{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:48:22Z","timestamp":1740098902334,"version":"3.37.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319630038"},{"type":"electronic","value":"9783319630045"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-63004-5_22","type":"book-chapter","created":{"date-parts":[[2017,7,8]],"date-time":"2017-07-08T01:34:07Z","timestamp":1499477647000},"page":"274-286","source":"Crossref","is-referenced-by-count":4,"title":["Integrating LDA with Clustering Technique for\u00a0Relevance Feature Selection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3692-4681","authenticated-orcid":false,"given":"Abdullah Semran","family":"Alharbi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3594-8980","authenticated-orcid":false,"given":"Yuefeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1137-0272","authenticated-orcid":false,"given":"Yue","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,7,9]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/978-1-4614-3223-4_4","volume-title":"Mining Text Data","author":"CC Aggarwal","year":"2012","unstructured":"Aggarwal, C.C., Zhai, C.: A survey of text clustering algorithms. In: Aggarwal, C.C., Zhai, C.X. (eds.) Mining Text Data, pp. 77\u2013128. Springer, New York (2012)"},{"key":"22_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1007\/978-3-319-03680-9_46","volume-title":"AI 2013: Advances in Artificial Intelligence","author":"M Albathan","year":"2013","unstructured":"Albathan, M., Li, Y., Algarni, A.: Enhanced N-gram extraction using relevance feature discovery. In: Cranefield, S., Nayak, A. (eds.) AI 2013. LNCS, vol. 8272, pp. 453\u2013465. Springer, Cham (2013). doi: 10.1007\/978-3-319-03680-9_46"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Albathan, M., Li, Y., Xu, Y.: Using extended random set to find specific patterns. In: WI 2014, vol. 2, pp. 30\u201337. IEEE (2014)","DOI":"10.1109\/WI-IAT.2014.77"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Beil, F., Ester, M., Xu, X.: Frequent term-based text clustering. In: KDD 2002, pp. 436\u2013442. ACM (2002)","DOI":"10.1145\/775047.775110"},{"key":"22_CR5","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993\u20131022 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Buckley, C., Voorhees, E.M.: Evaluating evaluation measure stability. In: SIGIR 2000, pp. 33\u201340. ACM (2000)","DOI":"10.1145\/345508.345543"},{"key":"22_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-319-42291-6_12","volume-title":"Intelligent Computing Theories and Application","author":"S Chao","year":"2016","unstructured":"Chao, S., Cai, J., Yang, S., Wang, S.: A clustering based feature selection method using feature information distance for text data. In: Huang, D.-S., Bevilacqua, V., Premaratne, P. (eds.) ICIC 2016. LNCS, vol. 9771, pp. 122\u2013132. Springer, Cham (2016). doi: 10.1007\/978-3-319-42291-6_12"},{"issue":"1","key":"22_CR8","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1109\/TSMCA.2007.909595","volume":"38","author":"S Das","year":"2008","unstructured":"Das, S., Abraham, A., Konar, A.: Automatic clustering using an improved differential evolution algorithm. IEEE Trans. Syst. Man Cybern.-Part A: Syst. Hum. 38(1), 218\u2013237 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern.-Part A: Syst. Hum."},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Ferreira, C.H., de Medeiros, D.M., Santana, F.: Fcfilter: feature selection based on clustering and genetic algorithms. In: CEC 2016, pp. 2106\u20132113. IEEE (2016)","DOI":"10.1109\/CEC.2016.7744048"},{"issue":"6","key":"22_CR10","first-page":"1629","volume":"27","author":"Y Gao","year":"2015","unstructured":"Gao, Y., Xu, Y., Li, Y.: Pattern-based topics for document modelling in information filtering. IEEE TKDE 27(6), 1629\u20131642 (2015)","journal-title":"IEEE TKDE"},{"issue":"1\u20132","key":"22_CR11","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1023\/A:1007617005950","volume":"42","author":"T Hofmann","year":"2001","unstructured":"Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Mach. Learn. 42(1\u20132), 177\u2013196 (2001)","journal-title":"Mach. Learn."},{"key":"22_CR12","unstructured":"Huang, A.: Similarity measures for text document clustering. In: NZCSRSC 2008, pp. 49\u201356 (2008)"},{"issue":"8","key":"22_CR13","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1016\/j.patrec.2009.09.011","volume":"31","author":"AK Jain","year":"2010","unstructured":"Jain, A.K.: Data clustering: 50 years beyond k-means. Pattern Recogn. Lett. 31(8), 651\u2013666 (2010)","journal-title":"Pattern Recogn. Lett."},{"issue":"6","key":"22_CR14","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1007\/s10791-011-9168-6","volume":"14","author":"E Krikon","year":"2011","unstructured":"Krikon, E., Kurland, O.: A study of the integration of passage-, document-, and cluster-based information for re-ranking search results. Inf. Retr. 14(6), 593 (2011)","journal-title":"Inf. Retr."