{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T11:46:19Z","timestamp":1788435979654,"version":"build-2803163510"},"reference-count":27,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T00:00:00Z","timestamp":1630195200000},"content-version":"vor","delay-in-days":240,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1016\/j.procs.2021.08.122","type":"journal-article","created":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T23:17:37Z","timestamp":1633130257000},"page":"1190-1197","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"special_numbering":"C","title":["Estimating the Number of Latent Topics Through a Combination of Methods"],"prefix":"10.1016","volume":"192","author":[{"given":"Asana","family":"Neishabouri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michel C.","family":"Desmarais","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.procs.2021.08.122_bib0001","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1080\/02522667.2019.1616911","article-title":"Deep lda: A new way to topic model","volume":"41","author":"Bhat","year":"2020","journal-title":"Journal of Information and Optimization Sciences"},{"key":"10.1016\/j.procs.2021.08.122_bib0002","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1145\/1667053.1667056","article-title":"The nested chinese restaurant process and bayesian nonparametric inference of topic hierarchies","volume":"57","author":"Blei","year":"2010","journal-title":"Journal of the ACM (JACM)"},{"key":"10.1016\/j.procs.2021.08.122_bib0003","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"Journal of machine Learning research"},{"key":"10.1016\/j.procs.2021.08.122_bib0004","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1146\/annurev.psych.53.100901.135239","article-title":"Latent variables in psychology and the social sciences","volume":"53","author":"Bollen","year":"2002","journal-title":"Annual review of psychology"},{"key":"10.1016\/j.procs.2021.08.122_bib0005","doi-asserted-by":"crossref","unstructured":"Chen, Q., Yao, L., Yang, J., 2016. Short text classification based on lda topic model, in: 2016 International Conference on Audio, Language and Image Processing (ICALIP), IEEE. pp. 749\u2013753.","DOI":"10.1109\/ICALIP.2016.7846525"},{"key":"10.1016\/j.procs.2021.08.122_bib0006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v025.i05","article-title":"Text mining infrastructure in r","volume":"25","author":"Feinerer","year":"2008","journal-title":"Journal of Statistical Software"},{"key":"10.1016\/j.procs.2021.08.122_bib0007","first-page":"17","article-title":"Hierarchical topic models and the nested chinese restaurant process","author":"Griffiths","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.procs.2021.08.122_bib0008","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/BF02289162","article-title":"Some necessary conditions for common-factor analysis","volume":"19","author":"Guttman","year":"1954","journal-title":"Psychometrika"},{"key":"10.1016\/j.procs.2021.08.122_bib0009","doi-asserted-by":"crossref","unstructured":"Henderson, K., Eliassi-Rad, T., 2009. Applying latent dirichlet allocation to group discovery in large graphs, in: Proceedings of the 2009 ACM symposium on Applied Computing, ACM. pp. 1456\u20131461.","DOI":"10.1145\/1529282.1529607"},{"key":"10.1016\/j.procs.2021.08.122_bib00010","doi-asserted-by":"crossref","unstructured":"Hira, Z.M., Gillies, D.F., 2015. A review of feature selection and feature extraction methods applied on microarray data. Advances in bioinformatics 2015.","DOI":"10.1155\/2015\/198363"},{"key":"10.1016\/j.procs.2021.08.122_bib00011","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/BF02289447","article-title":"A rationale and test for the number of factors in factor analysis","volume":"30","author":"Horn","year":"1965","journal-title":"Psychometrika"},{"key":"10.1016\/j.procs.2021.08.122_bib00012","doi-asserted-by":"crossref","unstructured":"Kang, J.H., Ma, J., Liu, Y., 2012. Transfer topic modeling with ease and scalability, in: Proceedings of the 2012 SIAM International Conference on Data Mining, SIAM. pp. 564\u2013575.","DOI":"10.1137\/1.9781611972825.49"},{"key":"10.1016\/j.procs.2021.08.122_bib00013","first-page":"1980","article-title":"The doubly correlated nonparametric topic model","volume":"24","author":"Kim","year":"2011","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.procs.2021.08.122_bib00014","doi-asserted-by":"crossref","first-page":"394","DOI":"10.3390\/e22040394","article-title":"Analyzing the influence of hyper-parameters and regularizers of topic modeling in terms of renyi entropy","volume":"22","author":"Koltcov","year":"2020","journal-title":"Entropy"},{"key":"10.1016\/j.procs.2021.08.122_bib00015","unstructured":"Mao, X.L., Ming, Z.Y., Chua, T.S., Li, S., Yan, H., Li, X., 2012. Sshlda: a semi-supervised hierarchical topic model, in: Proceedings of the 2012 joint conference on empirical methods in natural language processing and computational natural language learning, Association for Computational Linguistics. pp. 800\u2013809."