","volume":"131","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7768-2351","authenticated-orcid":false,"given":"Michael","family":"Gusenbauer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jochen","family":"Endermann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harald","family":"Huber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Strasser","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas-Nizar","family":"Granitzer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Str\u00f6hle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"issue":"6","key":"5490_CR1","doi-asserted-by":"publisher","first-page":"3493","DOI":"10.1007\/s11192-024-05030-2","volume":"129","author":"JM \u00c1lvarez-Llorente","year":"2024","unstructured":"\u00c1lvarez-Llorente, J. M., Guerrero-Bote, V. P., & de Moya-Aneg\u00f3n, F. (2024). New fractional classifications of papers based on two generations of references and on the ASJC Scopus scheme. Scientometrics, 129(6), 3493\u20133515. https:\/\/doi.org\/10.1007\/s11192-024-05030-2","journal-title":"Scientometrics"},{"issue":"2","key":"5490_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.joi.2025.101647","volume":"19","author":"JM \u00c1lvarez-Llorente","year":"2025","unstructured":"\u00c1lvarez-Llorente, J. M., Guerrero-Bote, V. P., & Moya-Aneg\u00f3n, F. (2025). New paper-by-paper classification for Scopus based on references reclassified by the origin of the papers citing them. Journal of Informetrics, 19(2), Article 101647. https:\/\/doi.org\/10.1016\/j.joi.2025.101647","journal-title":"Journal of Informetrics"},{"issue":"1","key":"5490_CR3","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s11192-024-05217-7","volume":"130","author":"C Arhiliuc","year":"2025","unstructured":"Arhiliuc, C., Guns, R., Daelemans, W., & Engels, T. C. E. (2025). Journal article classification using abstracts: A comparison of classical and transformer-based machine learning methods. Scientometrics, 130(1), 313\u2013342. https:\/\/doi.org\/10.1007\/s11192-024-05217-7","journal-title":"Scientometrics"},{"key":"5490_CR4","unstructured":"Beltagy, I., Lo, K., & Cohan, A. (2019a). Scibert: A pretrained language model for scientific text. In EMNLP. Association for Computational Linguistics. https:\/\/www.aclweb.org\/anthology\/D19-1371"},{"key":"5490_CR5","unstructured":"Beltagy, I., Lo, K., & Cohan, A. (2019b). Scibert: A pretrained language model for scientific text. EMNLP. http:\/\/arxiv.org\/pdf\/1903.10676"},{"issue":"1","key":"5490_CR6","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1007\/s11192-018-2855-y","volume":"117","author":"L Bornmann","year":"2018","unstructured":"Bornmann, L. (2018). Field classification of publications in dimensions: A first case study testing its reliability and validity. Scientometrics, 117(1), 637\u2013640. https:\/\/doi.org\/10.1007\/s11192-018-2855-y","journal-title":"Scientometrics"},{"key":"5490_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1742-5581-3-1","volume":"3","author":"JF Burnham","year":"2006","unstructured":"Burnham, J. F. (2006). Scopus database: A review. Biomedical Digital Libraries, 3, 1. https:\/\/doi.org\/10.1186\/1742-5581-3-1","journal-title":"Biomedical Digital Libraries"},{"key":"5490_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/asi.24979","author":"L C\u00e9spedes","year":"2025","unstructured":"C\u00e9spedes, L., Kozlowski, D., Pradier, C., Sainte-Marie, M. H., Shokida, N. S., Benz, P., Poitras, C., Ninkov, A. B., Ebrahimy, S., Ayeni, P., Filali, S., Li, B., & Larivi\u00e8re, V. (2025). Evaluating the linguistic coverage of OpenAlex: An assessment of metadata accuracy and completeness. Journal of the Association for Information Science and Technology. https:\/\/doi.org\/10.1002\/asi.24979","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"5490_CR9","doi-asserted-by":"crossref","unstructured":"Chae, Y., & Davidson, T. (2023). Large language models for text classification: From zero-shot learning to fine-tuning. Open Science Foundation 10.","DOI":"10.31235\/osf.io\/sthwk"},{"key":"5490_CR10","doi-asserted-by":"publisher","unstructured":"Crossref. (2023). April 2023 public data file from crossref. https:\/\/doi.org\/10.13003\/8wx5k","DOI":"10.13003\/8wx5k"},{"issue":"1","key":"5490_CR11","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1162\/qss_a_00286","volume":"5","author":"L