{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T15:18:57Z","timestamp":1780413537757,"version":"3.54.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T00:00:00Z","timestamp":1673827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T00:00:00Z","timestamp":1673827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1934925"],"award-info":[{"award-number":["1934925"]}],"id":[{"id":"10.13039\/501100008982","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":[[2023,5]]},"DOI":"10.1007\/s10115-022-01805-2","type":"journal-article","created":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T19:03:46Z","timestamp":1673895826000},"page":"2159-2186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Using topic-noise models to generate domain-specific topics across data sources"],"prefix":"10.1007","volume":"65","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4798-1582","authenticated-orcid":false,"given":"Rob","family":"Churchill","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,16]]},"reference":[{"key":"1805_CR1","unstructured":"Churchill R, Singh L (2020) Percolation-based topic modeling for tweets. In: WISDOM 2020: KDD workshop on issues of sentiment discovery and opinion mining"},{"key":"1805_CR2","doi-asserted-by":"crossref","unstructured":"Churchill R, Singh L, Kirov C (2018) A temporal topic model for noisy mediums. In: pacific-asia conference on knowledge discovery and data mining (PAKDD)","DOI":"10.1007\/978-3-319-93037-4_4"},{"key":"1805_CR3","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 (NIPS)","DOI":"10.7551\/mitpress\/7503.003.0035"},{"key":"1805_CR4","doi-asserted-by":"crossref","unstructured":"Li C, Wang H, Zhang Z, Sun A, Ma Z (2016) Topic modeling for short texts with auxiliary word embeddings. In: ACM SIGIR conference on research and development in information retrieval, pp. 165\u2013174","DOI":"10.1145\/2911451.2911499"},{"key":"1805_CR5","doi-asserted-by":"crossref","unstructured":"Churchill R, Singh L (2021) Topic-noise models: modeling topic and noise distributions in social media post collections. In: International conference on data mining (ICDM)","DOI":"10.1109\/ICDM51629.2021.00017"},{"key":"1805_CR6","doi-asserted-by":"crossref","unstructured":"Churchill R, Singh L (2021) The evolution of topic modeling. ACM Comput. Surv","DOI":"10.1145\/3507900"},{"key":"1805_CR7","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"},{"issue":"476","key":"1805_CR8","doi-asserted-by":"publisher","first-page":"1566","DOI":"10.1198\/016214506000000302","volume":"101","author":"YW Teh","year":"2006","unstructured":"Teh YW, Jordan MI, Beal MJ, Blei DM (2006) Hierarchical dirichlet processes. J Am Stat Assoc 101(476):1566\u20131581","journal-title":"J Am Stat Assoc"},{"key":"1805_CR9","doi-asserted-by":"crossref","unstructured":"Blei DM, Lafferty JD (2006) Dynamic topic models. In: International conference on machine learning (ICML)","DOI":"10.1145\/1143844.1143859"},{"key":"1805_CR10","unstructured":"Lafferty JD, Blei DM (2006) Correlated topic models. In: Advances in neural information processing systems (NIPS)"},{"issue":"2\u20133","key":"1805_CR11","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1023\/A:1007692713085","volume":"39","author":"K Nigam","year":"2000","unstructured":"Nigam K, McCallum AK, Thrun S, Mitchell T (2000) Text classification from labeled and unlabeled documents using EM. Mach Learn 39(2\u20133):103\u2013134","journal-title":"Mach Learn"},{"key":"1805_CR12","unstructured":"Quan X, Kit C, Ge Y, Pan SJ (2015) Short and sparse text topic modeling via self-aggregation. In: International joint conference on artificial intelligence"},{"key":"1805_CR13","doi-asserted-by":"crossref","unstructured":"Yin J, Wang J (2014) A dirichlet multinomial mixture model-based approach for short text clustering. In: ACM international conference on knowledge discovery and data mining (KDD)","DOI":"10.1145\/2623330.2623715"},{"key":"1805_CR14","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1162\/tacl_a_00140","volume":"3","author":"DQ Nguyen","year":"2015","unstructured":"Nguyen DQ, Billingsley R, Du L, Johnson M (2015) Improving topic models with latent feature word representations. Trans Assoc Comput Linguist 3:299\u2013313","journal-title":"Trans Assoc Comput Linguist"},{"issue":"Feb","key":"1805_CR15","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio Y, Ducharme R, Vincent P, Jauvin C (2003) A neural probabilistic language model. J Mach Learn Res 3(Feb):1137\u20131155","journal-title":"J Mach Learn Res"},{"key":"1805_CR16","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems (NIPS), pp. 3111\u20133119"},{"key":"1805_CR17","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781"},{"key":"1805_CR18","unstructured":"Moody CE (2016) Mixing dirichlet topic models and word embeddings to make lda2vec. CoRR arXiv:1605.02019"},{"key":"1805_CR19","doi-asserted-by":"crossref","unstructured":"Wang J, Chen L, Qin L, Wu X (2018) Astm: An attentional segmentation based topic model for short texts. In: IEEE international conference on data mining (ICDM)","DOI":"10.1109\/ICDM.2018.00073"},{"key":"1805_CR20","doi-asserted-by":"crossref","unstructured":"Dieng AB, Ruiz FJ, Blei DM (2019) Topic modeling in embedding spaces. arXiv preprint arXiv:1907.04907","DOI":"10.1162\/tacl_a_00325"},{"key":"1805_CR21","unstructured":"Dieng AB, Ruiz FJR, Blei DM (2019) The dynamic embedded topic model. CoRR arXiv:1907.05545"},{"key":"1805_CR22","doi-asserted-by":"crossref","unstructured":"Zhao WX, Jiang