{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:31:55Z","timestamp":1768249915002,"version":"3.49.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319060279","type":"print"},{"value":"9783319060286","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-06028-6_26","type":"book-chapter","created":{"date-parts":[[2014,3,24]],"date-time":"2014-03-24T09:24:27Z","timestamp":1395653067000},"page":"311-322","source":"Crossref","is-referenced-by-count":29,"title":["CiteSeer x : A Scholarly Big Dataset"],"prefix":"10.1007","author":[{"given":"Cornelia","family":"Caragea","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alina","family":"Ciobanu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle","family":"Williams","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Fern\u00e1ndez-Ram\u00edrez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Hsuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lee","family":"Giles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Giles, C.L., Bollacker, K., Lawrence, S.: Citeseer: An automatic citation indexing system. In: Digital Libraries 1998, pp. 89\u201398 (1998)","DOI":"10.1145\/276675.276685"},{"key":"26_CR2","unstructured":"Lu, Q., Getoor, L.: Link-based classification. In: ICML (2003)"},{"key":"26_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/3-540-36618-0_24","volume-title":"Advances in Information Retrieval","author":"F. Peng","year":"2003","unstructured":"Peng, F., Schuurmans, D.: Combining naive bayes and n-gram language models for text classification. In: Sebastiani, F. (ed.) ECIR 2003. LNCS, vol.\u00a02633, pp. 335\u2013350. Springer, Heidelberg (2003)"},{"key":"26_CR4","unstructured":"Caragea, C., Silvescu, A., Kataria, S., Caragea, D., Mitra, P.: Classifying scientific publications using abstract features. In: SARA (2011)"},{"issue":"3","key":"26_CR5","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1609\/aimag.v29i3.2157","volume":"29","author":"P. Sen","year":"2008","unstructured":"Sen, P., Namata, G.M., Bilgic, M., Getoor, L., Gallagher, B., Eliassi-Rad, T.: Collective classification in network data. AI Magazine\u00a029(3), 93\u2013106 (2008)","journal-title":"AI Magazine"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Zhou, D., Zhu, S., Yu, K., Song, X., Tseng, B.L., Zha, H., Giles, C.L.: Learning multiple graphs for document recommendations. In: Proc. of WWW 2008 (2008)","DOI":"10.1145\/1367497.1367517"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Caragea, C., Silvescu, A., Mitra, P., Giles, C.L.: Can\u2019t see the forest for the trees? a citation recommendation system. In: Proceedings of JCDL 2013 (2013)","DOI":"10.1145\/2467696.2467743"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Huang, W., Kataria, S., Caragea, C., Mitra, P., Giles, C.L., Rokach, L.: Recommending citations: translating papers into references. In: CIKM (2012)","DOI":"10.1145\/2396761.2398542"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"K\u00fc\u00e7\u00fcktun\u00e7, O., Saule, E., Kaya, K., \u00c7ataly\u00fcrek, \u00dc.V.: Diversified recommendation on graphs: pitfalls, measures, and algorithms. In: WWW (2013)","DOI":"10.1145\/2488388.2488451"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Nallapati, R.M., Ahmed, A., Xing, E.P., Cohen, W.W.: Joint latent topic models for text and citations. In: Proceedings of KDD 2008 (2008)","DOI":"10.1145\/1401890.1401957"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Treeratpituk, P., Giles, C.L.: Disambiguating authors in academic publications using random forests. In: Proc. of JCDL, JCDL 2009 (2009)","DOI":"10.1145\/1555400.1555408"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Gollapalli, S.D., Mitra, P., Giles, C.L.: Similar researcher search in academic environments. In: JCDL (2012)","DOI":"10.1145\/2232817.2232849"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Chen, H.H., Gou, L., Zhang, X., Giles, C.L.: Collabseer: a search engine for collaboration discovery. In: Proceedings of JCDL 2011 (2011)","DOI":"10.1145\/1998076.1998121"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Kan, M.Y.: Slideseer: a digital library of aligned document and presentation pairs. In: Proceedings of JCDL 2007 (2007)","DOI":"10.1145\/1255175.1255192"},{"key":"26_CR15","unstructured":"Kataria, S., Mitra, P., Caragea, C., Giles, C.L.: Context sensitive topic models for author influence in document networks. In: Proceedings of IJCAI 2011 (2011)"},{"key":"26_CR16","unstructured":"Rosen-Zvi, M., Griffiths, T., Steyvers, M., Smyth, P.: The author-topic model for authors and documents. In: Proceedings of UAI 2004 (2004)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Bhattacharya, I., Getoor, L.: A latent dirichlet model for unsupervised entity resolution. In: SDM (2006)","DOI":"10.1137\/1.9781611972764.5"},{"key":"26_CR18","unstructured":"Han, H., Giles, C.L., Manavoglu, E., Zha, H., Zhang, Z., Fox, E.A.: Automatic document metadata extraction using support vector machines. In: JCDL (2003)"},{"key":"26_CR19","unstructured":"Councill, I.G., Giles, C.L., Yen Kan, M.: Parscit: An open-source crf reference string parsing package. In: Intl. Language Resources and Evaluation (2008)"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Bhattacharya, I., Getoor, L.: Iterative record linkage for cleaning and integration. In: DMKD (2004)","DOI":"10.1145\/1008694.1008697"},{"key":"26_CR21","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"I.P. Fellegi","year":"1969","unstructured":"Fellegi, I.P., Sunter, A.B.: A theory for record linkage. Journal of the American Statistical Association\u00a064, 1183\u20131210 (1969)","journal-title":"Journal of the American Statistical Association"},{"key":"26_CR22","unstructured":"Rahm, E., Do, H.H.: Data cleaning: Problems and current approaches. IEEE Data Engineering Bulletin\u00a023 (2000)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Tejada, S., Knoblock, C.A., Minton, S.: Learning object identification rules for information integration. Journal Information Systems (2001)","DOI":"10.1016\/S0306-4379(01)00042-4"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Mooney, R.J.: Adaptive duplicate detection using learnable string similarity measures. In: Proceedings of KDD 2003 (2003)","DOI":"10.1145\/956750.956759"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Cohen, W.W., Richman, J.: Learning to match and cluster large high-dimensional data sets for data integration. In: Proceedings of KDD 2002 (2002)","DOI":"10.1145\/775047.775116"},{"key":"26_CR26","unstructured":"Winkler, W.E.: Methods for record linkage and bayesian networks. Technical report, Statistical Research Div., U.S. Bureau of the Census (2002)"},{"key":"26_CR27","unstructured":"Cohen, W.W., Ravikumar, P., Fienberg, S.E.: A comparison of string distance metrics for name-matching tasks. In: IJCAI, pp. 73\u201378 (2003)"},{"key":"26_CR28","unstructured":"Pasula, H., Marthi, B., Milch, B., Russell, S., Shpitser, I.: Identity uncertainty and citation matching. In: NIPS. MIT Press (2003)"},{"key":"26_CR29","unstructured":"McCallum, A., Wellner, B.: Toward conditional models of identity uncertainty with application to proper noun coreference. In: IIWeb (2003)"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Manku, G.S., Jain, A., Das Sarma, A.: Detecting near-duplicates for web crawling. In: Proc. of WWW 2007 (2007)","DOI":"10.1145\/1242572.1242592"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-06028-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,26]],"date-time":"2019-05-26T12:05:56Z","timestamp":1558872356000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-06028-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319060279","9783319060286"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-06028-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}