Delgado-Quir\u00f3s","year":"2024","unstructured":"Delgado-Quir\u00f3s, L., & Ortega, J. L. (2024). Completeness degree of publication metadata in eight free-access scholarly databases. Quantitative Science Studies, 5(1), 31\u201349. https:\/\/doi.org\/10.1162\/qss_a_00286","journal-title":"Quantitative Science Studies"},{"key":"5490_CR12","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: Human language technologies (Vol. 1, Long and Short Papers, pp. 4171\u20134186).","DOI":"10.18653\/v1\/N19-1423"},{"key":"5490_CR13","unstructured":"Elsevier Developer Portal. (2025). Search request. https:\/\/dev.elsevier.com\/tecdoc_search_request.html"},{"key":"5490_CR14","unstructured":"Elsevier. (2024). What are scopus subject area categories and asjc codes? https:\/\/service.elsevier.com\/app\/answers\/detail\/a_id\/12007\/supporthub\/scopus\/"},{"key":"5490_CR15","unstructured":"Elsevier. (2025a). Scopus content. https:\/\/www.elsevier.com\/products\/scopus\/content#4-titles-on-scopus"},{"key":"5490_CR16","unstructured":"Elsevier. (2025b). The impact rankings, scopus and scival."},{"issue":"1","key":"5490_CR17","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1162\/qss_a_00106","volume":"2","author":"J Eykens","year":"2021","unstructured":"Eykens, J., Guns, R., & Engels, T. C. E. (2021). Fine-grained classification of social science journal articles using textual data: A comparison of supervised machine learning approaches. Quantitative Science Studies, 2(1), 89\u2013110. https:\/\/doi.org\/10.1162\/qss_a_00106","journal-title":"Quantitative Science Studies"},{"key":"5490_CR18","unstructured":"Fan, A., Bhosale, S., Schwenk, H., Ma, Z., El-Kishky, A., Goyal, S.,Baines, M., Celebi, O., Wenzek, G., Chaudhary, V., Goyal, N., Birch, T., Liptchinsky, V., Edunov, S., Grave, E., Auli, M., & Joulin, A. (2020). Beyond english-centric multilingual machine translation. arXiv:2010.11125"},{"key":"5490_CR19","unstructured":"Feldner, D. (2025). Scopus data crosses the 100 million item threshold! https:\/\/blog.scopus.com\/topics\/scopus-csab"},{"issue":"4","key":"5490_CR20","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1016\/j.joi.2016.07.003","volume":"10","author":"F Franceschini","year":"2016","unstructured":"Franceschini, F., Maisano, D., & Mastrogiacomo, L. (2016). Empirical analysis and classification of database errors in scopus and web of science. Journal of Informetrics, 10(4), 933\u2013953. https:\/\/doi.org\/10.1016\/j.joi.2016.07.003","journal-title":"Journal of Informetrics"},{"issue":"3","key":"5490_CR21","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/BF02458488","volume":"44","author":"W Gl\u00e4nzel","year":"1999","unstructured":"Gl\u00e4nzel, W., Schubert, A., & Czerwon, H. (1999). An item-by-item subject classification of papers published in multidisciplinary and general journals using reference analysis. Scientometrics, 44(3), 427\u2013439.","journal-title":"Scientometrics"},{"key":"5490_CR22","doi-asserted-by":"publisher","unstructured":"Glazkova, A. (2021). Identifying topics of scientific articles with bert-based approaches and topic modeling. In Gupta, M., & Ramakrishnan, G. (Eds.), Trends and Applications in Knowledge Discovery and Data Mining, Lecture Notes in Artificial Intelligence (Vol. 12705, pp. 98\u2013105). Springer. https:\/\/doi.org\/10.1007\/978-3-030-75015-2_10","DOI":"10.1007\/978-3-030-75015-2_10"},{"key":"5490_CR23","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez-M\u00e1rquez, R., Schmidt, L., Schmidt, B. M., Berens, P., & Kobak, D. (2023). The landscape of biomedical research. bioRxiv","DOI":"10.1101\/2023.04.10.536208"},{"issue":"6","key":"5490_CR24","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1002\/jrsm.1520","volume":"12","author":"M Gusenbauer","year":"2021","unstructured":"Gusenbauer, M. (2021). The age of abundant scholarly information and its synthesis\u2014A time when \u2018just google it\u2019 is no longer enough. Research Synthesis Methods, 12(6), 684\u2013691. https:\/\/doi.org\/10.1002\/jrsm.1520","journal-title":"Research Synthesis Methods"},{"key":"5490_CR25","doi-asserted-by":"publisher","first-page":"2683","DOI":"10.1007\/s11192-022-04289-7","volume":"127","author":"M Gusenbauer","year":"2022","unstructured":"Gusenbauer, M. (2022). Search where you will find most: Comparing