{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T21:52:24Z","timestamp":1759960344996},"publisher-location":"Berlin, Heidelberg","reference-count":32,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540714941"},{"type":"electronic","value":"9783540714965"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-71496-5_35","type":"book-chapter","created":{"date-parts":[[2007,6,4]],"date-time":"2007-06-04T12:47:15Z","timestamp":1180961235000},"page":"381-392","source":"Crossref","is-referenced-by-count":1,"title":["Entropy-Based Authorship Search in Large Document Collections"],"prefix":"10.1007","author":[{"given":"Ying","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Justin","family":"Zobel","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"35_CR1","unstructured":"Baayen, H., et al.: An experiment in authorship attribution. In: 6th JADT (2002)"},{"key":"35_CR2","volume-title":"Modern Information Retrieval","author":"R. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval. Addison-Wesley Longman, Amsterdam (May 1999)"},{"key":"35_CR3","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1162\/153244303322753625","volume":"3","author":"R. Bekkerman","year":"2003","unstructured":"Bekkerman, R., et al.: Distributional word clusters vs. words for text categorization. J. Mach. Learn. Res.\u00a03, 1183\u20131208 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Benedetto, D., Caglioti, E., Loreto, V.: Language trees and zipping. The American Physical Society\u00a088(4) (2002)","DOI":"10.1103\/PhysRevLett.88.048702"},{"issue":"2","key":"35_CR5","first-page":"9","volume":"16","author":"J.N.G. Binongo","year":"2003","unstructured":"Binongo, J.N.G.: Who wrote the 15th book of Oz? an application of multivariate statistics to authorship attribution. Computational Linguistics\u00a016(2), 9\u201317 (2003)","journal-title":"Computational Linguistics"},{"key":"35_CR6","doi-asserted-by":"publisher","first-page":"310","DOI":"10.3115\/981863.981904","volume-title":"Proc. 34th Annual Meeting of the Association for Computational Linguistics","author":"S.F. Chen","year":"1996","unstructured":"Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. In: Joshi, A., Palmer, M. (eds.) Proc. 34th Annual Meeting of the Association for Computational Linguistics, pp. 310\u2013318. Morgan Kaufmann, San Francisco (1996)"},{"key":"35_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-017-0171-6","volume-title":"Language Modeling for Information Retrieval","author":"W.B. Croft","year":"2003","unstructured":"Croft, W.B., Lafferty, J.: Language Modeling for Information Retrieval. Kluwer Academic Publishers, Norwell (2003)"},{"issue":"1-2","key":"35_CR8","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1023\/A:1023824908771","volume":"19","author":"J. Diederich","year":"2003","unstructured":"Diederich, J., et al.: Authorship attribution with support vector machines. Applied Intelligence\u00a019(1-2), 109\u2013123 (2003)","journal-title":"Applied Intelligence"},{"key":"35_CR9","unstructured":"Goodman, J.: Extended comment on language trees and zipping (2002)"},{"issue":"3","key":"35_CR10","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/0306-4573(94)00047-7","volume":"31","author":"D. Harman","year":"1995","unstructured":"Harman, D.: Overview of the second text retrieval conf (TREC-2). Information Processing & Management\u00a031(3), 271\u2013289 (1995)","journal-title":"Information Processing & Management"},{"key":"35_CR11","first-page":"197","volume":"20","author":"D. Heckerman","year":"1995","unstructured":"Heckerman, D., Geiger, D., Chickering, D.: Learning bayesian networks: the combination of knowledge and statistical data. Machine Learning\u00a020, 197\u2013243 (1995)","journal-title":"Machine Learning"},{"key":"35_CR12","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1145\/564376.564385","volume-title":"Proc. 25th ACM SIGIR Conf. on Research and Development in Information Retrieval","author":"D. Hiemstra","year":"2002","unstructured":"Hiemstra, D.: Term-specific smoothing for the language modeling approach to information retrieval: the importance of a query term. In: Proc. 25th ACM SIGIR Conf. on Research and Development in Information Retrieval, pp. 35\u201341. ACM Press, New York (2002)"},{"issue":"3","key":"35_CR13","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1023\/A:1017549100097","volume":"35","author":"D.I. Holmes","year":"2001","unstructured":"Holmes, D.I., Robertson, M., Paez, R.: Stephen Crane and the New York Tribune: A case study in traditional and non-traditional authorship attribution. Computers and the Humanities\u00a035(3), 315\u2013331 (2001)","journal-title":"Computers and the Humanities"},{"key":"35_CR14","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1093\/llc\/16.4.421","volume":"16","author":"D.L. Hoover","year":"2001","unstructured":"Hoover, D.L.: Statistical stylistics and authorship attribution: an empirical investigation. Literary and Linguistic Computing\u00a016, 421\u2013444 (2001)","journal-title":"Literary and Linguistic Computing"},{"key":"35_CR15","unstructured":"Juola, P., Baayen, H.: A controlled-corpus experiment in authorship identification by cross-entropy. Literary and Linguistic Computing (2003)"},{"key":"35_CR16","unstructured":"Kaster, A., Siersdorfer, S., Weikum, G.: Combining text and linguistic doument representations for authorship attribution. In: SIGIR workshop: Stylistic Analysis of Text For Information Access (August 2005)"},{"issue":"4","key":"35_CR17","first-page":"229","volume":"16","author":"D.V. Khmelev","year":"2002","unstructured":"Khmelev, D.V., Tweedie, F.: Using