{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T05:55:09Z","timestamp":1740808509715,"version":"3.38.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2010,12,15]],"date-time":"2010-12-15T00:00:00Z","timestamp":1292371200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2010,12,15]],"date-time":"2010-12-15T00:00:00Z","timestamp":1292371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Inf Retrieval"],"published-print":{"date-parts":[[2011,6]]},"DOI":"10.1007\/s10791-010-9160-6","type":"journal-article","created":{"date-parts":[[2010,12,15]],"date-time":"2010-12-15T15:14:10Z","timestamp":1292426050000},"page":"215-236","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A unified representation of web logs for mining applications"],"prefix":"10.1007","volume":"14","author":[{"given":"Michelangelo","family":"Diligenti","sequence":"first","affiliation":[]},{"given":"Marco","family":"Gori","sequence":"additional","affiliation":[]},{"given":"Marco","family":"Maggini","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,12,15]]},"reference":[{"key":"9160_CR1","doi-asserted-by":"crossref","unstructured":"Adomavicius, G., & Tuzhilin, A. (2005). Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Engineering , 734\u2013749.","DOI":"10.1109\/TKDE.2005.99"},{"key":"9160_CR2","doi-asserted-by":"crossref","unstructured":"Baeza-Yates, R., Hurtado, C., & Mendoza, M. (2004). Query recommendation using query logs in search engines. In International workshop on clustering information over the web (ClustWeb, in conjunction with EDBT), Creete, Greece, March (to flapper in LNCS). Springer.","DOI":"10.1007\/978-3-540-30192-9_58"},{"key":"9160_CR3","doi-asserted-by":"crossref","unstructured":"Baeza-Yates, R., Hurtado, C., & Mendoza, M. (2005a). Query recommendation using query logs in search engines. In Proceedings of current trends in database technology\u2014EDBT 2004 workshops (pp. 395\u2013397). Springer.","DOI":"10.1007\/978-3-540-30192-9_58"},{"key":"9160_CR4","doi-asserted-by":"crossref","unstructured":"Baeza-Yates, R., Hurtado, C., & Mendoza, M. (2005b). Modeling user search behavior. In 3rd Latin American Web Congress (LA-WEB) pp. 242\u2013251.","DOI":"10.1109\/LAWEB.2005.23"},{"key":"9160_CR5","doi-asserted-by":"crossref","unstructured":"Baeza-Yates, R., & Tiberi, A. (2007). Extracting semantic relations from query logs. In Proceedings of the 13th ACM SIGKDD international conference on knowledge discovery and data mining (p. 85). ACM.","DOI":"10.1145\/1281192.1281204"},{"key":"9160_CR6","doi-asserted-by":"crossref","unstructured":"Baluja, S., Seth, R., Sivakumar, D., Jing, Y., Yagnik, J., Kumar, S., Ravichandran, D., & Aly, M. (2008). Video suggestion and discovery for Youtube: Taking random walks through the view graph. In Proceedings of the 17th international conference on world wide web (pp. 895\u2013904). ACM.","DOI":"10.1145\/1367497.1367618"},{"key":"9160_CR7","doi-asserted-by":"crossref","unstructured":"Beeferman, D., & Berger, A. (2000). Agglomerative clustering of a search engine query log. In Sixth ACM international conference on knowledge discovery and data mining (SIGKDD) (pp. 407\u2013416). New York, NY: ACM.","DOI":"10.1145\/347090.347176"},{"key":"9160_CR8","volume-title":"Survey of text mining II: Clustering, classification, and retrieval","author":"M. Berry","year":"2007","unstructured":"Berry, M., & Castellanos, M. (2007). Survey of text mining II: Clustering, classification, and retrieval. New York: Springer New York Inc."},{"key":"9160_CR9","doi-asserted-by":"crossref","unstructured":"Boldi, P., Bonchi, F., Castillo, C., Donato, D., Gionis, A., & Vigna, S. (2008). The query-flow graph: Model and applications. In CIKM \u201908: Proceedings of the 17th ACM conference on information and knowledge mining (pp. 609\u2013618). New York, NY, USA: ACM.","DOI":"10.1145\/1458082.1458163"},{"issue":"2","key":"9160_CR10","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/792550.792552","volume":"36","author":"A. Broder","year":"2002","unstructured":"Broder, A. (2002). A taxonomy of web search. SIGIR Forum, 36(2), 3\u201310.","journal-title":"SIGIR Forum"},{"issue":"8-13","key":"9160_CR11","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/S0169-7552(97)00031-7","volume":"29","author":"A. Broder","year":"1997","unstructured":"Broder, A., Glassman, S., Manasse, M., & Zweig, G. (1997). Syntactic clustering of the web. Computer