},{"key":"10.1016\/j.procs.2021.08.122_bib00016","doi-asserted-by":"crossref","unstructured":"Mimno, D., Li, W., McCallum, A., 2007. Mixtures of hierarchical topics with pachinko allocation, in: Proceedings of the 24th international conference on Machine learning, ACM. pp. 633\u2013640.","DOI":"10.1145\/1273496.1273576"},{"key":"10.1016\/j.procs.2021.08.122_bib00017","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/BF02293559","article-title":"Latent roots of random data correlation matrices with squared multiple correlations on the diagonal: A monte carlo study","volume":"41","author":"Montanelli","year":"1976","journal-title":"Psychometrika"},{"key":"10.1016\/j.procs.2021.08.122_bib00018","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1046\/j.1365-2141.2003.04624.x","article-title":"Factor v i359t: a novel mutation associated with thrombosis and resistance to activated protein c","volume":"123","author":"Mumford","year":"2003","journal-title":"British journal of haematology"},{"key":"10.1016\/j.procs.2021.08.122_bib00019","unstructured":"Neishabouri, A., Desmarais, M.C., 2019. Investigating methods to estimate the number of latent dimensions under different assumptions and data characteristics. Technical Report."},{"key":"10.1016\/j.procs.2021.08.122_bib00020","unstructured":"Neishabouri, A., Desmarais, M.C., 2020. Reliability of perplexity to find number of latent topics, in: The Thirty-Third International Flairs Conference."},{"key":"10.1016\/j.procs.2021.08.122_bib00021","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1109\/TPAMI.2014.2318728","article-title":"Nested hierarchical dirichlet processes","volume":"37","author":"Paisley","year":"2014","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.procs.2021.08.122_bib00022","doi-asserted-by":"crossref","unstructured":"Phan, X.H., Nguyen, L.M., Horiguchi, S., 2008. Learning to classify short and sparse text & web with hidden topics from large-scale data collections, in: Proceedings of the 17th international conference on World Wide Web, pp. 91\u2013100.","DOI":"10.1145\/1367497.1367510"},{"key":"10.1016\/j.procs.2021.08.122_bib00023","series-title":"Textstem: Tools for stemming and lemmatizing text","author":"Rinker","year":"2018"},{"key":"10.1016\/j.procs.2021.08.122_bib00024","doi-asserted-by":"crossref","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, pp. 8138\u20138150.","DOI":"10.18653\/v1\/2020.acl-main.724"},{"key":"10.1016\/j.procs.2021.08.122_bib00025","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1016\/j.tourman.2019.06.011","article-title":"Discovering implicit activity preferences in travel itineraries by topic modeling","volume":"75","author":"Vu","year":"2019","journal-title":"Tourism Management"},{"key":"10.1016\/j.procs.2021.08.122_bib00026","first-page":"1973","article-title":"Rethinking lda: Why priors matter","author":"Wallach","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.procs.2021.08.122_bib00027","unstructured":"Wang, C., Paisley, J., Blei, D., 2011. Online variational inference for the hierarchical dirichlet process, in: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, JMLR Workshop and Conference Proceedings. pp. 752\u2013760."}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050921016112?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050921016112?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T01:44:26Z","timestamp":1761788666000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050921016112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":27,"alternative-id":["S1877050921016112"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2021.08.122","relation":{},"ISSN":["1877-0509"],"issn-type":[{"value":"1877-0509","type":"print"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Estimating the Number of Latent Topics Through a Combination of Methods","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2021.08.122","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}