the disciplinary coverage of 56 bibliographic databases. Scientometrics, 127, 2683\u20132745. https:\/\/doi.org\/10.1007\/s11192-022-04289-7","journal-title":"Scientometrics"},{"issue":"6","key":"5490_CR26","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1002\/jrsm.1746","volume":"15","author":"M Gusenbauer","year":"2024","unstructured":"Gusenbauer, M. (2024). Searchsmart.org: Guiding researchers to the best databases and search systems for systematic reviews and beyond. Research Synthesis Methods, 15(6), 1200\u20131213. https:\/\/doi.org\/10.1002\/jrsm.1746","journal-title":"Research Synthesis Methods"},{"issue":"1","key":"5490_CR27","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s11192-019-03114-y","volume":"120","author":"AW Harzing","year":"2019","unstructured":"Harzing, A. W. (2019). Two new kids on the block: How do crossref and dimensions compare with google scholar, microsoft academic, scopus and the web of science? Scientometrics, 120(1), 341\u2013349.","journal-title":"Scientometrics"},{"key":"5490_CR28","unstructured":"He, P., Gao, J., & Chen, W. (2021a). Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv:2111.09543"},{"key":"5490_CR29","unstructured":"He, P., Liu, X., Gao, J., & Chen, W. (2021b). Deberta: Decoding-enhanced bert with disentangled attention. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=XPZIaotutsD"},{"issue":"1","key":"5490_CR30","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1007\/s11192-018-2854-z","volume":"117","author":"C Herzog","year":"2018","unstructured":"Herzog, C., & Lunn, B. K. (2018). Response to the letter \u2019field classification of publications in dimensions: A first case study testing its reliability and validity. Scientometrics, 117(1), 641\u2013645. https:\/\/doi.org\/10.1007\/s11192-018-2854-z","journal-title":"Scientometrics"},{"key":"5490_CR31","doi-asserted-by":"publisher","unstructured":"Ho, C. W. C., Weber, T., Fritze, T., & Risse, T. (2024). Towards multilingual llm-based approaches for automatic dewey decimal classification. In Antonacopoulos, A., Hinze, A., Piwowarski, B., et\u00a0al. (Eds.), Linking Theory and Practice of Digital Libraries, Lecture Notes in Computer Science (Vol. 15178, pp.\u00a023\u201333). Springer. https:\/\/doi.org\/10.1007\/978-3-031-72440-4_3","DOI":"10.1007\/978-3-031-72440-4_3"},{"issue":"4","key":"5490_CR32","doi-asserted-by":"publisher","first-page":"984","DOI":"10.1002\/asi.23734","volume":"68","author":"R Klavans","year":"2017","unstructured":"Klavans, R., & Boyack, K. W. (2017). Which type of citation analysis generates the most accurate taxonomy of scientific and technical knowledge? Journal of the Association for Information Science and Technology, 68(4), 984\u2013998. https:\/\/doi.org\/10.1002\/asi.23734","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"5490_CR33","unstructured":"Koroteev, M. V. (2021). Bert: A review of applications in natural language processing and understanding. arXiv preprint arXiv:2103.11943"},{"issue":"7","key":"5490_CR34","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"},{"issue":"3","key":"5490_CR35","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1002\/asi.23408","volume":"67","author":"L Leydesdorff","year":"2016","unstructured":"Leydesdorff, L., & Bornmann, L. (2016). The operationalization of \u201cfields\u2019\u2019 as wos subject categories (wcs) in evaluative bibliometrics: The cases of \u201clibrary and information science\u2019\u2019 and \u201cscience & technology studies\u2019\u2019. Journal of the Association for Information Science and Technology, 67(3), 707\u2013714. https:\/\/doi.org\/10.1002\/asi.23408","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"5490_CR36","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.aiopen.2022.03.001","volume":"3","author":"B Li","year":"2022","unstructured":"Li, B., Hou, Y., & Che, W. (2022). Data augmentation approaches in natural language processing: A survey. AI Open, 3, 71\u201390.","journal-title":"Ai Open"},{"key":"5490_CR37","unstructured":"Likhareva, D., Sankaran, H., & Thiyagarajan, S. (2024). Empowering interdisciplinary research with bert-based models: An approach through scibert-cnn with topic modeling. http:\/\/arxiv.org\/pdf\/2404.13078v2"},{"key":"5490_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2021.121023","volume":"172","author":"W