{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:40:41Z","timestamp":1743118841263,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":27,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642247637"},{"type":"electronic","value":"9783642247644"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[[2011]]},"DOI":"10.1007\/978-3-642-24764-4_18","type":"book-chapter","created":{"date-parts":[[2011,11,9]],"date-time":"2011-11-09T01:21:39Z","timestamp":1320801699000},"page":"198-209","source":"Crossref","is-referenced-by-count":2,"title":["Investigating the Statistical Properties of User-Generated Documents"],"prefix":"10.1007","author":[{"given":"Giacomo","family":"Inches","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark James","family":"Carman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Crestani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Java, A., Song, X., Finin, T., Tseng, B.: Why we twitter: understanding microblogging usage and communities. In: WebKDD\/SNA-KDD 2007: Proceedings of the 9th WebKDD and 1st SNA-KDD 2007 Workshop on Web Mining and Social Network Analysis, pp. 56\u201365. ACM, New York (2007)","DOI":"10.1145\/1348549.1348556"},{"key":"18_CR2","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1145\/1397735.1397741","volume-title":"WOSP 2008: Proceedings of the First Workshop on Online Social Networks","author":"B. Krishnamurthy","year":"2008","unstructured":"Krishnamurthy, B., Gill, P., Arlitt, M.: A few chirps about twitter. In: WOSP 2008: Proceedings of the First Workshop on Online Social Networks, pp. 19\u201324. ACM, New York (2008)"},{"issue":"5","key":"18_CR3","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1108\/14684520610706398","volume":"30","author":"S.C.H. Haichao Dong","year":"2006","unstructured":"Haichao Dong, S.C.H., He, Y.: Structural analysis of chat messages for topic detection. Online Information Review\u00a030(5), 496\u2013516 (2006)","journal-title":"Online Information Review"},{"key":"18_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1007\/11890393_29","volume-title":"Advances in Information Systems","author":"T. Kucukyilmaz","year":"2006","unstructured":"Kucukyilmaz, T., Cambazoglu, B., Aykanat, C., Can, F.: Chat mining for gender prediction. In: Yakhno, T., Neuhold, E.J. (eds.) ADVIS 2006. LNCS, vol.\u00a04243, pp. 274\u2013283. Springer, Heidelberg (2006)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Medina, E.W.: Military textual analysis and chat research. In: International Conference on Semantic Computing, pp. 569\u2013572 (2008)","DOI":"10.1109\/ICSC.2008.57"},{"key":"18_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1007\/978-3-540-77094-7_63","volume-title":"Asian Digital Libraries. Looking Back 10 Years and Forging New Frontiers","author":"R. Bache","year":"2007","unstructured":"Bache, R., Crestani, F., Canter, D., Youngs, D.: Mining police digital archives to link criminal styles with offender characteristics. In: Goh, D.H.-L., Cao, T.H., S\u00f8lvberg, I.T., Rasmussen, E. (eds.) ICADL 2007. LNCS, vol.\u00a04822, pp. 493\u2013494. Springer, Heidelberg (2007)"},{"key":"18_CR7","unstructured":"Yin, D., Xue, Z., Hong, L., Davison, B.D., Kontostathis, A., Edwards, L.: Detection of harassment on web 2.0. In: CAW 2.0 2009: Proceedings of the 1st Content Analysis in Web 2.0 Workshop, Madrid, Spain (2009)"},{"issue":"6","key":"18_CR8","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1007\/s11767-006-0044-2","volume":"23","author":"H. Qi","year":"2006","unstructured":"Qi, H., Li, M., Gao, J., Li, S.: Information retrieval for short documents. Journal of Electronics (China)\u00a023(6), 933\u2013936 (2006)","journal-title":"Journal of Electronics (China)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Wang, F., Greer, J.: Retrieval of short documents from discussion forums. In: Advances in Artificial Intelligence, pp. 339\u2013343 (2002)","DOI":"10.1007\/3-540-47922-8_30"},{"key":"18_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-642-12275-0_68","volume-title":"Advances in Information Retrieval","author":"G. Inches","year":"2010","unstructured":"Inches, G., Carman, M., Crestani, F.: Statistics of online user-generated short documents. In: Gurrin, C., He, Y., Kazai, G., Kruschwitz, U., Little, S., Roelleke, T., R\u00fcger, S., van Rijsbergen, K. (eds.) ECIR 2010. LNCS, vol.\u00a05993, pp. 649\u2013652. Springer, Heidelberg (2010)"},{"issue":"10","key":"18_CR11","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1016\/j.patrec.2009.04.001","volume":"30","author":"M. Carullo","year":"2009","unstructured":"Carullo, M., Binaghi, E., Gallo, I.: An online document clustering technique for short web contents. Pattern Recognition Letters\u00a030(10), 870\u2013876 (2009)","journal-title":"Pattern Recognition Letters"},{"key":"18_CR12","first-page":"206","volume-title":"WI 2004: Proceedings of the 2004 IEEE\/WIC\/ACM International Conference on Web Intelligence","author":"V.H. Tuulos","year":"2004","unstructured":"Tuulos, V.H., Tirri, H.: Combining topic models and social networks for chat data mining. In: WI 2004: Proceedings of the 2004 IEEE\/WIC\/ACM International Conference on Web Intelligence, pp. 206\u2013213. IEEE Computer Society, Washington, DC, USA (2004)"},{"key":"18_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/978-3-540-71496-5_5","volume-title":"Advances in Information Retrieval","author":"D. Metzler","year":"2007","unstructured":"Metzler, D., Dumais, S., Meek, C.: Similarity measures for short segments of text. In: Amati, G., Carpineto, C., Romano, G. (eds.) ECiR 2007. LNCS, vol.