Networks and ISDN Systems, 29(8\u201313), 1157\u20131166.","journal-title":"Computer Networks and ISDN Systems"},{"key":"9160_CR12","doi-asserted-by":"crossref","unstructured":"Burges, C., Shaked, T., Renshaw, E., Lazier, A., Deeds, M., Hamilton, N., & Hullender, G. (2005). Learning to rank using gradient descent. In Proceedings of the 22nd international conference on machine learning (pp. 96). ACM.","DOI":"10.1145\/1102351.1102363"},{"issue":"3","key":"9160_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1541880.1541884","volume":"41","author":"C. Carpineto","year":"2009","unstructured":"Carpineto, C., Osi\u0144ski, S., Romano, G., & Weiss, D. (2009). A survey of web clustering engines. ACM Computer Survey, 41(3), 1\u201338.","journal-title":"ACM Computer Survey"},{"key":"9160_CR14","doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., Joshi, M., & Tawde, V. (2001). Enhanced topic distillation using text, markup tags, and hyperlinks. In Proceedings of the 24th annual international ACM SIGIR conference on research and development in information retrieval (pp. 208\u2013216), New York, NY, USA: ACM.","DOI":"10.1145\/383952.383990"},{"issue":"4","key":"9160_CR15","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MCSE.2009.120","volume":"11","author":"J. Cohen","year":"2009","unstructured":"Cohen, J. (2009). Graph twiddling in a MapReduce world. Computing in Science & Engineering, 11(4), 29\u201341.","journal-title":"Computing in Science & Engineering"},{"key":"9160_CR16","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1613\/jair.587","volume":"10","author":"W. Cohen","year":"1999","unstructured":"Cohen, W., Schapire, R., & Singer, Y. (1999). Learning to order things. The Journal of Artificial Intelligence Research, 10, 243\u2013270.","journal-title":"The Journal of Artificial Intelligence Research"},{"key":"9160_CR17","doi-asserted-by":"crossref","unstructured":"Collins-Thompson, K., & Callan, J. (2005). Query expansion using random walk models. In Proceedings of the 14th ACM international conference on information and knowledge management (pp. 704\u2013711). New York, NY, USA: ACM.","DOI":"10.1145\/1099554.1099727"},{"key":"9160_CR18","doi-asserted-by":"crossref","unstructured":"Cooper, J., Coden, A., & Brown, E. (2002). Detecting similar documents using salient terms. In Proceedings of the eleventh international conference on information and knowledge management (p. 251). ACM, 2002.","DOI":"10.1145\/584792.584835"},{"key":"9160_CR19","doi-asserted-by":"crossref","unstructured":"Craswell, N., & Szummer, M. (2007). Random walks on the click graph. In 30th annual international ACM SIGIR conference on research and development in information retrieval (pp. 239\u2013246). New York, NY, USA: ACM Press.","DOI":"10.1145\/1277741.1277784"},{"issue":"1","key":"9160_CR20","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J. Dean","year":"2008","unstructured":"Dean, J., & Ghemawat, S. (2008). MapReduce: Simplified data processing on large clusters. Communications of the ACM, 51(1), 107\u2013113.","journal-title":"Communications of the ACM"},{"key":"9160_CR21","doi-asserted-by":"crossref","unstructured":"Donato, D., & Gionis, A. (2010). A survey of graph mining for web applications. Managing and Mining Graph Data, 455\u2013485.","DOI":"10.1007\/978-1-4419-6045-0_15"},{"issue":"7","key":"9160_CR22","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1093\/nar\/30.7.1575","volume":"30","author":"A. Enright","year":"2002","unstructured":"Enright, A., Van Dongen, S., & Ouzounis, C. (2002). An efficient algorithm for large-scale detection of protein families. Nucleic Acids Research, 30(7), 1575.","journal-title":"Nucleic Acids Research"},{"issue":"2","key":"9160_CR23","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1002\/spe.829","volume":"38","author":"P. Ferragina","year":"2008","unstructured":"Ferragina, P., & Gulli, A. (2008). A personalized search engine based on web-snippet hierarchical clustering. Software: Practice and Experience, 38(2), 189\u2013225.","journal-title":"Software: Practice and Experience"},{"issue":"3","key":"9160_CR24","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1109\/2.989932","volume":"35","author":"G. Flake","year":"2002","unstructured":"Flake, G., Lawrence, S., Giles, C., & Coetzee, F. (2002). Self-organization and identification of web communities. IEEE Computer, 35(3), 66\u201370.","journal-title":"IEEE