{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T07:16:37Z","timestamp":1775286997102,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030030551","type":"print"},{"value":"9783030030568","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-03056-8_10","type":"book-chapter","created":{"date-parts":[[2018,11,28]],"date-time":"2018-11-28T08:24:42Z","timestamp":1543393482000},"page":"115-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["The Problem of Data Cleaning for Knowledge Extraction from Social Media"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7505-7827","authenticated-orcid":false,"given":"Emre","family":"Calisir","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8753-2434","authenticated-orcid":false,"given":"Marco","family":"Brambilla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,29]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Salloum, S.A., Al-Emran, M., Monem, A.A., Shaalan, K.: A survey of text mining in social media Facebook and Twitter perspectives. Adv. Sci. Technol. Eng. Syst. J. (2017)","DOI":"10.25046\/aj020115"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Sakaki, T., Okazaki, M., Matsuo, Y.: Earthquake shakes Twitter users: real-time event detection by social sensors. In: Proceedings of the 19th International Conference on World Wide Web, New York, USA, pp. 851\u2013860 (2010)","DOI":"10.1145\/1772690.1772777"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Culotta A: Towards detecting influenza epidemics by analyzing Twitter messages. In: Proceedings of the First Workshop on Social Media Analytics, Washington, D.C., pp. 115\u2013122 (2010)","DOI":"10.1145\/1964858.1964874"},{"issue":"8","key":"10_CR4","doi-asserted-by":"publisher","first-page":"e103408","DOI":"10.1371\/journal.pone.0103408","volume":"9","author":"Michael J. Paul","year":"2014","unstructured":"Paul, M.J., Dredze, M.: Discovering health topics in social media using models. PLoS ONE 9, e103408 (2014)","journal-title":"PLoS ONE"},{"issue":"3","key":"10_CR5","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1007\/s40264-015-0379-4","volume":"39","author":"A Sarker","year":"2016","unstructured":"Sarker, A., et al.: Social media mining for toxicovigilance: automatic monitoring of prescription medication abuse from Twitter. Drug Saf. 39(3), 231\u2013240 (2016)","journal-title":"Drug Saf."},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Lin, J., Snow, R., Morgan, W.: Smoothing techniques for adaptive online language models: topic tracking in tweet streams. In: KDD, pp. 422\u2013429 (2011)","DOI":"10.1145\/2020408.2020476"},{"issue":"3","key":"10_CR7","first-page":"507","volume":"21","author":"MAH Khan","year":"2013","unstructured":"Khan, M.A.H., Iwai, M., Sezaki, K.: An improved classification strategy for filtering relevant tweets using bag-of-word classifiers. J. Inf. Process. 21(3), 507\u2013516 (2013)","journal-title":"J. Inf. Process."},{"key":"10_CR8","unstructured":"Kunneman, F., Bosch, A.: Event detection in Twitter: a machine-learning approach based on term pivoting. In: BNAIC, pp. 65\u201372 (2014)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Castillo, C., Mendoza, M., Poblete, B.: Information credibility on Twitter. In: Proceedings of the 20th International Conference on World Wide Web, Hyderabad, pp. 675\u2013684. ACM (2011)","DOI":"10.1145\/1963405.1963500"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Bollegala, D., Matsuo, Y., Ishizuka, M.: Measuring semantic similarity between words using web search engines. In: Proceedings of the 16th International Conference on World Wide Web (WWW2007), pp. 757\u2013766. ACM Press, New York (2007)","DOI":"10.1145\/1242572.1242675"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Yang, S., Kolcz, A., Schlaikjer, A., Gupta, P.: Large-scale high-precision topic modeling on Twitter. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2014), pp. 1907\u20131916. ACM, New York (2014)","DOI":"10.1145\/2623330.2623336"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Banerjee, S., Ramanathan, K., Gupta, A.: Clustering short texts using Wikipedia. In: SIGIR, pp. 787\u2013788 (2007)","DOI":"10.1145\/1277741.1277909"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Li, Q., Liu, X., Shah, S., Nourbakhsh, A.: Tweet topic classification using distributed language representations. In: Proceedings of the 2016 IEEE\/WIC\/ACM International Conference on Web Intelligence, Nebraska, USA (2016)","DOI":"10.1109\/WI.2016.0022"},{"key":"10_CR14","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1016\/j.procs.2017.08.166","volume":"112","author":"M Hajjem","year":"2017","unstructured":"Hajjem, M., Latiri, C.: Combining IR and LDA topic modeling for filtering microblogs. Procedia Comput. Sci. 112, 761\u2013770 (2017)","journal-title":"Procedia Comput. Sci."},{"key":"10_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/BFb0026683","volume-title":"Machine Learning: ECML-98","author":"T Joachims","year":"1998","unstructured":"Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: N\u00e9dellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 137\u2013142. Springer, Heidelberg (1998). https:\/\/doi.org\/10.1007\/BFb0026683"},{"key":"10_CR16","unstructured":"Lewis, J.P.: Tutorial on SVM. In: CGIT Lab, USC (2004)"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Sun, A.: Short text classification using very few words. In: SIGIR, pp. 1145\u20131146. ACM (2012)","DOI":"10.1145\/2348283.2348511"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Sriram, B., Fuhry, D., Demir, E., Ferhatosmanoglu, H., Demirbas, M.: Short text classification in Twitter to improve information filtering. In: Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval (2010)","DOI":"10.1145\/1835449.1835643"},{"issue":"5199","key":"10_CR19","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1126\/science.267.5199.843","volume":"267","author":"M Damashek","year":"1995","unstructured":"Damashek, M.: Gauging similarity with n-grams: language independent categorization of text. Science 267(5199), 843\u2013848 (1995)","journal-title":"Science"},{"key":"10_CR20","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Proceedings of Workshop at ICLR (2013)"}],"container-title":["Lecture Notes in Computer Science","Current Trends in Web Engineering"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03056-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:33:22Z","timestamp":1775284402000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-03056-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030030551","9783030030568"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03056-8_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"ICWE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"C\u00e1ceres","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icwe2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icwe2018.webengineering.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}