\u00a04425, pp. 16\u201327. Springer, Heidelberg (2007)"},{"issue":"4","key":"18_CR14","doi-asserted-by":"publisher","first-page":"5372","DOI":"10.1371\/journal.pone.0005372","volume":"4","author":"M. Serrano","year":"2009","unstructured":"Serrano, M., Flammini, A., Menczer, F.: Modeling statistical properties of written text. PLoS ONE\u00a04(4), e5372 (2009)","journal-title":"PLoS ONE"},{"key":"18_CR15","volume-title":"Modern Information Retrieval","author":"R.A. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates, R.A., Ribeiro-Neto, B.: Modern Information Retrieval. Addison-Wesley Longman Publishing Co., Inc., Boston (1999)"},{"key":"18_CR16","volume-title":"Foundations of Statistical Natural Language Processing","author":"C.D. Manning","year":"1999","unstructured":"Manning, C.D., Sch\u00fctze, H.: Foundations of Statistical Natural Language Processing. MIT Press, Cambridge (1999)"},{"key":"18_CR17","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1145\/564376.564430","volume-title":"SIGIR 2002: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"J. Allan","year":"2002","unstructured":"Allan, J., Raghavan, H.: Using part-of-speech patterns to reduce query ambiguity. In: SIGIR 2002: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 307\u2013314. ACM, New York (2002)"},{"key":"18_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1007\/978-3-642-00958-7_37","volume-title":"Advances in Information Retrieval","author":"C. Lioma","year":"2009","unstructured":"Lioma, C., Blanco, R.: Part of speech based term weighting for information retrieval. In: Boughanem, M., Berrut, C., Mothe, J., Soule-Dupuy, C. (eds.) ECIR 2009. LNCS, vol.\u00a05478, pp. 412\u2013423. Springer, Heidelberg (2009)"},{"key":"18_CR19","doi-asserted-by":"publisher","first-page":"531","DOI":"10.3115\/1273073.1273142","volume-title":"Proceedings of the COLING\/ACL on Main Conference Poster Sessions","author":"C. Lioma","year":"2006","unstructured":"Lioma, C., Ounis, I.: Examining the content load of part of speech blocks for information retrieval. In: Proceedings of the COLING\/ACL on Main Conference Poster Sessions, pp. 531\u2013538. Association for Computational Linguistics, Morristown (2006)"},{"key":"18_CR20","unstructured":"Codina, J., Kaltenbrunner, A., Grivolla, J., Banchs, R.E., Baeza-Yates, R.: Content analysis in web 2.0. 18th International World Wide Web Conference (April 2009)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Ramage, D., Dumais, S., Liebling, D.: Characterizing microblogs with topic models. In: ICWSM (2010)","DOI":"10.1609\/icwsm.v4i1.14026"},{"key":"18_CR22","unstructured":"Cunningham, H., Maynard, D., Bontcheva, K., Tablan, V.: GATE: A framework and graphical development environment for robust NLP tools and applications. In: Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics (2002)"},{"issue":"1","key":"18_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00194ED1V01Y200905HLT003","volume":"2","author":"G. Wilcock","year":"2009","unstructured":"Wilcock, G.: Introduction to linguistic annotation and text analytics. Synthesis Lectures on Human Language Technologies\u00a02(1), 1\u2013159 (2009)","journal-title":"Synthesis Lectures on Human Language Technologies"},{"key":"18_CR24","unstructured":"Balog, K., Bron, M., He, J., Hofmann, K., Meij, E.J., de Rijke, M., Tsagkias, E., Weerkamp, W.: The university of amsterdam at trec 2009: Blog, web, entity, and relevance feedback. In: TREC 2009 Working Notes. NIST (November 2009)"},{"issue":"1","key":"18_CR25","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/1842890.1842899","volume":"44","author":"C. Macdonald","year":"2010","unstructured":"Macdonald, C., Santos, R.L., Ounis, I., Soboroff, I.: Blog track research at trec. SIGIR Forum\u00a044(1), 58\u201375 (2010)","journal-title":"SIGIR Forum"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"O\u2019Connor, B., Balasubramanyan, R., Routledge, B.R., Smith, N.A.: From tweets to polls: Linking text sentiment to public opinion time series. In: Proceedings of the International AAAI Conference on Weblogs and Social Media (2010)","DOI":"10.1609\/icwsm.v4i1.14031"},{"key":"18_CR27","unstructured":"Ku, L.W., Ke, K.J., Chen, H.H.: Opinion analysis on caw 2.0 datasets. In: CAW 2.0 2009: Proceedings of the 1st Content Analysis in Web 2.0 Workshop, Madrid, Spain (2009)"}],"container-title":["Lecture Notes in Computer Science","Flexible Query Answering Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-24764-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,11]],"date-time":"2023-06-11T00:44:06Z","timestamp":1686444246000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-24764-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642247637","9783642247644"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-24764-4_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}