Liu","year":"2021","unstructured":"Liu, W. (2021). Caveats for the use of web of science core collection in old literature retrieval and historical bibliometric analysis. Technological Forecasting and Social Change, 172, Article 121023. https:\/\/doi.org\/10.1016\/j.techfore.2021.121023","journal-title":"Technological Forecasting and Social Change"},{"key":"5490_CR39","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. http:\/\/arxiv.org\/pdf\/1711.05101"},{"issue":"1","key":"5490_CR40","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1007\/s11192-020-03690-4","volume":"126","author":"A Mart\u00edn-Mart\u00edn","year":"2021","unstructured":"Mart\u00edn-Mart\u00edn, A., Thelwall, M., Orduna-Malea, E., & Delgado L\u00f3pez-C\u00f3zar, E. (2021). Google scholar, microsoft academic, scopus, dimensions, web of science, and opencitations\u2019 coci: A multidisciplinary comparison of coverage via citations. Scientometrics, 126(1), 871\u2013906. https:\/\/doi.org\/10.1007\/s11192-020-03690-4","journal-title":"Scientometrics"},{"issue":"1","key":"5490_CR41","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1162\/qss_a_00014","volume":"1","author":"S Milojevi\u0107","year":"2020","unstructured":"Milojevi\u0107, S. (2020). Practical method to reclassify web of science articles into unique subject categories and broad disciplines. Quantitative Science Studies, 1(1), 183\u2013206. https:\/\/doi.org\/10.1162\/qss_a_00014","journal-title":"Quantitative Science Studies"},{"key":"5490_CR42","doi-asserted-by":"publisher","unstructured":"Newman, D., Noh, Y., Talley, E., Karimi, S., & Baldwin, T. (2010). Evaluating topic models for digital libraries. In Proceedings of the 10th annual joint conference on Digital libraries. ACM, New York, NY, USA, pp. 215\u2013224. https:\/\/doi.org\/10.1145\/1816123.1816156","DOI":"10.1145\/1816123.1816156"},{"issue":"3","key":"5490_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jik.2024.100516","volume":"9","author":"AY Noaman","year":"2024","unstructured":"Noaman, A. Y., Gad-Elrab, A. A., & Baabdullah, A. M. (2024). Towards scientists and researchers classification model (srcm)-based machine learning and data mining methods: An ism-micmac approach. Journal of Innovation & Knowledge, 9(3), Article 100516. https:\/\/doi.org\/10.1016\/j.jik.2024.100516","journal-title":"Journal of Innovation & Knowledge"},{"key":"5490_CR44","unstructured":"NobelPrize.org (2025). All nobel prizes. https:\/\/www.nobelprize.org\/prizes\/lists\/all-nobel-prizes\/all\/"},{"key":"5490_CR45","volume-title":"Towards scientists and researchers classification model (srcm)-based machine learning and data mining methods: An ism-micmac approach","author":"OECD","year":"2007","unstructured":"OECD. (2007). Towards scientists and researchers classification model (srcm)-based machine learning and data mining methods: An ism-micmac approach. OECD."},{"issue":"1","key":"5490_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e23781","volume":"10","author":"D Ofer","year":"2024","unstructured":"Ofer, D., Kaufman, H., & Linial, M. (2024). What\u2019s next? Forecasting scientific research trends. Heliyon, 10(1), Article e23781. https:\/\/doi.org\/10.1016\/j.heliyon.2023.e23781","journal-title":"Heliyon"},{"key":"5490_CR47","doi-asserted-by":"crossref","unstructured":"Okamura, K. (2024). Evolving interdisciplinary contributions to global societal challenges: A 50-year overview. http:\/\/arxiv.org\/pdf\/2410.20619v1","DOI":"10.1016\/j.wdp.2025.100728"},{"key":"5490_CR48","unstructured":"OpenAlex, (2025b). SMEs development and digital marketing (t13053). https:\/\/openalex.org\/topics\/t13053"},{"key":"5490_CR49","unstructured":"OpenAlex, O. (2024). End-to-end process for topic classification.  https:\/\/docs.google.com\/document\/d\/1bDopkhuGieQ4F8gGNj7sEc8WSE8mvLZS\/"},{"key":"5490_CR50","unstructured":"OpenAlex. (2025a). About. https:\/\/openalex.org\/about"},{"issue":"2","key":"5490_CR51","doi-asserted-by":"publisher","first-page":"420","DOI":"10.3145\/epi.2018.mar.21","volume":"27","author":"E Ordu\u00f1a-Malea","year":"2018","unstructured":"Ordu\u00f1a-Malea, E., & Delgado-L\u00f3pez-C\u00f3zar, E. (2018). Dimensions: Re-discovering the ecosystem of scientific information. El Profesional de la Informaci\u00f3n, 27(2), 420. https:\/\/doi.org\/10.3145\/epi.2018.mar.21","journal-title":"El Profesional de la Informaci\u00f3n"},{"key":"5490_CR52","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., K\u00f6pf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., & Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library. http:\/\/arxiv.org\/pdf\/1912.01703"},{"key":"5490_CR53","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., & Duchesnay, \u00c9. