{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T10:52:38Z","timestamp":1770288758107,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,6,12]],"date-time":"2019-06-12T00:00:00Z","timestamp":1560297600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,6,12]],"date-time":"2019-06-12T00:00:00Z","timestamp":1560297600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002666","name":"Aalto University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002666","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Stat"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s00180-019-00891-1","type":"journal-article","created":{"date-parts":[[2019,6,12]],"date-time":"2019-06-12T09:04:36Z","timestamp":1560330276000},"page":"175-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["DOLDA: a regularized supervised topic model for high-dimensional multi-class regression"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0296-2719","authenticated-orcid":false,"given":"M\u00e5ns","family":"Magnusson","sequence":"first","affiliation":[]},{"given":"Leif","family":"Jonsson","sequence":"additional","affiliation":[]},{"given":"Mattias","family":"Villani","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,12]]},"reference":[{"key":"891_CR1","unstructured":"Ahmed A, Xing EP (2010) Staying informed: supervised and semi-supervised multi-view topical analysis of ideological perspective. In: Proceedings of the 2010 conference on empirical methods in natural language processing. Association for Computational Linguistics, pp 1140\u20131150"},{"issue":"422","key":"891_CR2","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1080\/01621459.1993.10476321","volume":"88","author":"JH Albert","year":"1993","unstructured":"Albert JH, Chib S (1993) Bayesian analysis of binary and polychotomous response data. J Am Stat Assoc 88(422):669\u2013679","journal-title":"J Am Stat Assoc"},{"key":"891_CR3","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"key":"891_CR4","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1093\/biomet\/asq017","volume":"97","author":"C Carvalho","year":"2010","unstructured":"Carvalho C, Polson N, Scott J (2010) The horseshoe estimator for sparse signals. Biometrika 97:465\u2013480","journal-title":"Biometrika"},{"issue":"5","key":"891_CR5","doi-asserted-by":"publisher","first-page":"1986","DOI":"10.1214\/15-AOS1334","volume":"43","author":"I Castillo","year":"2015","unstructured":"Castillo I, Schmidt-Hieber J, Van der Vaart A (2015) Bayesian linear regression with sparse priors. Ann Stat 43(5):1986\u20132018","journal-title":"Ann Stat"},{"key":"891_CR6","unstructured":"Chang J, Gerrish S, Wang C, Boyd-Graber JL, Blei DM (2009) Reading tea leaves: how humans interpret topic models. In: Advances in neural information processing systems, pp 288\u2013296"},{"key":"891_CR7","doi-asserted-by":"crossref","unstructured":"Chemudugunta C, Smyth P, Steyvers M (2007) Modeling general and specific aspects of documents with a probabilistic topic model. In: Advances in neural information processing systems, pp 241\u2013248","DOI":"10.7551\/mitpress\/7503.003.0035"},{"issue":"2","key":"891_CR8","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1111\/1467-9868.00179","volume":"61","author":"P Damlen","year":"1999","unstructured":"Damlen P, Wakefield J, Walker S (1999) Gibbs sampling for Bayesian non-conjugate and hierarchical models by using auxiliary variables. J R Stat Soc Ser B (Stat Methodol) 61(2):331\u2013344","journal-title":"J R Stat Soc Ser B (Stat Methodol)"},{"key":"891_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0003-2670(86)80028-9","volume":"185","author":"P Geladi","year":"1986","unstructured":"Geladi P, Kowalski BR (1986) Partial least-squares regression: a tutorial. Anal Chim Acta 185:1\u201317","journal-title":"Anal Chim Acta"},{"key":"891_CR10","unstructured":"Griffiths TL, Steyvers M, Blei DM, Tenenbaum JB (2005) Integrating topics and syntax. In: Advances in neural information processing systems, pp 537\u2013544"},{"issue":"2","key":"891_CR11","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.jeconom.2004.02.002","volume":"124","author":"K Imai","year":"2005","unstructured":"Imai K, van Dyk DA (2005) A Bayesian analysis of the multinomial probit model using marginal data augmentation. J Econom 124(2):311\u2013334","journal-title":"J Econom"},{"issue":"4","key":"891_CR12","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s10791-015-9254-2","volume":"18","author":"S Jameel","year":"2015","unstructured":"Jameel S, Lam W, Bing L (2015) Supervised topic models with word order structure for document classification and retrieval learning. Inf Retr J 18(4):283\u2013330","journal-title":"Inf Retr J"},{"key":"891_CR13","unstructured":"Jiang Q, Zhu J, Sun M, Xing EP (2012) Monte Carlo methods for maximum margin supervised topic models. In: Advances in neural information processing systems, pp 1592\u20131600"},{"key":"891_CR14","unstructured":"Johndrow J, Dunson D, Lum K (2013) Diagonal orthant multinomial probit models. In: Proceedings of the sixteenth international conference on artificial intelligence and statistics, pp 29\u201338"},{"key":"891_CR15","doi-asserted-by":"crossref","unstructured":"Jonsson L, Broman D, Magnusson M, Sandahl K, Villani M, Eldh S (2016) Automatic localization of bugs to faulty components in large scale software systems using Bayesian classification. In: 2016 IEEE international conference on software quality, reliability and security (QRS). IEEE, pp 423\u2013430","DOI":"10.1109\/QRS.2016.54"},{"issue":"3","key":"891_CR16","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s10489-014-0595-0","volume":"42","author":"X