{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T12:52:22Z","timestamp":1771591942113,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2020,7,10]],"date-time":"2020-07-10T00:00:00Z","timestamp":1594339200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,7,10]],"date-time":"2020-07-10T00:00:00Z","timestamp":1594339200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Vingroup Innovation Foundation","award":["VINIF.2019.DA18"],"award-info":[{"award-number":["VINIF.2019.DA18"]}]},{"DOI":"10.13039\/100007297","name":"Office of Naval Research Global","doi-asserted-by":"crossref","award":["N62909-18-1-2072"],"award-info":[{"award-number":["N62909-18-1-2072"]}],"id":[{"id":"10.13039\/100007297","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Air Force Office of Scientific Research (AFOSR), Asian Office of Aerospace Research & Development","award":["17IOA031"],"award-info":[{"award-number":["17IOA031"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1007\/s10115-020-01482-z","type":"journal-article","created":{"date-parts":[[2020,7,10]],"date-time":"2020-07-10T14:04:11Z","timestamp":1594389851000},"page":"4055-4090","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Bag of biterms modeling for short texts"],"prefix":"10.1007","volume":"62","author":[{"given":"Anh Phan","family":"Tuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bach","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thien Huu","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0011-5137","authenticated-orcid":false,"given":"Linh Ngo","family":"Van","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khoat","family":"Than","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,7,10]]},"reference":[{"key":"1482_CR1","unstructured":"Hofmann T (1999) Probabilistic latent semantic analysis. In: Proceedings of the fifteenth conference on uncertainty in artificial intelligence. Morgan Kaufmann Publishers Inc., Burlington, pp 289\u2013296"},{"key":"1482_CR2","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":"1482_CR3","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":"1482_CR4","unstructured":"Tang J, Meng Z, Nguyen X, Mei Q, Zhang M (2014) Understanding the limiting factors of topic modeling via posterior contraction analysis. In: Proceedings of The 31st international conference on machine learning, pp 190\u2013198"},{"key":"1482_CR5","unstructured":"Than K, Doan T (2014) Dual online inference for latent Dirichlet allocation. In: ACML"},{"key":"1482_CR6","doi-asserted-by":"crossref","unstructured":"Sahami M, Heilman TD (2006) A web-based kernel function for measuring the similarity of short text snippets. In: Proceedings of the 15th international conference on world wide web. ACM, pp\u00a0377\u2013386","DOI":"10.1145\/1135777.1135834"},{"key":"1482_CR7","unstructured":"Bollegala D, Matsuo Y, Ishizuka M (2007) Measuring semantic similarity between words using web search engines. In: www, vol\u00a07, pp\u00a0757\u2013766"},{"key":"1482_CR8","unstructured":"Yih W-T, Meek C (2007) Improving similarity measures for short segments of text. In: AAAI, vol 7, pp 1489\u20131494"},{"key":"1482_CR9","doi-asserted-by":"crossref","unstructured":"Banerjee S, Ramanathan K, Gupta A (2007) Clustering short texts using wikipedia. In: Proceedings of the 30th annual international ACM SIGIR conference on research and development in information retrieval. ACM, pp\u00a0787\u2013788","DOI":"10.1145\/1277741.1277909"},{"issue":"2","key":"1482_CR10","doi-asserted-by":"publisher","first-page":"195","DOI":"10.3233\/WIA-2009-0162","volume":"7","author":"P Sch\u00f6nhofen","year":"2009","unstructured":"Sch\u00f6nhofen P (2009) Identifying document topics using the wikipedia category network. Web Intell Agent Syst 7(2):195\u2013207","journal-title":"Web Intell Agent Syst"},{"key":"1482_CR11","doi-asserted-by":"crossref","unstructured":"Phan