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825\u20132830.","journal-title":"Journal of Machine Learning Research"},{"key":"5490_CR54","doi-asserted-by":"crossref","unstructured":"Polischuk, P. (2024). Subject codes, incomplete and unreliable, have got to go. https:\/\/www.crossref.org\/blog\/subject-codes-incomplete-and-unreliable-have-got-to-go\/","DOI":"10.64000\/35zxh-sgw46"},{"key":"5490_CR55","unstructured":"QS World University Rankings. (2025). Qs world university rankings by subject. https:\/\/support.qs.com\/hc\/en-gb\/articles\/4410488025106-QS-World-University-Rankings-by-Subject"},{"key":"5490_CR56","doi-asserted-by":"crossref","unstructured":"Rong, G., Chen, Y., Ma, F., & Koch, T. (2025). 40 years of interdisciplinary research: Phases, origins, and key turning points (1981-2020). http:\/\/arxiv.org\/pdf\/2501.05001v1","DOI":"10.2139\/ssrn.5085453"},{"key":"5490_CR57","doi-asserted-by":"publisher","first-page":"567","DOI":"10.48366\/R732033","volume":"6","author":"AA Salatino","year":"2024","unstructured":"Salatino, A. A., Aggarwal, T., Mannocci, A., Osborne, F., & Motta, E. (2024). A survey on knowledge organization systems of research fields: Resources and challenges. Quantitative Science Studies, 6, 567\u2013610. https:\/\/doi.org\/10.48366\/R732033","journal-title":"Quantitative Science Studies"},{"key":"5490_CR58","doi-asserted-by":"publisher","unstructured":"Shen, Z., Ma, H., & Wang, K. (2018). A web-scale system for scientific knowledge exploration. In Liu, F., & Solorio, T. (Eds,). Proceedings of ACL 2018, System Demonstrations. Association for Computational Linguistics (pp. 87\u201392). https:\/\/doi.org\/10.18653\/V1\/P18-4015","DOI":"10.18653\/V1\/P18-4015"},{"key":"5490_CR59","unstructured":"Shokraneh, F. (2025). Using ai in automation of evidence synthesis: What does research tell us? https:\/\/www.youtube.com\/watch?v=4ZM3MZibP0c&t=2383s"},{"issue":"2","key":"5490_CR60","doi-asserted-by":"publisher","first-page":"123","DOI":"10.5860\/lrts.49n2.123","volume":"49","author":"J Shorten","year":"2005","unstructured":"Shorten, J., Seikel, M., & Ahrberg, J. H. (2005). Why do you still use dewey? Library Resources & Technical Services, 49(2), 123\u2013136. https:\/\/doi.org\/10.5860\/lrts.49n2.123","journal-title":"Library Resources & Technical Services"},{"issue":"1","key":"5490_CR61","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. Journal of Informetrics, 13(1), 202\u2013225. https:\/\/doi.org\/10.1016\/j.joi.2018.12.005","journal-title":"Journal of Informetrics"},{"key":"5490_CR62","unstructured":"Singh, A. (2023). Specter2: Adapting scientific document embeddings to multiple fields and task formats. https:\/\/allenai.org\/blog\/specter2-adapting-scientific-document-embeddings-to-multiple-fields-and-task-formats-c95686c06567"},{"key":"5490_CR63","doi-asserted-by":"publisher","DOI":"10.1093\/wentk\/9780190640118.001.0001","volume-title":"Measuring research: What everyone needs to know. What everyone needs to know\u00ae ser","author":"CR Sugimoto","year":"2018","unstructured":"Sugimoto, C. R. (2018). Measuring research: What everyone needs to know. What everyone needs to know\u00ae ser. Oxford University Press."},{"issue":"6","key":"5490_CR64","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1093\/scipol\/scv007","volume":"42","author":"CR Sugimoto","year":"2015","unstructured":"Sugimoto, C. R., Ni, C. Q., & Larivi\u00e8re, V. (2015). On the relationship between gender disparities in scholarly communication and country-level development indicators. Science and Public Policy, 42(6), 789\u2013810. https:\/\/doi.org\/10.1093\/scipol\/scv007","journal-title":"Science and Public Policy"},{"key":"5490_CR65","doi-asserted-by":"crossref","unstructured":"Thelwall, M., & Jiang, X. (2025). Is openalex suitable for research quality evaluation and which citation indicator is best? arXiv preprint arXiv:2502.18427","DOI":"10.1002\/asi.70020"},{"issue":"2","key":"5490_CR66","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1007\/s11192-023-04901-4","volume":"129","author":"M Thelwall","year":"2024","unstructured":"Thelwall, M., & Pinfield, S. (2024). The accuracy of field classifications for journals in scopus. Scientometrics, 129(2), 1097\u20131117. https:\/\/doi.org\/10.1007\/s11192-023-04901-4","journal-title":"Scientometrics"},{"key":"5490_CR67","volume-title":"Impact rankings methodology 2025","author":"Times Higher Education","year":"2025","unstructured":"Times Higher Education. (2025). Impact rankings methodology 2025. Times Higher Education."