J, Weng J, He J, Lim E-P, Yan H, Li X (2011) Comparing twitter and traditional media using topic models. In: European conference on information retrieval (ECIR)","DOI":"10.1007\/978-3-642-20161-5_34"},{"key":"1805_CR23","doi-asserted-by":"crossref","unstructured":"Qiang J, Chen P, Wang T, Wu X (2016) Topic modeling over short texts by incorporating word embeddings. CoRR arXiv:1609.08496","DOI":"10.1007\/978-3-319-57529-2_29"},{"key":"1805_CR24","doi-asserted-by":"crossref","unstructured":"Zuo Y, Wu J, Zhang H, Lin H, Wang F, Xu K, Xiong H (2016) Topic modeling of short texts: a pseudo-document view. In: International conference on knowledge discovery & data mining (KDD), pp. 2105\u20132114","DOI":"10.1145\/2939672.2939880"},{"key":"1805_CR25","doi-asserted-by":"crossref","unstructured":"Yan X, Guo J, Lan Y, Cheng X (2013) A biterm topic model for short texts. In: International conference on world wide web (WWW)","DOI":"10.1145\/2488388.2488514"},{"key":"1805_CR26","unstructured":"Miao Y, Yu L, Blunsom P (2016) Neural variational inference for text processing. In: international conference on machine learning (ICML), vol. 48, pp. 1727\u20131736"},{"key":"1805_CR27","doi-asserted-by":"crossref","unstructured":"Gui L, Leng J, Pergola G, Zhou Y, Xu R, He Y (2019) Neural topic model with reinforcement learning. In: Conference on empirical methods in natural language processing and the international joint conference on natural language processing (EMNLP-IJCNLP), pp. 3478\u20133483","DOI":"10.18653\/v1\/D19-1350"},{"issue":"6","key":"1805_CR28","doi-asserted-by":"publisher","first-page":"102098","DOI":"10.1016\/j.ipm.2019.102098","volume":"56","author":"R Wang","year":"2019","unstructured":"Wang R, Zhou D, He Y (2019) Atm: adversarial-neural topic model. Inf Process Manag 56(6):102098","journal-title":"Inf Process Manag"},{"key":"1805_CR29","doi-asserted-by":"crossref","unstructured":"Wang R, Hu X, Zhou D, He Y, Xiong Y, Ye C, Xu H (2020) Neural topic modeling with bidirectional adversarial training. arXiv preprint arXiv:2004.12331","DOI":"10.18653\/v1\/2020.acl-main.32"},{"key":"1805_CR30","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.ins.2018.04.071","volume":"456","author":"X Li","year":"2018","unstructured":"Li X, Wang Y, Zhang A, Li C, Chi J, Ouyang J (2018) Filtering out the noise in short text topic modeling. Inf Sci 456:83\u201396","journal-title":"Inf Sci"},{"key":"1805_CR31","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/j.ipm.2004.11.005","volume":"42","author":"F Shahnaz","year":"2006","unstructured":"Shahnaz F, Berry MW, Pauca VP, Plemmons RJ (2006) Document clustering using nonnegative matrix factorization. Inf Process Manag 42:373\u2013386","journal-title":"Inf Process Manag"},{"key":"1805_CR32","doi-asserted-by":"crossref","unstructured":"Kasiviswanathan SP, Melville P, Banerjee A, Sindhwani V (2011) Emerging topic detection using dictionary learning. In: ACM international conference on information and knowledge management","DOI":"10.1145\/2063576.2063686"},{"key":"1805_CR33","doi-asserted-by":"crossref","unstructured":"Yan X, Guo J, Liu S, Cheng X, Wang Y (2013) Learning topics in short texts by non-negative matrix factorization on term correlation matrix. In: SIAM international conference on data mining (SDM)","DOI":"10.1137\/1.9781611972832.83"},{"key":"1805_CR34","doi-asserted-by":"crossref","unstructured":"Cataldi M, Di\u00a0Caro L, Schifanella C (2010) Emerging topic detection on twitter based on temporal and social terms evaluation. In: ACM KDD workshop on multimedia data mining","DOI":"10.1145\/1814245.1814249"},{"key":"1805_CR35","doi-asserted-by":"crossref","unstructured":"de Arruda HF, da Fontoura\u00a0Costa L, Amancio DR (2016) Topic segmentation via community detection in complex networks. Chaos 26","DOI":"10.1063\/1.4954215"},{"key":"1805_CR36","unstructured":"McCallum AK (2002) Mallet: a machine learning for language toolkit"},{"key":"1805_CR37","unstructured":"Lang K (1995) 20 Newsgroups Dataset. http:\/\/people.csail.mit.edu\/jrennie\/20Newsgroups\/"},{"key":"1805_CR38","doi-asserted-by":"crossref","unstructured":"Churchill R, Singh L (2021) textprep: a text preprocessing toolkit for topic modeling on social media data. In: International conference on data science, technology, and applications (DATA)","DOI":"10.5220\/0010559000600070"},{"key":"1805_CR39","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Empirical methods in natural language processing (EMNLP), pp. 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"1805_CR40","doi-asserted-by":"crossref","unstructured":"Lau JH, Newman D, Baldwin T (2014) Machine reading tea leaves: automatically evaluating topic coherence and topic model quality. In: Conference of the european chapter of the association for computational linguistics, pp. 530\u2013539","DOI":"10.3115\/v1\/E14-1056"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-022-01805-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-022-01805-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-022-01805-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T14:35:06Z","timestamp":1744209306000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-022-01805-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,16]]},"references-count":40,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["1805"],"URL":"https:\/\/doi.org\/10.1007\/s10115-022-01805-2","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,16]]},"assertion":[{"value":"8 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}