{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T13:30:07Z","timestamp":1747834207951,"version":"3.40.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T00:00:00Z","timestamp":1657497600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T00:00:00Z","timestamp":1657497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004901","name":"FAPEMIG","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004901","id-type":"DOI","asserted-by":"crossref"}]},{"name":"CNPQ"},{"DOI":"10.13039\/501100002322","name":"CAPES","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100008536","name":"Amazon Web Services","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008536","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Scientometrics"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s11192-022-04449-9","type":"journal-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T06:06:40Z","timestamp":1657606000000},"page":"5005-5026","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Semantic Academic Profiler (SAP): a framework for researcher assessment based on semantic topic modeling"],"prefix":"10.1007","volume":"127","author":[{"given":"Felipe","family":"Viegas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ant\u00f4nio","family":"Pereira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo","family":"Cec\u00edlio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elisa","family":"Tuler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"suffix":"Jr.","given":"Wagner","family":"Meira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos","family":"Gon\u00e7alves","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4913-4902","authenticated-orcid":false,"given":"Leonardo","family":"Rocha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,11]]},"reference":[{"key":"4449_CR1","doi-asserted-by":"publisher","unstructured":"Allahyari, M., & Kochut, K. (2016). Discovering coherent topics with entity topic models. In 2016 ACM International Conference on Web Intelligence (WI) (pp.\u00a026\u201333). https:\/\/doi.org\/10.1109\/WI.2016.0015","DOI":"10.1109\/WI.2016.0015"},{"issue":"6","key":"4449_CR2","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1080\/10447310802205776","volume":"24","author":"A Bangor","year":"2008","unstructured":"Bangor, A., Kortum, P. T., & Miller, J. T. (2008). An empirical evaluation of the system usability scale. International Journal of Human-Computer Interaction, 24(6), 574\u2013594. https:\/\/doi.org\/10.1080\/10447310802205776.","journal-title":"International Journal of Human-Computer Interaction"},{"key":"4449_CR3","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of Machine Learning Research, 3, 993\u20131022.","journal-title":"Journal of Machine Learning Research"},{"key":"4449_CR4","doi-asserted-by":"crossref","unstructured":"Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2016). Enriching word vectors with subword information. CoRR arXiv:1607.04606.","DOI":"10.1162\/tacl_a_00051"},{"key":"4449_CR5","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":"4449_CR33","doi-asserted-by":"publisher","unstructured":"de Alencar\u00a0Almeida, R. J., Serapilha\u00a0Durelli, V. H., Campos\u00a0Moraes, I., Carvalho\u00a0Viana, M., Carvalho\u00a0Fazzion, E., Barbosa Feres\u00a0Carvalho, D., Colombo\u00a0Dias, D. R., & Chaves Dutra\u00a0da Rocha, L. (2019). Combining data mining techniques for evolutionary analysis of programming languages. In 2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI) (pp. 1\u20138). https:\/\/doi.org\/10.1109\/IRI.2019.00015.","DOI":"10.1109\/IRI.2019.00015"},{"issue":"1","key":"4449_CR27","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/s00799-018-0260-z","volume":"21","author":"GO de Siqueira","year":"2020","unstructured":"de Siqueira, G. O., Canuto, S. D., Gon\u00e7alves, M. A., & Laender, A. H. F. (2020). A pragmatic approach to hierarchical categorization of research expertise in the presence of scarce information. International Journal on Digital Libraries, 21(1), 61\u201373. https:\/\/doi.org\/10.1007\/s00799-018-0260-z.","journal-title":"International Journal on Digital Libraries"},{"issue":"5","key":"4449_CR6","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1016\/j.is.2011.02.002","volume":"36","author":"F Figueiredo","year":"2011","unstructured":"Figueiredo, F., Rocha, L., Couto, T., Salles, T., Gon\u00e7alves, M. A., & Meira, W., Jr. (2011). Word co-occurrence features for text classification. Information Systems, 36(5), 843\u2013858.","journal-title":"Information