Li","year":"2015","unstructured":"Li X, Ouyang J, Zhou X, Lu Y, Liu Y (2015) Supervised labeled latent Dirichlet allocation for document categorization. Appl Intell 42(3):581\u2013593","journal-title":"Appl Intell"},{"issue":"2","key":"891_CR17","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1080\/10618600.2017.1366913","volume":"27","author":"M Magnusson","year":"2018","unstructured":"Magnusson M, Jonsson L, Villani M, Broman D (2018) Sparse partially collapsed mcmc for parallel inference in topic models. J Comput Graph Stat 27(2):449\u2013463","journal-title":"J Comput Graph Stat"},{"key":"891_CR18","unstructured":"McAuliffe JD, Blei DM (2008) Supervised topic models. In: Advances in neural information processing systems, pp 121\u2013128"},{"key":"891_CR19","unstructured":"Mimno D, McCallum A (2012) Topic models conditioned on arbitrary features with Dirichlet-multinomial regression. arXiv preprint arXiv:1206.3278"},{"key":"891_CR20","unstructured":"Mimno D, Wallach HM, Talley E, Leenders M, McCallum A (2011) Optimizing semantic coherence in topic models. In: Proceedings of the 2011 conference on empirical methods in natural language processing. association for computational linguistics, pp 262\u2013272"},{"key":"891_CR21","doi-asserted-by":"crossref","unstructured":"Mullen L (2016) tokenizers: a consistent interface to tokenize natural language text. R package version 0.1.4","DOI":"10.32614\/CRAN.package.tokenizers"},{"issue":"4","key":"891_CR22","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1214\/18-AOAS1157","volume":"12","author":"M Nalenz","year":"2018","unstructured":"Nalenz M, Villani M (2018) Tree ensembles with rule structured horseshoe regularization. Ann Appl Stat 12(4):2379\u20132408","journal-title":"Ann Appl Stat"},{"issue":"Aug","key":"891_CR23","first-page":"1801","volume":"10","author":"D Newman","year":"2009","unstructured":"Newman D, Asuncion A, Smyth P, Welling M (2009) Distributed algorithms for topic models. J Mach Learn Res 10(Aug):1801\u20131828","journal-title":"J Mach Learn Res"},{"key":"891_CR24","unstructured":"Parnin C, Orso A (2011) Are automated debugging techniques actually helping programmers? In: Proceedings of the 2011 international symposium on software testing and analysis. ACM, pp 199\u2013209"},{"key":"891_CR25","unstructured":"Perotte AJ, Wood F, Elhadad N, Bartlett N (2011) Hierarchically supervised latent Dirichlet allocation. In: Advances in neural information processing systems, pp 2609\u20132617"},{"issue":"504","key":"891_CR26","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1080\/01621459.2013.829001","volume":"108","author":"NG Polson","year":"2013","unstructured":"Polson NG, Scott JG, Windle J (2013) Bayesian inference for logistic models using P\u00f3lya-gamma latent variables. J Am Stat Assoc 108(504):1339\u20131349","journal-title":"J Am Stat Assoc"},{"key":"891_CR27","unstructured":"Rosen-Zvi M, Griffiths T, Steyvers M, Smyth P (2004) The author-topic model for authors and documents. In: Proceedings of the 20th conference on uncertainty in artificial intelligence. AUAI Press, pp 487\u2013494"},{"issue":"1\u20132","key":"891_CR28","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s10994-011-5272-5","volume":"88","author":"TN Rubin","year":"2012","unstructured":"Rubin TN, Chambers A, Smyth P, Steyvers M (2012) Statistical topic models for multi-label document classification. Mach Learn 88(1\u20132):157\u2013208","journal-title":"Mach Learn"},{"key":"891_CR29","volume-title":"The New York Times annotated corpus LDC2008T19","author":"E Sandhaus","year":"2008","unstructured":"Sandhaus E (2008) The New York Times annotated corpus LDC2008T19. Linguistic Data Consortium, Philadelphia"},{"key":"891_CR30","unstructured":"Scott JG (2010) Parameter expansion in local-shrinkage models. arXiv preprint arXiv:1010.5265"},{"key":"891_CR31","unstructured":"Wallach HM, Mimno DM, McCallum A (2009) Rethinking LDA: why priors matter. In: Advances in neural information processing systems, pp 1973\u20131981"},{"key":"891_CR32","doi-asserted-by":"crossref","unstructured":"Zheng X, Yu Y, Xing EP (2015) Linear time samplers for supervised topic models using compositional proposals. In: Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 1523\u20131532","DOI":"10.1145\/2783258.2783371"},{"issue":"1","key":"891_CR33","first-page":"2237","volume":"13","author":"J Zhu","year":"2012","unstructured":"Zhu J, Ahmed A, Xing EP (2012) MedLDA: maximum margin supervised topic models. J Mach Learn Res 13(1):2237\u20132278","journal-title":"J Mach Learn Res"},{"key":"891_CR34","unstructured":"Zhu J, Zheng X, Zhang B (2013) Improved Bayesian logistic supervised topic models with data augmentation. In: Proceedings of the 51st annual meeting of the association for computational linguistics, vol 1, pp 187\u2013195"}],"container-title":["Computational Statistics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00180-019-00891-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00180-019-00891-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00180-019-00891-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T16:09:36Z","timestamp":1721405376000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00180-019-00891-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,12]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["891"],"URL":"https:\/\/doi.org\/10.1007\/s00180-019-00891-1","relation":{},"ISSN":["0943-4062","1613-9658"],"issn-type":[{"value":"0943-4062","type":"print"},{"value":"1613-9658","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,12]]},"assertion":[{"value":"13 June 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}