{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:21Z","timestamp":1760245041281,"version":"3.41.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319487397"},{"type":"electronic","value":"9783319487403"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-48740-3_3","type":"book-chapter","created":{"date-parts":[[2016,11,1]],"date-time":"2016-11-01T10:32:20Z","timestamp":1477996340000},"page":"35-49","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Data Cleaning Method for CiteSeer Dataset"],"prefix":"10.1007","author":[{"given":"Yan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaxin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deyun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanlin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianguo","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,2]]},"reference":[{"key":"3_CR1","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. 2633, pp. 335\u2013350. Springer, Heidelberg (2003). doi:10.1007\/3-540-36618-0_24"},{"unstructured":"Caragea, C., Silvescu, A., Kataria, S., Caragea, D., Mitra, P.: Classifying scientific publications using abstract features. In: SARA (2011)","key":"3_CR2"},{"issue":"3","key":"3_CR3","first-page":"93","volume":"29","author":"P Sen","year":"2008","unstructured":"Sen, P., Namata, G., Bilgic, M., Getoor, L., Gallagher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93\u2013106 (2008)","journal-title":"AI Mag."},{"doi-asserted-by":"crossref","unstructured":"Caragea, C., Silvescu, A., Mitra, P., Giles, C.: Can\u2019t see the forest for the trees? a citation recommendation system. In: JCDL, pp. 111\u2013114 (2013)","key":"3_CR4","DOI":"10.1145\/2467696.2467743"},{"unstructured":"Carage, C., Wu, J., Williams, K., Das, S., Khabsa, M., Teregowda, P., Giles, C.L.: Automatic identification of research articles from crawled documents. In: WSDM-WSCBD (2014)","key":"3_CR5"},{"doi-asserted-by":"crossref","unstructured":"Huang, W., Kataria, S., Caragea, C., Mitra, P., Giles, C., Rokach, L.: Recommending citations: translating papers into references. In: CIKM, pp. 1910\u20131914 (2012)","key":"3_CR6","DOI":"10.1145\/2396761.2398542"},{"doi-asserted-by":"crossref","unstructured":"Caragea, C., Wu, J., Ciobanu, A., Williams, K. ndez Ram rez, J.F., Chen, H., Wu, Z., Giles, L.: Citeseerx: a scholarly big dataset. In: Advances in InformationRetrieval, pp. 311\u2013322 (2014)","key":"3_CR7","DOI":"10.1007\/978-3-319-06028-6_26"},{"unstructured":"CiteSeerX. http:\/\/csxstatic.ist.psu.edu\/about\/data","key":"3_CR8"},{"doi-asserted-by":"crossref","unstructured":"Lipinski, M., Yao, K., Breitinger, C., Beel, J., Gipp, B.: Evaluation of header metadata extraction approaches and tools for scientific pdf documents. In: Proceedings of JCDL, pp. 385\u2013386 (2013)","key":"3_CR9","DOI":"10.1145\/2467696.2467753"},{"doi-asserted-by":"crossref","unstructured":"Wu, J., Williams, K., Khabsa, M., Giles, C.L.: The impact of user corrections on a crawl-based digital library: a citeseerx perspective. In: Collaborative Computing: Networking, Applications and Worksharing (CollaborateCom) (2014)","key":"3_CR10","DOI":"10.4108\/icst.collaboratecom.2014.257563"},{"issue":"328","key":"3_CR11","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"IP Fellegi","year":"1969","unstructured":"Fellegi, I.P., Sunter, A.B.: A theory for record linkage. J. Am. Stat. Assoc. 64(328), 1183\u20131210 (1969)","journal-title":"J. Am. Stat. Assoc."