X-H, Nguyen L-M, Horiguchi S (2008) Learning to classify short and sparse text and web with hidden topics from large-scale data collections. In: Proceedings of the 17th international conference on world wide web. ACM, pp\u00a091\u2013100","DOI":"10.1145\/1367497.1367510"},{"key":"1482_CR12","doi-asserted-by":"crossref","unstructured":"Mehrotra R, Sanner S, Buntine W, Xie L (2013) Improving LDA topic models for microblogs via tweet pooling and automatic labeling. In: Proceedings of the 36th international ACM SIGIR conference on research and development in information retrieval. ACM, pp\u00a0889\u2013892","DOI":"10.1145\/2484028.2484166"},{"key":"1482_CR13","unstructured":"Grant CE, George CP, Jenneisch C, Wilson JN (2011) Online topic modeling for real-time Twitter search. In: TREC"},{"key":"1482_CR14","first-page":"10433","volume":"10","author":"C Ye","year":"2014","unstructured":"Ye C, Wen W (2014) PY: TM-HDP\u2014an effective nonparametric topic model for Tibetan messages. J Comput Inf Syst 10:10433\u201310444","journal-title":"J Comput Inf Syst"},{"key":"1482_CR15","doi-asserted-by":"crossref","unstructured":"Hong L, Davison BD (2010) Empirical study of topic modeling in Twitter. In: Proceedings of the first workshop on social media analytics. ACM, pp\u00a080\u201388","DOI":"10.1145\/1964858.1964870"},{"key":"1482_CR16","doi-asserted-by":"crossref","unstructured":"Qiang J, Chen P, Wang T, Wu X (2017) Topic modeling over short texts by incorporating word embeddings. In: Pacific-Asia conference on knowledge discovery and data mining. Springer, Berlin, pp\u00a0363\u2013374","DOI":"10.1007\/978-3-319-57529-2_29"},{"key":"1482_CR17","unstructured":"Zhao H, Du L, Buntine W (2017) A word embeddings informed focused topic model. In: Asian conference on machine learning, pp\u00a0423\u2013438"},{"issue":"2","key":"1482_CR18","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/3091108","volume":"36","author":"C Li","year":"2017","unstructured":"Li C, Duan Y, Wang H, Zhang Z, Sun A, Ma Z (2017) Enhancing topic modeling for short texts with auxiliary word embeddings. ACM Trans Inf Syst (TOIS) 36(2):11","journal-title":"ACM Trans Inf Syst (TOIS)"},{"key":"1482_CR19","doi-asserted-by":"crossref","unstructured":"Weng J, Lim E-P, Jiang J, He Q (2010) Twitterrank: finding topic-sensitive influential Twitterers. In: Proceedings of the third ACM international conference on web search and data mining. ACM, pp\u00a0261\u2013270","DOI":"10.1145\/1718487.1718520"},{"key":"1482_CR20","doi-asserted-by":"crossref","unstructured":"Jiang L, Lu H, Xu M, Wang C (2016) Biterm pseudo document topic model for short text. In: 2016 IEEE 28th International conference on tools with artificial intelligence (ICTAI). IEEE, pp\u00a0865\u2013872","DOI":"10.1109\/ICTAI.2016.0134"},{"key":"1482_CR21","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.ins.2017.02.007","volume":"393","author":"P Bicalho","year":"2017","unstructured":"Bicalho P, Pita M, Pedrosa G, Lacerda A, Pappa GL (2017) A general framework to expand short text for topic modeling. Inf Sci 393:66\u201381","journal-title":"Inf Sci"},{"issue":"2","key":"1482_CR22","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/s11280-017-0467-8","volume":"21","author":"Y Yang","year":"2018","unstructured":"Yang Y, Wang F, Zhang J, Xu J, Philip SY (2018) A topic model for co-occurring normal documents and short texts. World Wide Web 21(2):487\u2013513","journal-title":"World Wide Web"},{"key":"1482_CR23","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: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp\u00a02105\u20132114","DOI":"10.1145\/2939672.2939880"},{"key":"1482_CR24","unstructured":"Quan X, Kit C, Ge Y, Pan SJ (2015) Short and sparse text topic modeling via self-aggregation. In: IJCAI, pp\u00a02270\u20132276"},{"issue":"12","key":"1482_CR25","doi-asserted-by":"publisher","first-page":"2928","DOI":"10.1109\/TKDE.2014.2313872","volume":"26","author":"X Cheng","year":"2014","unstructured":"Cheng X, Yan X, Lan Y, Guo J (2014) BTM: topic modeling over short texts. IEEE Trans Knowl Data Eng 26(12):2928\u20132941","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1482_CR26","unstructured":"Wang C, Paisley JW, Blei DM (2011) Online variational inference for the hierarchical Dirichlet process. In: AISTATS, vol\u00a02, p\u00a04"},{"key":"1482_CR27","unstructured":"Broderick T, Boyd N, Wibisono A, Wilson AC, Jordan MI (2013) Streaming variational Bayes. In: Proceedings of advances in neural information processing systems conferences. Curran Associates, pp\u00a01727\u20131735"},{"key":"1482_CR28","doi-asserted-by":"crossref","unstructured":"Duc AN, Van\u00a0Linh N, Kim AN, Than K (2017) Keeping priors in streaming Bayesian learning. In: Pacific-Asia conference on knowledge discovery and data mining. Springer, Berlin, pp\u00a0247\u2013258","DOI":"10.1007\/978-3-319-57529-2_20"},{"key":"1482_CR29","unstructured":"Mimno D, Wallach HM, Talley E, Leenders M, McCallum A (2011) Optimizing semantic coherence in topic models. In: Proceedings of the conference on empirical methods in natural language processing. Association for Computational Linguistics, pp\u00a0262\u2013272"},{"key":"1482_CR30","doi-asserted-by":"crossref","unstructured":"Yan X, Guo J, Lan Y, Cheng X (2013) A biterm topic model for short texts. In: Proceedings of the 22nd international conference on world wide web. ACM, pp\u00a01445\u20131456","DOI":"10.1145\/2488388.2488514"},{"key":"1482_CR31","unstructured":"Hoffman M, Bach FR, Blei DM (2010) Online learning for latent Dirichlet allocation. In: Proceedings of advances in neural information processing systems conferences. Curran Associates, pp\u00a0856\u2013864"},{"issue":"1","key":"1482_CR32","first-page":"1303","volume":"14","author":"MD Hoffman","year":"2013","unstructured":"Hoffman MD, Blei DM, Wang C, Paisley J (2013) Stochastic variational inference. J Mach Learn Res 14(1):1303\u20131347","journal-title":"J Mach Learn Res"},{"key":"1482_CR33","doi-asserted-by":"crossref","unstructured":"Mai K, Mai S, Nguyen A, Van\u00a0Linh N, Than K (2006) Enabling hierarchical Dirichlet processes to work better for short texts at large scale. In: Pacific-Asia conference on knowledge discovery and data mining. Springer, Berlin, pp\u00a0431\u2013442","DOI":"10.1007\/978-3-319-31750-2_34"},{"key":"1482_CR34","doi-asserted-by":"crossref","unstructured":"Chang C-C, Lin C-J, (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:27:1\u201327:27. Software available at http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm","DOI":"10.1145\/1961189.1961199"},{"key":"1482_CR35","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceedings of the conference on empirical methods in natural language processing (EMNLP), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"1482_CR36","unstructured":"Bouma G (2009) Normalized (pointwise) mutual information in collocation extraction. In: Proceedings of GSCL, pp\u00a031\u201340"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-020-01482-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-020-01482-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-020-01482-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,10]],"date-time":"2021-07-10T00:36:54Z","timestamp":1625877414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-020-01482-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,10]]},"references-count":36,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["1482"],"URL":"https:\/\/doi.org\/10.1007\/s10115-020-01482-z","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,10]]},"assertion":[{"value":"20 September 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}