},{"key":"5490_CR68","unstructured":"van Rossum, G. (2010). The Python language reference, Documentation for Python (Vol Pt. 2, Release 3.0.1 [Repr.] Ed.). Python Software Foundation and SoHo Books"},{"issue":"1","key":"5490_CR69","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1162\/qss_a_00112","volume":"2","author":"M Visser","year":"2021","unstructured":"Visser, M., van Eck, N. J., & Waltman, L. (2021). Large-scale comparison of bibliographic data sources: Scopus, web of science, dimensions, crossref, and microsoft academic. Quantitative Science Studies, 2(1), 20\u201341. https:\/\/doi.org\/10.1162\/qss_a_00112","journal-title":"Quantitative Science Studies"},{"issue":"12","key":"5490_CR70","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1002\/asi.22748","volume":"63","author":"L Waltman","year":"2012","unstructured":"Waltman, L., & van Eck, N. J. (2012). A new methodology for constructing a publication-level classification system of science. Journal of the American Society for Information Science and Technology, 63(12), 2378\u20132392. https:\/\/doi.org\/10.1002\/asi.22748","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"2","key":"5490_CR71","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. Journal of Informetrics, 10(2), 347\u2013364. https:\/\/doi.org\/10.1016\/j.joi.2016.02.003","journal-title":"Journal of Informetrics"},{"key":"5490_CR72","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., & Rush, A. M. (2020). Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 conference on empirical methods in natural language processing: System demonstrations (pp. 38\u201345).","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"5490_CR73","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., von Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Le Scao, T., Gugger, S., & Rush, A. M. (2019). Huggingface\u2019s transformers: State-of-the-art natural language processing. http:\/\/arxiv.org\/pdf\/1910.03771","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"5490_CR74","doi-asserted-by":"publisher","DOI":"10.1002\/asi.70004","author":"M Wu","year":"2025","unstructured":"Wu, M., Sivertsen, G., Zhang, L., Qi, F., & Zhang, Y. (2025). Scaling research aim identification: Language models for classifying scientific and societal-oriented studies. Journal of the Association for Information Science and Technology. https:\/\/doi.org\/10.1002\/asi.70004","journal-title":"Journal of the Association for Information Science and Technology"},{"issue":"1","key":"5490_CR75","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"F Zhuang","year":"2020","unstructured":"Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2020). A comprehensive survey on transfer learning. Proceedings of the IEEE, 109(1), 43\u201376.","journal-title":"Proceedings of the IEEE"}],"container-title":["Scientometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-025-05490-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11192-025-05490-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-025-05490-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T06:57:08Z","timestamp":1777100228000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11192-025-05490-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":75,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["5490"],"URL":"https:\/\/doi.org\/10.1007\/s11192-025-05490-0","relation":{},"ISSN":["0138-9130","1588-2861"],"issn-type":[{"value":"0138-9130","type":"print"},{"value":"1588-2861","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]},"assertion":[{"value":"28 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2025","order":3,"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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}