Computer"},{"key":"9160_CR25","doi-asserted-by":"crossref","unstructured":"F\u00fcrnkranz, J. (1999). Exploiting structural information for text classification on the WWW. Advances in Intelligent Data Analysis, 487\u2013497.","DOI":"10.1007\/3-540-48412-4_41"},{"issue":"5","key":"9160_CR26","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1016\/S0306-4573(01)00060-7","volume":"38","author":"D. He","year":"2002","unstructured":"He, D., G\u00f6ker, A., & Harper, D. (2002) Combining evidence for automatic web session identification. Information Processing and Management, 38(5), 727\u2013742.","journal-title":"Information Processing and Management"},{"issue":"1","key":"9160_CR27","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/S0167-9473(02)00070-1","volume":"41","author":"H. HeX. Zha","year":"2002","unstructured":"He, X., Zha, H., HQ, D., et\u00a0al. (2002). Web document clustering using hyperlink structures. Computational Statistics & Data Analysis, 41(1), 19\u201345.","journal-title":"Computational Statistics & Data Analysis"},{"key":"9160_CR28","doi-asserted-by":"crossref","unstructured":"Hotho, A., J\u00e4schke, R., Schmitz, C., & Stumme, G. (2006). Information retrieval in folksonomies: Search and ranking. The Semantic Web: Research and Applications, 411\u2013426.","DOI":"10.1007\/11762256_31"},{"issue":"14","key":"9160_CR29","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1002\/asi.20084","volume":"55","author":"X. Huang","year":"2004","unstructured":"Huang, X., Peng, F., An, A., & Schuurmans, D. (2004) Dynamic web log session identification with statistical language models. Journal of the American Society for Information Science and Technology, 55(14), 1290\u20131303.","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"5","key":"9160_CR30","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1002\/asi.20555","volume":"58","author":"B. Jansen","year":"2007","unstructured":"Jansen, B., Spink, A., & Koshman, S. (2007). Web searcher interaction with the Dogpile.com metasearch engine. Journal of the American Society for Information Science and Technology, 58(5), 744\u2013755.","journal-title":"Journal of the American Society for Information Science and Technology"},{"key":"9160_CR31","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/BFb0026683","volume":"98","author":"T. Joachims","year":"1998","unstructured":"Joachims, T. (1998). Text categorization with support vector machines: Learning with many relevant features. Machine Learning: ECML-98, 137\u2013142.","journal-title":"Machine Learning: ECML"},{"key":"9160_CR32","doi-asserted-by":"crossref","unstructured":"Jones, R., Rey, B., Madani, O., & Greiner, W. (2006). Generating query substitutions. In Proceedings of the 15th international conference on world wide web (pp. 387\u2013396). New York, NY, USA: ACM.","DOI":"10.1145\/1135777.1135835"},{"issue":"3","key":"9160_CR33","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1561\/1500000016","volume":"3","author":"T.-Y. Liu","year":"2009","unstructured":"Liu, T. -Y. (2009). Learning to rank for information retrieval. Foundations and Trends in Information Retrieval, 3(3), 225\u2013331.","journal-title":"Foundations and Trends in Information Retrieval"},{"key":"9160_CR34","doi-asserted-by":"crossref","unstructured":"Papadimitriou, S., & Sun, J. (2008) Disco: Distributed co-clustering with MapReduce: A case study towards petabyte-scale end-to-end mining. In Eighth IEEE international conference on data mining, 2008, ICDM\u201908 (pp. 512\u2013521).","DOI":"10.1109\/ICDM.2008.142"},{"issue":"4","key":"9160_CR35","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1023\/A:1026238916441","volume":"13","author":"D. Pierrakos","year":"2003","unstructured":"Pierrakos, D., Paliouras, G., Papatheodorou, C., & Spyropoulos, C. (2003). Web usage mining as a tool for personalization: A survey. User Modeling and User-Adapted Interaction, 13(4), 311\u2013372.","journal-title":"User Modeling and User-Adapted Interaction"},{"key":"9160_CR36","doi-asserted-by":"crossref","unstructured":"Radlinski, F., & Joachims, T. (2005). Query chains: Learning to rank from implicit feedback. In KDD \u201905: Proceedings of the eleventh ACM SIGKDD international conference on knowledge discovery in data mining (pp. 239\u2013248). New York, NY, USA: ACM.","DOI":"10.1145\/1081870.1081899"},{"key":"9160_CR37","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4175.001.0001","volume-title":"Learning with Kernels","author":"B. Scholkopf","year":"2001","unstructured":"Scholkopf, B., & Smola. A. J. (2001). Learning with Kernels. Cambridge, MA, USA: MIT Press."