markov chains for identification of writers. Literary and Linguistic Computing\u00a016(4), 229\u2013307 (2002)","journal-title":"Literary and Linguistic Computing"},{"key":"35_CR18","unstructured":"Koppel, M., Schler, J.: Exploiting stylistic idiosyncrasies for authorship attribution. In: IJCAI\u201903 Workshop on Computational Approaches to Style Analysis and Synthesis (2003)"},{"key":"35_CR19","volume-title":"Proc. 21st Int. Conf. on Machine Learning","author":"M. Koppel","year":"2004","unstructured":"Koppel, M., Schler, J.: Authorship verification as a one-class classification problem. In: Proc. 21st Int. Conf. on Machine Learning, ACM Press, New York (2004)"},{"key":"35_CR20","first-page":"194","volume-title":"Proc. 27th ACM SIGIR Conf. on Research and Development in Information Retrieval","author":"O. Kurland","year":"2004","unstructured":"Kurland, O., Lee, L.: Corpus structure, language models, and ad hoc information retrieval. In: Proc. 27th ACM SIGIR Conf. on Research and Development in Information Retrieval, pp. 194\u2013201. ACM Press, New York (2004)"},{"issue":"1","key":"35_CR21","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1145\/595576.595579","volume":"1","author":"Y.S. Lai","year":"2002","unstructured":"Lai, Y.S., Wu, C.H.: Meaningful term extraction and discriminative term selection in text categorization via unknown-word methodology. ACM Transactions on Asian Language Information Processing\u00a01(1), 34\u201364 (2002)","journal-title":"ACM Transactions on Asian Language Information Processing"},{"key":"35_CR22","first-page":"361","volume":"5","author":"D.D. Lewis","year":"2004","unstructured":"Lewis, D.D., et al.: Rcv1: A new benchmark collection for text categorization research. J. Mach. Learn. Res.\u00a05, 361\u2013397 (2004)","journal-title":"J. Mach. Learn. Res."},{"key":"35_CR23","volume-title":"Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond","author":"B. Scholkopf","year":"2002","unstructured":"Scholkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond. MIT Press, Cambridge (2002)"},{"issue":"6","key":"35_CR24","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1016\/S0306-4573(00)00015-7","volume":"36","author":"K. Spark Jones","year":"2000","unstructured":"Spark Jones, K., Walker, S., Robertson, S.E.: A probabilistic model of information retrieval: development and comparative experiments. Inf. Process. Manage.\u00a036(6), 779\u2013840 (2000)","journal-title":"Inf. Process. Manage."},{"issue":"2","key":"35_CR25","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1023\/A:1002681919510","volume":"35","author":"E. Stamatatos","year":"2001","unstructured":"Stamatatos, E., Fakotakis, N., Kokkinakis, G.: Computer-based authorship attribution without lexical measures. Computers and the Humanities\u00a035(2), 193\u2013214 (2001)","journal-title":"Computers and the Humanities"},{"key":"35_CR26","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1145\/383952.383975","volume-title":"Proc. 24th ACM SIGIR Conf. on Research and Development in Information Retrieval","author":"Y.M. Yang","year":"2001","unstructured":"Yang, Y.M.: A study on thresholding strategies for text categorization. In: Proc. 24th ACM SIGIR Conf. on Research and Development in Information Retrieval, pp. 137\u2013145. ACM Press, New York (2001)"},{"issue":"2","key":"35_CR27","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1145\/984321.984322","volume":"22","author":"C.X. Zhai","year":"2004","unstructured":"Zhai, C.X., Lafferty, J.: A study of smoothing methods for language models applied to information retrieval. ACM Transaction on Information System\u00a022(2), 179\u2013214 (2004)","journal-title":"ACM Transaction on Information System"},{"key":"35_CR28","first-page":"174","volume-title":"Proc. 2nd AIRS Asian Information Retrieval Symposium","author":"Y. Zhao","year":"2005","unstructured":"Zhao, Y., Zobel, J.: Effective authorship attribution using function word. In: Proc. 2nd AIRS Asian Information Retrieval Symposium, pp. 174\u2013190. Springer, Heidelberg (2005)"},{"key":"35_CR29","unstructured":"Zhao, Y., Zobel, J.: Search with style: authorship attribution in classic literature. In: Proc. 30th ACSC Thirtieth Australasian Computer Science Conference, ACM Press, New York (to appear, 2007)"},{"key":"35_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/11880592_8","volume-title":"Information Retrieval Technology","author":"Y. Zhao","year":"2006","unstructured":"Zhao, Y., Zobel, J., Vines, P.: Using relative entropy for authorship attribution. In: Ng, H.T., et al. (eds.) AIRS 2006. LNCS, vol.\u00a04182, pp. 92\u2013105. Springer, Heidelberg (2006)"},{"issue":"1","key":"35_CR31","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1145\/281250.281256","volume":"32","author":"J. Zobel","year":"1998","unstructured":"Zobel, J., Moffat, A.: Exploring the similarity space. ACM SIGIR Forum\u00a032(1), 18\u201334 (1998)","journal-title":"ACM SIGIR Forum"},{"key":"35_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1132956.1132959","volume":"38","author":"J. Zobel","year":"2006","unstructured":"Zobel, J., Moffat, A.: Inverted files for text search engines. ACM Computing Surveys\u00a038, 1\u201356 (2006)","journal-title":"ACM Computing Surveys"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-71496-5_35.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T05:21:54Z","timestamp":1605763314000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-71496-5_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540714941","9783540714965"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-71496-5_35","relation":{},"subject":[]}}