},{"unstructured":"Tang, J.: https:\/\/aminer.org\/","key":"3_CR12"},{"doi-asserted-by":"crossref","unstructured":"Manning, C.D., Raghavan, P., Schutze, H.: Introduction to Information retrieval. Cambridge University Press, Cambridge (2008)","key":"3_CR13","DOI":"10.1017\/CBO9780511809071"},{"key":"3_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/978-3-319-11116-2_17","volume-title":"Web Technologies and Applications","author":"Y Wang","year":"2014","unstructured":"Wang, Y., Lu, J., Chen, J.: TS-IDS algorithm for query selection in the deep web crawling. In: Chen, L., Jia, Y., Sellis, T., Liu, G. (eds.) APWeb 2014. LNCS, vol. 8709, pp. 189\u2013200. Springer, Heidelberg (2014). doi:10.1007\/978-3-319-11116-2_17"},{"doi-asserted-by":"crossref","unstructured":"Manku, G., Jain, A., Sarma, S.A.: Detecting near-duplicates for web crawling. In: WWW, pp. 141\u2013150 (2007)","key":"3_CR15","DOI":"10.1145\/1242572.1242592"},{"issue":"3","key":"3_CR16","first-page":"35","volume":"36","author":"J Wu","year":"2015","unstructured":"Wu, J., William, K., Chen, H., Khabsa, M., Caragea, C., Tuarob, S., Ororbia, A.G., Jordan, D., Mitra, P., Lee Giles, C.: Citeseerx: AI in a digital library search engine. AI Mag. 36(3), 35\u201349 (2015)","journal-title":"AI Mag."},{"unstructured":"Cohen, W., Ravikumar, P., Fienberg, S.: A comparison of string metrics for matching names and records. In: KDD Workshop on Data Cleaning and Object Consolidation, vol. 3, pp. 73\u201378 (2003)","key":"3_CR17"},{"doi-asserted-by":"crossref","unstructured":"McCallum, A., Nigam, K., Ungar, L.H.: Efficient clustering of high-dimensional data sets with application to reference matching. In: Proceedings of SIGKDD, pp. 169\u2013178 (2000)","key":"3_CR18","DOI":"10.1145\/347090.347123"},{"key":"3_CR19","first-page":"3","volume":"23","author":"E Rahm","year":"2000","unstructured":"Rahm, E., Do, H.: Data cleaning: problems and current approaches. IEEE Data Eng. Bull. 23, 3\u201313 (2000)","journal-title":"IEEE Data Eng. Bull."},{"issue":"3","key":"3_CR20","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1016\/S0306-4379(01)00042-4","volume":"26","author":"S Tejada","year":"2001","unstructured":"Tejada, S., Knoblock, C., Minton, S.: Learning object identification rules for information integration. J. Inf. Syst. 26(3), 607\u2013633 (2001)","journal-title":"J. Inf. Syst."},{"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 SIGKDD, pp. 475\u2013480 (2002)","key":"3_CR21","DOI":"10.1145\/775047.775116"},{"issue":"9","key":"3_CR22","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/TKDE.2011.127","volume":"24","author":"P Christen","year":"2012","unstructured":"Christen, P.: A survey of indexing techniques for scalable record linkage and deduplication. IEEE Trans. Knowl. Data Eng. 24(9), 1537\u20131555 (2012)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"unstructured":"Chakrabarti, S.: Mining the web: discovering knowledge from hypertext data. Morgan-Kauffman (2002)","key":"3_CR23"},{"doi-asserted-by":"crossref","unstructured":"Jin, L., Li, C., Mehrotra, S.: Efficient record linkage in large data sets. In: Proceedings of DASFAA, pp. 137\u2013146 (2003)","key":"3_CR24","DOI":"10.1109\/DASFAA.2003.1192377"},{"unstructured":"Hatcher, E., Gospodnetic, O.: Lucene in Action. Manning Publications (2004)","key":"3_CR25"},{"issue":"5","key":"3_CR26","doi-asserted-by":"crossref","first-page":"e93949","DOI":"10.1371\/journal.pone.0093949","volume":"9","author":"Madian Khabsa","year":"2014","unstructured":"Khabsa, M., Giles, C.L.: The number of scholarly documents on the public web. PLoS One 9(5) (2014)","journal-title":"PLoS ONE"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems Engineering \u2013 WISE 2016"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-48740-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T23:00:30Z","timestamp":1749682830000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-48740-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319487397","9783319487403"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-48740-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"2 November 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WISE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 November 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wise2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.wise-conferences.org\/2016\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}