{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T23:44:15Z","timestamp":1771890255951,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,12,18]],"date-time":"2018-12-18T00:00:00Z","timestamp":1545091200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61472291"],"award-info":[{"award-number":["61472291"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772382"],"award-info":[{"award-number":["61772382"]}],"id":[{"id":"10.13039\/501100001809","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":[[2019,11]]},"DOI":"10.1007\/s10115-018-1314-7","type":"journal-article","created":{"date-parts":[[2018,12,17]],"date-time":"2018-12-17T22:45:34Z","timestamp":1545086734000},"page":"1123-1145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Incorporating word embeddings into topic modeling of short text"],"prefix":"10.1007","volume":"61","author":[{"given":"Wang","family":"Gao","sequence":"first","affiliation":[]},{"given":"Min","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Hua","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yanchun","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qianqian","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Tian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,18]]},"reference":[{"key":"1314_CR1","unstructured":"Alsmadi I, Hoon GK (2018) Term weighting scheme for short-text classification: Twitter corpuses. Neural Comput Appl 1\u201313"},{"key":"1314_CR2","doi-asserted-by":"crossref","unstructured":"Bansal M, Gimpel K, Livescu K (2014) Tailoring continuous word representations for dependency parsing. In: Proceedings of the annual meeting of the association for computational linguistics (ACL), pp 809\u2013815","DOI":"10.3115\/v1\/P14-2131"},{"key":"1314_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":"1314_CR4","unstructured":"Chang J, Gerrish S, Wang C, Boyd-Graber JL, Blei DM (2009) Reading tea leaves: How humans interpret topic models. In: Proceedings of advances in neural information processing systems (NIPS), pp 288\u2013296"},{"issue":"12","key":"1314_CR5","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":"1314_CR6","doi-asserted-by":"crossref","unstructured":"Das R, Zaheer M, Dyer C (2015) Gaussian LDA for topic models with word embeddings. In: Proceedings of the annual meeting of the association for computational linguistics (ACL), pp 795\u2013804","DOI":"10.3115\/v1\/P15-1077"},{"key":"1314_CR7","unstructured":"Lau JH, Baldwin T (2016) An empirical evaluation of doc2vec with practical insights into document embedding generation. In: Proceedings of the workshop on representation learning for NLP (RepL4NLP), pp 78\u201386"},{"key":"1314_CR8","unstructured":"Gregor H (2005) Parameter estimation for text analysis. Technical Report"},{"key":"1314_CR9","unstructured":"Hofmann T (1999) Probabilistic latent semantic analysis. In: Proceedings of the conference on uncertainty in artificial intelligence (UAI), pp 289\u2013296"},{"key":"1314_CR10","doi-asserted-by":"crossref","unstructured":"Hong L, Davison BD (2010) Empirical study of topic modeling in twitter. In: Proceedings of the workshop on social media analytics (SOMA), pp 80\u201388","DOI":"10.1145\/1964858.1964870"},{"key":"1314_CR11","unstructured":"Huang EH, Socher R, Manning CD, Ng AY (2012) Improving word representations via global context and multiple word prototypes. In: Proceedings of the annual meeting of the association for computational linguistics (ACL), pp 873\u2013882"},{"issue":"1","key":"1314_CR12","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1162\/COLI_a_00167","volume":"40","author":"F Huang","year":"2014","unstructured":"Huang F, Ahuja A, Downey D, Yang Y, Guo Y, Yates A (2014) Learning representations for weakly supervised natural language processing tasks. Computational Linguistics 40(1):85\u2013120","journal-title":"Computational Linguistics"},{"issue":"2","key":"1314_CR13","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/s11280-016-0390-4","volume":"20","author":"J Huang","year":"2017","unstructured":"Huang J, Peng M, Wang H, Cao J, Gao W, Zhang X (2017) A probabilistic method for emerging topic tracking in microblog stream. World Wide Web J 