Systems"},{"issue":"12","key":"4449_CR7","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1038\/s42256-019-0112-6","volume":"1","author":"M Gerlach","year":"2019","unstructured":"Gerlach, M., Shi, H., & Amaral, L. A. N. (2019). A universal information theoretic approach to the identification of stopwords. Nature Machine Intelligence, 1(12), 606\u2013612.","journal-title":"Nature Machine Intelligence"},{"key":"4449_CR8","doi-asserted-by":"publisher","unstructured":"Gudivada, V. N., & Arbabifard, K. (2018). Chapter 3\u2014Open-source libraries, application frameworks, and workflow systems for nlp. In: Gudivada, V. N., Rao, C. R. (Eds.), Computational analysis and understanding of natural languages: Principles, methods and applications. Handbook of statistics (Vol. 38, pp. 31\u201350). https:\/\/doi.org\/10.1016\/bs.host.2018.07.007. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0169716118300221.","DOI":"10.1016\/bs.host.2018.07.007"},{"issue":"1","key":"4449_CR9","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s11192-018-2958-5","volume":"118","author":"M Gusenbauer","year":"2019","unstructured":"Gusenbauer, M. (2019). Google scholar to overshadow them all? Comparing the sizes of 12 academic search engines and bibliographic databases. Scientometrics, 118(1), 177\u2013214.","journal-title":"Scientometrics"},{"key":"4449_CR10","doi-asserted-by":"crossref","unstructured":"Hofmann, T. (1999). Probabilistic latent semantic indexing. In ACM SIGIR Conference on Research and Development in Information Retrieval (pp.\u00a050\u201357).","DOI":"10.1145\/312624.312649"},{"issue":"1","key":"4449_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cjar.2019.09.002","volume":"13","author":"X Hu","year":"2020","unstructured":"Hu, X., Li, O. Z., & Pei, S. (2020). Of stars and galaxies\u2014Co-authorship network and research. China Journal of Accounting Research, 13(1), 1\u201330. https:\/\/doi.org\/10.1016\/j.cjar.2019.09.002.","journal-title":"China Journal of Accounting Research"},{"key":"4449_CR12","unstructured":"Huang, Q., Chen, Z., Lu, Z., & Ye, Y. (2018). Analysis of bag-of-n-grams representation\u2019s properties based on textual reconstruction. CoRR arXiv:1809.06502."},{"key":"4449_CR13","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1108\/OIR-06-2016-0166","volume":"41","author":"S-Y Hwang","year":"2017","unstructured":"Hwang, S.-Y., Wei, C.-P., Lee, C.-H., & Chen, Y.-S. (2017). Coauthorship network-based literature recommendation with topic model. Online Information Review, 41, 318\u2013336.","journal-title":"Online Information Review"},{"key":"4449_CR14","doi-asserted-by":"publisher","unstructured":"Jeong, Y.-S., Lee, S.-H., & Gweon, G. (2016) Discovery of research interests of authors over time using a topic model. In 2016 International Conference on Big Data and Smart Computing (BigComp) (pp.\u00a024\u201331). https:\/\/doi.org\/10.1109\/BIGCOMP.2016.7425797","DOI":"10.1109\/BIGCOMP.2016.7425797"},{"key":"4449_CR15","doi-asserted-by":"crossref","unstructured":"Kocaballi, A. B., Laranjo, L., & Coiera, E. (2018). Measuring user experience in conversational interfaces: A comparison of six questionnaires. In Proceedings of the 32nd International BCS Human Computer Interaction Conference, p. 21.","DOI":"10.14236\/ewic\/HCI2018.21"},{"key":"4449_CR16","doi-asserted-by":"publisher","unstructured":"Krasnov, F., Dimentov, A., & Shvartsman, M. (2019). Comparative Analysis of Scientific Papers Collections via Topic Modeling and Co-authorship Networks, pp. 77\u201398. https:\/\/doi.org\/10.1007\/978-3-030-34518-1_6.","DOI":"10.1007\/978-3-030-34518-1_6"},{"issue":"6755","key":"4449_CR17","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1038\/44565","volume":"401","author":"DD Lee","year":"1999","unstructured":"Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788\u2013791.","journal-title":"Nature"},{"key":"4449_CR18","doi-asserted-by":"crossref","unstructured":"Lin, C.-J. (2007). Projected gradient methods for nonnegative matrix factorization. Neural Comput.","DOI":"10.1162\/neco.2007.19.10.2756"},{"key":"4449_CR19","unstructured":"Mikolov, T., Grave, E., Bojanowski, P., Puhrsch, C., & Joulin, A. (2017). Advances in pre-training distributed word representations. CoRR arXiv:1712.09405."},{"key":"4449_CR20","unstructured":"Mikolov, T., Grave, E., Bojanowski, P., Puhrsch, C., & Joulin, A. (2018). Advances in pre-training distributed word representations. In LREC\u201918."