{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:00:57Z","timestamp":1743001257571,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811366604"},{"type":"electronic","value":"9789811366611"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-981-13-6661-1_19","type":"book-chapter","created":{"date-parts":[[2019,2,15]],"date-time":"2019-02-15T05:58:46Z","timestamp":1550210326000},"page":"241-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Taxonomy-Augmented Features for Document Clustering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5325-9724","authenticated-orcid":false,"given":"Sattar","family":"Seifollahi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9250-6604","authenticated-orcid":false,"given":"Massimo","family":"Piccardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehsan Zare","family":"Borzeshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernie","family":"Kruger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,2,16]]},"reference":[{"key":"19_CR1","unstructured":"Arthur, D., Vassilvitskii, S.: k-means++: the advantages of careful seeding. In: Gabow, H. (Ed.) Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms [SODA07], pp. 1027\u20131035. Society for Industrial and Applied Mathematics (2007)"},{"key":"19_CR2","unstructured":"Bagirov, A., Seifollahi, S., Piccardi, M., Zare, E., Kruger, B.: SMGKM: an efficient incremental algorithm for clustering document collections. CICLing 2018 (2018)"},{"key":"19_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v025.i04","volume":"25","author":"G Brock","year":"2008","unstructured":"Brock, G., Pihur, V., Datta, S., Datta, S.: clValid: an R package for cluster validation. J. Stat. Softw. 25, 1\u201322 (2008)","journal-title":"J. Stat. Softw."},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Y. Cheng. Ontology-based fuzzy semantic clustering. In Proceedings \u2013 3rd International Conference on Convergence and Hybrid Information Technology, ICCIT 2008, vol. 2, pp. 128\u2013133 (2008)","DOI":"10.1109\/ICCIT.2008.232"},{"key":"19_CR5","unstructured":"Das, R., Zaheer, M., Dyer, C.: Gaussian LDA for topic models with word embeddings. In: Proceedings ACL 2015, pp. 795\u2013804 (2015)"},{"key":"19_CR6","volume-title":"Data Mining for Scientific and Engineering Applications","author":"S Dhillon","year":"2001","unstructured":"Dhillon, S., Fan, J., Guan, Y.: Efficient clustering of very large document collections. In: Kamath, C., Kumar, V., Grossman, R., Namburu, R. (eds.) Data Mining for Scientific and Engineering Applications. Kluwer Academic Publishers, Oxford (2001)"},{"issue":"2","key":"19_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5121\/ijdms.2015.7201","volume":"7","author":"A Elsayed","year":"2015","unstructured":"Elsayed, A., Mokhtar, H.M.O., Ismail, O.: Ontology based document clustering using Mapreduce. Int. J. Database Manag. Syst. 7(2), 1\u201312 (2015)","journal-title":"Int. J. Database Manag. Syst."},{"key":"19_CR8","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.ins.2014.08.062","volume":"292","author":"U Erra","year":"2015","unstructured":"Erra, U., Senatore, S., Minnella, F., Caggianese, G.: Approximate tf-idf based on topic extraction from massive message stream using the gpu. Inf. Sci. 292, 143\u2013161 (2015)","journal-title":"Inf. Sci."},{"issue":"2","key":"19_CR9","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s10115-010-0370-4","volume":"28","author":"S Fodeh","year":"2011","unstructured":"Fodeh, S., Punch, B., Tan, P.-N.: On ontology-driven document clustering using core semantic features. Knowl. Inf. Syst. 28(2), 395\u2013421 (2011)","journal-title":"Knowl. Inf. Syst."},{"issue":"1","key":"19_CR10","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1023\/A:1009778005914","volume":"1","author":"JH Friedman","year":"1997","unstructured":"Friedman, J.H.: On bias, variance, 0\/1-loss, and the curse-of-dimensionality. Data Min. Knowl. Discov. 1(1), 55\u201377 (1997)","journal-title":"Data Min. Knowl. Discov."},{"key":"19_CR11","unstructured":"Hotho, A., Staab, S., Stumme, G.: Ontologies improve text document clustering. In: Third IEEE International Conference on Data Mining, pp. 541\u2013544 (2003)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Kim, J., Rousseau, F., Vazirgiannis, M.: Convolutional sentence kernel from word embeddings for short text categorization. In: Proceedings EMNLP 2015, pp. 775\u2013780, September 2015","DOI":"10.18653\/v1\/D15-1089"},{"key":"19_CR13","unstructured":"Kusner, M.J., Sun, Y., Kolkin, N.I., Weinberger, K.Q.: From word embeddings to document distances. In: Proceedings - ICML, vol. 37, pp. 957\u2013966 (2015)"},{"key":"19_CR14","unstructured":"Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: Proceedings of the 31st International Conference on Machine Learning, vol. 32, pp. 1188\u20131196 (2014)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Lenc, L., Kr\u00e1l, P.: Word embeddings for multi-label document classification. In: Proceedings of Recent Advances in Natural Language Processing, pp. 431\u2013437 (2017)","DOI":"10.26615\/978-954-452-049-6_057"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Lilleberg, J., Zhu, Y., Zhang, Y.: Support vector machines and word2vec for text classification with semantic features. In: Proceedings of IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC), pp. 136\u2013140 (2015)","DOI":"10.1109\/ICCI-CC.2015.7259377"},{"key":"19_CR17","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. Arxiv, pp. 1\u201312 (2013)"},{"key":"19_CR18","unstructured":"Moseley, B., Wang, J.R.: Approximation bounds for hierarchical clustering: average linkage, bisecting K-means, and local search. Number Nips, pp. 3097\u20133106 (2017)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings EMNLP 2014, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"issue":"4","key":"19_CR20","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1007\/s00521-014-1792-9","volume":"26","author":"C Qimin","year":"2015","unstructured":"Qimin, C., Qiao, G., Yongliang, W., Xianghua, W.: Text clustering using vsm with feature clusters. Neural Comput. Appl. 26(4), 995\u20131003 (2015)","journal-title":"Neural Comput. Appl."},{"issue":"6","key":"19_CR21","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1007\/s10791-007-9035-7","volume":"10","author":"DR Recupero","year":"2007","unstructured":"Recupero, D.R.: A new unsupervised method for document clustering by using WordNet lexical and conceptual relations. Inf. Retr. 10(6), 563\u2013579 (2007)","journal-title":"Inf. Retr."},{"issue":"2","key":"19_CR22","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s11063-017-9593-7","volume":"46","author":"S Seifollahi","year":"2017","unstructured":"Seifollahi, S., Bagirov, A., Layton, R., Gondal, I.: Optimization based clustering algorithms for authorship analysis of phishing emails. Neural Process. Lett. 46(2), 411\u2013425 (2017)","journal-title":"Neural Process. Lett."},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Seifzadeh, S., Farahat, A.K., Kamel, M.S., Karray, F.: Short-text clustering using statistical semantics. In: Proceedings WWW 2015, pp. 805\u2013810 (2015)","DOI":"10.1145\/2740908.2742474"},{"key":"19_CR24","unstructured":"Socher, R., Bauer, J., Manning, C.D., Ng, A.Y.: Parsing with compositional vector grammars. In: Proceedings ACL 2013, vol. 1, pp. 455\u2013465 (2013)"},{"key":"19_CR25","unstructured":"Steinbach, M., Karypis, G., Kumar, V.: A comparison of document clustering techniques. In: KDD workshop on text mining, vol. 400, pp. 1\u20132 (2000)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Tang, D., Wei, F., Yang, N., Zhou, M., Liu, T., Qin, B.: Learning sentiment-specific word embedding for twitter sentiment classification. In: Proceedings ACL, pp. 1555\u20131565 (2014)","DOI":"10.3115\/v1\/P14-1146"},{"key":"19_CR27","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1016\/j.neucom.2015.09.096","volume":"174","author":"P Wang","year":"2016","unstructured":"Wang, P., Xu, B., Xu, J., Tian, G., Liu, C.L., Hao, H.: Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification. Neurocomputing 174, 806\u2013814 (2016)","journal-title":"Neurocomputing"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Xun, G., Gopalakrishnan, V., Li, F.M.Y., Gao, J., Zhang, A.: Topic discovery for short texts using word embeddings. In: Proceedings - IEEE International Conference on Data Mining, ICDM, pp. 1299\u20131304 (2017)","DOI":"10.1109\/ICDM.2016.0176"},{"issue":"4","key":"19_CR29","doi-asserted-by":"publisher","first-page":"1857","DOI":"10.1016\/j.eswa.2014.09.011","volume":"42","author":"D Zhang","year":"2015","unstructured":"Zhang, D., Xu, H., Su, Z., Xu, Y.: Chinese comments sentiment classification based on word2vec and SVMperf. Expert Syst. Appl. 42(4), 1857\u20131863 (2015)","journal-title":"Expert Syst. Appl."}],"container-title":["Communications in Computer and Information Science","Data Mining"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-13-6661-1_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T05:21:34Z","timestamp":1568956894000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-13-6661-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9789811366604","9789811366611"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-13-6661-1_19","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"16 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AusDM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Conference on Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bathurst, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausdm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ausdm18.ausdm.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}