20(2):325\u2013350","journal-title":"World Wide Web J"},{"key":"1314_CR14","doi-asserted-by":"crossref","unstructured":"Jin O, Liu NN, Zhao K, Yu Y, Yang Q (2011) Transferring topical knowledge from auxiliary long texts for short text clustering. In: Proceedings of the ACM conference on information and knowledge management (CIKM), pp 775\u2013784","DOI":"10.1145\/2063576.2063689"},{"issue":"3","key":"1314_CR15","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/s10115-016-0993-1","volume":"51","author":"FH Khan","year":"2017","unstructured":"Khan FH, Qamar U, Bashir S (2017) A semi-supervised approach to sentiment analysis using revised sentiment strength based on SentiWordNet. Knowl Inf Syst 51(3):851\u2013872","journal-title":"Knowl Inf Syst"},{"key":"1314_CR16","unstructured":"Kusner M, Sun Y, Kolkin N, Weinberger K (2015) From word embeddings to document distances. In: Proceedings of international conference on machine learning (ICML), pp 957\u2013966"},{"key":"1314_CR17","unstructured":"Lafferty JD, Mccallum A, Pereira FCN (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the international conference on machine learning (ICML), pp 282\u2013289"},{"key":"1314_CR18","unstructured":"Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: Proceedings of the international conference on machine learning (ICML), pp 1188\u20131196"},{"key":"1314_CR19","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: Proceedings of the ACM conference on research and development in information retrieval (SIGIR), pp 165\u2013174","DOI":"10.1145\/2911451.2911499"},{"key":"1314_CR20","doi-asserted-by":"crossref","unstructured":"Li S, Chua TS, Zhu J, Miao C (2016) Generative topic embedding: a continuous representation of documents. In: Proceedings of the annual meeting of the association for computational linguistics (ACL), pp 666\u2013675","DOI":"10.18653\/v1\/P16-1063"},{"key":"1314_CR21","doi-asserted-by":"crossref","unstructured":"Ma S, Zhang C, He D (2016) Document representation methods for clustering bilingual documents. In: Proceedings of the annual meeting of the association for information science and technology (ASIST), pp 1\u201310","DOI":"10.1002\/pra2.2016.14505301065"},{"key":"1314_CR22","doi-asserted-by":"crossref","unstructured":"Mahmoud H (2008) Polya urn models. CRC press","DOI":"10.1201\/9781420059847"},{"key":"1314_CR23","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 ACM conference on research and development in information retrieval (SIGIR), pp 889\u2013892","DOI":"10.1145\/2484028.2484166"},{"key":"1314_CR24","doi-asserted-by":"crossref","unstructured":"Menini S, Nanni F, Ponzetto SP, Tonelli S (2017) Topic-based agreement and disagreement in us electoral manifestos. In: Proceedings of the conference on empirical methods in natural language processing (EMNLP), pp 2938\u20132944","DOI":"10.18653\/v1\/D17-1318"},{"key":"1314_CR25","doi-asserted-by":"crossref","unstructured":"Metzler D, Dumais S, Meek C (2007) Similarity measures for short segments of text. In: Proceedings of European conference on information retrieval (ECIR), pp 16\u201327","DOI":"10.1007\/978-3-540-71496-5_5"},{"key":"1314_CR26","unstructured":"Mikolov T, Yih WT, Zweig G (2013) Linguistic regularities in continuous space word representations. In: Proceedings of the conference of the North American chapter of the association for computational linguistics: human language technologies (HIT-NAACL), pp 889\u2013892"},{"key":"1314_CR27","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 (EMNLP), pp 262\u2013272"},{"key":"1314_CR28","unstructured":"Newman D, Lau JH, Grieser K, Baldwin T (2010) Automatic evaluation of topic coherence. In: Proceedings of the conference of the North American chapter of the association for computational linguistics (NAACL), pp 100\u2013108"},{"key":"1314_CR29","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":"3","key":"1314_CR30","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s10115-010-0299-7","volume":"27","author":"X Ni","year":"2011","unstructured":"Ni X, Quan X, Lu Z, Wenyin L, Hua B (2011) Short text clustering by finding core terms. Knowl Inf Syst 27(3):345\u2013365","journal-title":"Knowl