},{"key":"4449_CR21","doi-asserted-by":"crossref","unstructured":"Nikolenko, S. I. (2016). Topic quality metrics based on distributed word representations. In: SIGIR\u201916","DOI":"10.1145\/2911451.2914720"},{"key":"4449_CR22","unstructured":"Nunes, D. A. P., de Matos, D. M., Ferreira-Gomes, J., & Neto, F. (2021). Chronic pain and language: A topic modelling approach to personal pain descriptions. CoRR arXiv:2109.00402."},{"key":"4449_CR23","unstructured":"Nunes, D., Matos, D., Gomes, J., & Neto, F. (2021). Chronic Pain and Language: A Topic Modelling Approach to Personal Pain Descriptions. arXiv:2109.00402 ."},{"key":"4449_CR24","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C. D. (2014). Glove: Global vectors for word representation. In EMNLP.","DOI":"10.3115\/v1\/D14-1162"},{"key":"4449_CR34","doi-asserted-by":"crossref","unstructured":"Pedro, A., Pereira, A., Cecilio, P., Pena, N., Viegas, F., Tuler, E., Dias, D., & Rocha, L. (2021). An article-oriented framework for automatic semantic analysis of covid-19 researches. In Computational Science and Its Applications\u2014ICCSA 2021 (pp. 172\u2013187). Springer, Cham.","DOI":"10.1007\/978-3-030-86970-0_13"},{"issue":"5","key":"4449_CR25","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton, G., & Buckley, C. (1988). Term-weighting approaches in automatic text retrieval. Information Processing and Management, 24(5), 513\u2013523. https:\/\/doi.org\/10.1016\/0306-4573(88)90021-0.","journal-title":"Information Processing and Management"},{"key":"4449_CR26","doi-asserted-by":"crossref","unstructured":"Shi, T., Kang, K., Choo, J., & Reddy, C. K. (2018). Short-text topic modeling via non-negative matrix factorization enriched with local word-context correlations. In WWW \u201918 (pp. 1105\u20131114).","DOI":"10.1145\/3178876.3186009"},{"issue":"1","key":"4449_CR28","doi-asserted-by":"publisher","first-page":"04","DOI":"10.1016\/j.ipm.2013.08.006","volume":"50","author":"AK Uysal","year":"2014","unstructured":"Uysal, A. K., & Gunal, S. (2014). The impact of preprocessing on text classification. Information Processing & Management, 50(1), 04\u2013112. https:\/\/doi.org\/10.1016\/j.ipm.2013.08.006.","journal-title":"Information Processing & Management"},{"key":"4449_CR29","doi-asserted-by":"publisher","unstructured":"Viegas, F., Cunha, W., Gomes, C., Pereira, A., Rocha, L., & Goncalves, M. (2020). CluHTM - semantic hierarchical topic modeling based on CluWords. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, (pp. 8138\u20138150). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.724.","DOI":"10.18653\/v1\/2020.acl-main.724"},{"key":"4449_CR30","doi-asserted-by":"crossref","unstructured":"Viegas, F., Canuto, S., Gomes, C., Luiz, W., Rosa, T., Ribas, S., Rocha, L., & Gon\u00e7alves, M. A. (2019). Cluwords: exploiting semantic word clustering representation for enhanced topic modeling, 753\u2013761.","DOI":"10.1145\/3289600.3291032"},{"key":"4449_CR31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3106003","author":"F Wu","year":"2021","unstructured":"Wu, F., Du, M., Fan, C., Tang, R., Yang, Y., Mostafavi, A., & Hu, X. (2021). Understanding social biases behind location names in contextual word embedding models. IEEE Transactions on Computational Social Systems. https:\/\/doi.org\/10.1109\/TCSS.2021.3106003.","journal-title":"IEEE Transactions on Computational Social Systems"},{"key":"4449_CR32","doi-asserted-by":"publisher","unstructured":"Xuan, J., Lu, J., Zhang, G., Yi\u00a0Da\u00a0Xu, R., & Luo, X. (2015). Infinite author topic model based on mixed gamma-negative binomial process. In 2015 IEEE International Conference on Data Mining (pp.\u00a0489\u2013498). https:\/\/doi.org\/10.1109\/ICDM.2015.19.","DOI":"10.1109\/ICDM.2015.19"}],"container-title":["Scientometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-022-04449-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11192-022-04449-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11192-022-04449-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T23:52:27Z","timestamp":1744156347000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11192-022-04449-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,11]]},"references-count":34,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["4449"],"URL":"https:\/\/doi.org\/10.1007\/s11192-022-04449-9","relation":{},"ISSN":["0138-9130","1588-2861"],"issn-type":[{"type":"print","value":"0138-9130"},{"type":"electronic","value":"1588-2861"}],"subject":[],"published":{"date-parts":[[2022,7,11]]},"assertion":[{"value":"2 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}