},{"issue":"1","key":"9160_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"F. Sebastiani","year":"2002","unstructured":"Sebastiani, F. (2002). Machine learning in automated text categorization. ACM Computing Surveys (CSUR), 34,(1), 1\u201347.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"9160_CR39","volume-title":"Non-negative matrices and Markov chains","author":"E. Seneta","year":"2006","unstructured":"Seneta, E. (2006). Non-negative matrices and Markov chains. Berlin: Springer."},{"key":"9160_CR40","doi-asserted-by":"crossref","unstructured":"Szummer, M., & Craswell, N. (2008). Behavioral classification on the click graph. In WWW \u201908: Proceedings of the 17th international conference on world wide web (pp. 1241\u20131242). New York, NY, USA: ACM.","DOI":"10.1145\/1367497.1367746"},{"key":"9160_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Y., & Kitsuregawa, M. (2002). On combining link and contents information for web page clustering. In Database and expert systems applications (pp. 487\u2013566). Berlin: Springer.","DOI":"10.1007\/3-540-46146-9_89"},{"key":"9160_CR42","doi-asserted-by":"crossref","unstructured":"Wen, J.-R., Nie, J.-Y., & Zhang, H.-J. (2001). Clustering user queries of a search engine. In WWW \u201901: Proceedings of the 10th international conference on world wide web (pp. 162\u2013168). New York, NY, USA: ACM Press.","DOI":"10.1145\/371920.371974"},{"key":"9160_CR43","doi-asserted-by":"crossref","unstructured":"Zamir, O., & Etzioni, O. (1998). Web document clustering: A feasibility demonstration. In Proceedings of the 21st annual international ACM SIGIR conference on research and development in information retrieval (pp. 46\u201354). ACM.","DOI":"10.1145\/290941.290956"},{"key":"9160_CR44","doi-asserted-by":"crossref","unstructured":"Zeng, H., He, Q., Chen, Z., Ma, W., & Ma, J. (2004). Learning to cluster web search results. In Proceedings of the 27th annual international ACM SIGIR conference on research and development in information retrieval (p. 217). ACM.","DOI":"10.1145\/1008992.1009030"},{"key":"9160_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Z., & Nasraoui, O. (2006). Mining search engine query logs for query recommendation. In Proceedings of the 15th international conference on world wide web (p. 1040). ACM.","DOI":"10.1145\/1135777.1136004"},{"key":"9160_CR46","unstructured":"Zhou, D., & Scholkopf, B. (2004). A regularization framework for learning from graph data. In ICML workshop on statistical relational learning and Its connections to other fields (pp. 132\u2013137)."},{"key":"9160_CR47","first-page":"321","volume":"16","author":"D. Zhou","year":"2004","unstructured":"Zhou, D., Bousquet, O., Lal, T., Weston, J., & Scholkopf, B. (2004). Learning with local and global consistency. Advances in Neural Information Processing Systems, 16, 321\u2013328.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"9160_CR48","first-page":"1633","volume":"17","author":"D. Zhou","year":"2005","unstructured":"Zhou, D., Scholkopf, B., & Hofmann, T. (2005). Semi-supervised learning on directed graphs. Advances in Neural Information Processing Systems, 17, 1633\u20131640.","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-010-9160-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-010-9160-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-010-9160-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-010-9160-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T21:00:02Z","timestamp":1740776402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-010-9160-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12,15]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2011,6]]}},"alternative-id":["9160"],"URL":"https:\/\/doi.org\/10.1007\/s10791-010-9160-6","relation":{},"ISSN":["1386-4564","1573-7659"],"issn-type":[{"type":"print","value":"1386-4564"},{"type":"electronic","value":"1573-7659"}],"subject":[],"published":{"date-parts":[[2010,12,15]]},"assertion":[{"value":"30 April 2010","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2010","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 December 2010","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}