Inf Syst"},{"issue":"2","key":"1314_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3086702","volume":"36","author":"M Peng","year":"2017","unstructured":"Peng M, Gao W, Wang H, Zhang Y, Huang J, Xie Q, Hu G, Tian G (2017) Parallelization of massive textstream compression based on compressed sensing. ACM Trans Inf Syst 36(2):1\u201318","journal-title":"ACM Trans Inf Syst"},{"key":"1314_CR32","doi-asserted-by":"crossref","unstructured":"Peng M, Xie Q, Zhang Y, Wang H, Zhang X, Huang J, Tian G (2018) Neural sparse topical coding. In: Proceedings of the annual meeting of the association for computational linguistics (ACL), pp 2332\u20132340","DOI":"10.18653\/v1\/P18-1217"},{"key":"1314_CR33","doi-asserted-by":"crossref","unstructured":"Phan XH, Nguyen LM, Horiguchi S (2008) Learning to classify short and sparse text & web with hidden topics from large-scale data collections. In: Proceedings of the conference on world wide web (WWW), pp 91\u2013100","DOI":"10.1145\/1367497.1367510"},{"key":"1314_CR34","unstructured":"Quan X, Kit C, Ge Y, Pan SJ (2015) Short and sparse text topic modeling via self-aggregation. In: Proceedings of the international joint conferences on artificial intelligence (IJCAI), pp 2270\u20132276"},{"key":"1314_CR35","doi-asserted-by":"crossref","unstructured":"Weng J, Lim EP, Jiang J, He Q (2010) Twitterrank: finding topic-sensitive influential twitterers. In: Proceedings of the ACM conference on web search and data mining (WSDM), pp 261\u2013270","DOI":"10.1145\/1718487.1718520"},{"key":"1314_CR36","unstructured":"Xia Y, Tang N, Hussain A, Cambria E (2015) Discriminative bi-term topic model for headline-based social news clustering. In: Proceedings of the Florida artificial intelligence research society conference (FLAIRS), pp 311\u2013316"},{"key":"1314_CR37","doi-asserted-by":"crossref","unstructured":"Xie P, Yang D, Xing E (2015) Incorporating word correlation knowledge into topic modeling. In: Proceedings of the conference of the North American chapter of the association for computational linguistics: human language technologies (HIT-NAACL), pp 725\u2013734","DOI":"10.3115\/v1\/N15-1074"},{"key":"1314_CR38","doi-asserted-by":"crossref","unstructured":"Xu J, Wang P, Tian G, Xu B, Zhao J, Wang F, Hao H (2015) Short text clustering via convolutional neural networks. In: Proceedings of the conference of the North American chapter of the association for computational linguistics: human language technologies (HIT-NAACL), pp 62\u201369","DOI":"10.3115\/v1\/W15-1509"},{"key":"1314_CR39","doi-asserted-by":"crossref","unstructured":"Yin J, Wang J (2014) A Dirichlet multinomial mixture model-based approach for short text clustering. In: Proceedings of the ACM international conference on knowledge discovery and data mining (SIGKDD), pp 233\u2013242","DOI":"10.1145\/2623330.2623715"},{"key":"1314_CR40","doi-asserted-by":"crossref","unstructured":"Zhao WX, Jiang J, Weng J, He J, Lim EP, Yan H, Li X (2011) Comparing twitter and traditional media using topic models. In: Proceedings of European conference on information retrieval (ECIR), pp 338\u2013349","DOI":"10.1007\/978-3-642-20161-5_34"},{"key":"1314_CR41","doi-asserted-by":"crossref","unstructured":"Zuo Y, Wu J, Zhang H, Lin H, Wang F, Xu K (2016) Topic modeling of short texts: a pseudo-document view. In: Proceedings of the ACM international conference on knowledge discovery and data mining (SIGKDD), pp 2015\u20132114","DOI":"10.1145\/2939672.2939880"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-018-1314-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-018-1314-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-018-1314-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,17]],"date-time":"2019-12-17T19:29:10Z","timestamp":1576610950000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-018-1314-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,18]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,11]]}},"alternative-id":["1314"],"URL":"https:\/\/doi.org\/10.1007\/s10115-018-1314-7","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,18]]},"assertion":[{"value":"10 September 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}