},{"key":"22_CR15","volume-title":"Uncertainty and Vagueness in Knowledge Based Systems: Numerical Methods","author":"R Kruse","year":"2012","unstructured":"Kruse, R., Schwecke, E., Heinsohn, J.: Uncertainty and Vagueness in Knowledge Based Systems: Numerical Methods. Springer Science & Business Media, Heidelberg (2012)"},{"issue":"4","key":"22_CR16","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1109\/TPAMI.2008.110","volume":"31","author":"M Lan","year":"2009","unstructured":"Lan, M., Tan, C.L., Su, J., Lu, Y.: Supervised and traditional term weighting methods for automatic text categorization. IEEE TPAMI 31(4), 721\u2013735 (2009)","journal-title":"IEEE TPAMI"},{"key":"22_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1007\/3-540-39205-X_87","volume-title":"Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing","author":"Y Li","year":"2003","unstructured":"Li, Y.: Extended random sets for knowledge discovery in information systems. In: Wang, G., Liu, Q., Yao, Y., Skowron, A. (eds.) RSFDGrC 2003. LNCS (LNAI), vol. 2639, pp. 524\u2013532. Springer, Heidelberg (2003). doi: 10.1007\/3-540-39205-X_87"},{"issue":"6","key":"22_CR18","first-page":"1656","volume":"27","author":"Y Li","year":"2015","unstructured":"Li, Y., Algarni, A., Albathan, M., Shen, Y., Bijaksana, M.A.: Relevance feature discovery for text mining. IEEE TKDE 27(6), 1656\u20131669 (2015)","journal-title":"IEEE TKDE"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Liu, X., Croft, W.B.: Cluster-based retrieval using language models. In: SIGIR 2004, pp. 186\u2013193. ACM (2004)","DOI":"10.1145\/1008992.1009026"},{"key":"22_CR20","unstructured":"Macdonald, C., Ounis, I.: Global statistics in proximity weighting models. In: Web N-Gram Workshop, p. 30. Citeseer (2010)"},{"key":"22_CR21","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"CD Manning","year":"2008","unstructured":"Manning, C.D., Raghavan, P., Sch\u00fctze, H.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Maxwell, K.T., Croft, W.B.: Compact query term selection using topically related text. In: SIGIR 2013, pp. 583\u2013592. ACM (2013)","DOI":"10.1145\/2484028.2484096"},{"key":"22_CR23","unstructured":"McCallum, A.K.: Mallet: A machine learning for language toolkit (2002)"},{"key":"22_CR24","volume-title":"Theory of Random Sets","author":"I Molchanov","year":"2006","unstructured":"Molchanov, I.: Theory of Random Sets. Springer Science & Business Media, London (2006)"},{"key":"22_CR25","unstructured":"Rasmussen, M., Karypis, G.: gCLUTO: an interactive clustering, visualization, and analysis system. UMN-CS TR-04 21(7) (2004)"},{"key":"22_CR26","volume-title":"The Probabilistic Relevance Framework: BM25 and Beyond","author":"S Robertson","year":"2009","unstructured":"Robertson, S., Zaragoza, H.: The Probabilistic Relevance Framework: BM25 and Beyond. Now Publishers Inc., Breda (2009)"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Robertson, S.E., Soboroff, I.: The TREC 2002 filtering track report. In: TREC, vol. 2002, p. 5 (2002)","DOI":"10.6028\/NIST.SP.500-251.filtering-overview"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Savaresi, S.M., Boley, D.L.: On the performance of bisecting k-means and PDDP. In: ICDM 2001, pp. 1\u201314. SIAM (2001)","DOI":"10.1137\/1.9781611972719.5"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Soboroff, I., Robertson, S.: Building a filtering test collection for TREC 2002. In: SIGIR 2003, pp. 243\u2013250. ACM (2003)","DOI":"10.1145\/860435.860481"},{"key":"22_CR30","unstructured":"Steinbach, M., Karypis, G., Kumar, V., et al.: A comparison of document clustering techniques. In: KDD Workshop on Text Mining, vol. 400, Boston, pp. 525\u2013526 (2000)"},{"issue":"7","key":"22_CR31","first-page":"424","volume":"427","author":"M Steyvers","year":"2007","unstructured":"Steyvers, M., Griffiths, T.: Probabilistic topic models. Handb. Latent Semant. Anal. 427(7), 424\u2013440 (2007)","journal-title":"Handb. Latent Semant. Anal."},{"key":"22_CR32","unstructured":"Tagarelli, A., Karypis, G.: Document clustering: the next frontier. In: Data Clustering: Algorithms and Applications, p. 305. CRC Press (2013)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Tasci, S., Gungor, T.: LDA-based keyword selection in text categorization. In: ISCIS 2009, pp. 230\u2013235. IEEE (2009)","DOI":"10.1109\/ISCIS.2009.5291818"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., McCallum, A., Wei, X.: Topical n-grams: phrase and topic discovery, with an application to information retrieval. In: ICDM 2007, pp. 697\u2013702. IEEE (2007)","DOI":"10.1109\/ICDM.2007.86"},{"key":"22_CR35","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1007\/978-3-642-15246-7_28","volume-title":"PRICAI 2010: Trends in Artificial Intelligence","author":"Q Wu","year":"2010","unstructured":"Wu, Q., Ye, Y., Ng, M., Su, H., Huang, J.: Exploiting word cluster information for unsupervised feature selection. In: Zhang, B.-T., Orgun, M.A. (eds.) PRICAI 2010. LNCS (LNAI), vol. 6230, pp. 292\u2013303. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15246-7_28"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Phan, X.H., Horiguchi, S.: An efficient feature selection using hidden topic in text categorization. In: AINAW 2008, pp. 1223\u20131228. IEEE (2008)","DOI":"10.1109\/WAINA.2008.137"},{"issue":"1","key":"22_CR37","first-page":"30","volume":"24","author":"N Zhong","year":"2012","unstructured":"Zhong, N., Li, Y., Wu, S.T.: Effective pattern discovery for text mining. IEEE TKDE 24(1), 30\u201344 (2012)","journal-title":"IEEE TKDE"}],"container-title":["Lecture Notes in Computer Science","AI 2017: Advances in Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-63004-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T09:29:17Z","timestamp":1719307757000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-63004-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319630038","9783319630045"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-63004-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}