{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:46:57Z","timestamp":1773247617313,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319943008","type":"print"},{"value":"9783319943015","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":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-94301-5_2","type":"book-chapter","created":{"date-parts":[[2018,6,20]],"date-time":"2018-06-20T12:37:59Z","timestamp":1529498279000},"page":"17-25","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Inter-Category Distribution Enhanced Feature Extraction for Efficient Text Classification"],"prefix":"10.1007","author":[{"given":"Yuming","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lai","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,21]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-0907-3","volume-title":"Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms","author":"T Joachims","year":"2002","unstructured":"Joachims, T.: Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms, vol. 186. Kluwer Academic Publishers, Norwell (2002)"},{"issue":"1","key":"2_CR2","first-page":"1","volume":"2","author":"T Almeida","year":"2013","unstructured":"Almeida, T., Hidalgo, J.M.G., Silva, T.P.: Towards sms spam filtering: results under a new dataset. Int. J. Inf. Secur. Sci. 2(1), 1\u201318 (2013)","journal-title":"Int. J. Inf. Secur. Sci."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Liu, S., Huang, K., Chai, J.: Research of news tagging based on word frequency statistics and user information. In: 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp. 1\u20135. IEEE (2017)","DOI":"10.1109\/CISP-BMEI.2017.8302113"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Ali, K., Dong, H., Bouguettaya, A., Erradi, A., Hadjidj, R.: Sentiment analysis as a service: a social media based sentiment analysis framework. In: 2017 IEEE International Conference on Web Services (ICWS), pp. 660\u2013667. IEEE (2017)","DOI":"10.1109\/ICWS.2017.79"},{"issue":"2","key":"2_CR5","first-page":"134","volume":"22","author":"RG Ramani","year":"2013","unstructured":"Ramani, R.G., Jacob, S.G.: Benchmarking classification models for cancer prediction from gene expression data: a novel approach and new findings. Stud. Inf. Control 22(2), 134\u2013143 (2013)","journal-title":"Stud. Inf. Control"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chu, Z., Gianvecchio, S., Wang, H., Jajodia, S.: Who is tweeting on Twitter: human, bot, or cyborg? In: Proceedings of the 26th Annual Computer Security Applications Conference, pp. 21\u201330. ACM (2010)","DOI":"10.1145\/1920261.1920265"},{"issue":"1","key":"2_CR7","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1023\/A:1009982220290","volume":"1","author":"Y Yang","year":"1999","unstructured":"Yang, Y.: An evaluation of statistical approaches to text categorization. Inf. Retrieval 1(1), 69\u201390 (1999)","journal-title":"Inf. Retrieval"},{"issue":"1","key":"2_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"F Sebastiani","year":"2002","unstructured":"Sebastiani, F.: Machine learning in automated text categorization. ACM Comput. Surv. 34(1), 1\u201347 (2002)","journal-title":"ACM Comput. Surv."},{"key":"2_CR9","doi-asserted-by":"publisher","first-page":"1848","DOI":"10.1360\/jos171848","volume":"7","author":"JS Su","year":"2006","unstructured":"Su, J.S., Bo-Feng, Z., Xin, X.: Advances in machine learning based text categorization. J. Softw. 7, 1848\u20131859 (2006)","journal-title":"J. Softw."},{"key":"2_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3223-4","volume-title":"Mining Text Data","year":"2012","unstructured":"Aggarwal, C.C., Zhai, C. (eds.): Mining Text Data, 1st edn. Springer, New York (2012). https:\/\/doi.org\/10.1007\/978-1-4614-3223-4","edition":"1"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Mladeni\u0107, D., Brank, J., Grobelnik, M., Milic-Frayling, N.: Feature selection using linear classifier weights: interaction with classification models. In: Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2004, pp. 234\u2013241. ACM, New York (2004)","DOI":"10.1145\/1008992.1009034"},{"issue":"3","key":"2_CR12","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1145\/951761.951766","volume":"9","author":"G Salton","year":"1973","unstructured":"Salton, G., Yu, C.T.: On the construction of effective vocabularies for information retrieval. SIGIR Forum 9(3), 48\u201360 (1973)","journal-title":"SIGIR Forum"},{"key":"2_CR13","unstructured":"Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: Proceedings of the Fourteenth International Conference on Machine Learning, ICML 1997, pp. 412\u2013420. Morgan Kaufmann Publishers Inc., San Francisco (1997)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Hofmann, T.: Probabilistic latent semantic indexing. In: Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 1999, pp. 50\u201357. ACM, New York (1999)","DOI":"10.1145\/312624.312649"},{"key":"2_CR15","unstructured":"Joachims, T.: A probabilistic analysis of the Rocchio algorithm with TFIDF for text categorization. In: Proceedings of the Fourteenth International Conference on Machine Learning, ICML 1997, pp. 143\u2013151. Morgan Kaufmann Publishers Inc., San Francisco (1997)"},{"key":"2_CR16","doi-asserted-by":"publisher","first-page":"856","DOI":"10.3724\/SP.J.1016.2011.00856","volume":"34","author":"CH Huang","year":"2011","unstructured":"Huang, C.H., Yin, J., Hou, F.: A text similarity measurement combining word semantic information with TF-IDF method. Chin. J. Comput. 34, 856\u2013864 (2011)","journal-title":"Chin. J. Comput."},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, G., Zou, X.: Improved information gain feature selection method for Chinese text classification based on word embedding. In: Proceedings of the 6th International Conference on Software and Computer Applications, pp. 72\u201376. ACM (2017)","DOI":"10.1145\/3056662.3056671"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Qu, S., Wang, S., Zou, Y.: Improvement of text feature selection method based on TFIDF. In: International Seminar on Future Information Technology and Management Engineering, FITME 2008, pp. 79\u201381. IEEE (2008)","DOI":"10.1109\/FITME.2008.25"},{"key":"2_CR19","unstructured":"HanLP: Han Language Processing (2014). https:\/\/github.com\/hankcs\/HanLP"},{"issue":"3","key":"2_CR20","first-page":"833","volume":"29","author":"XL Hua","year":"2012","unstructured":"Hua, X.L., Zhu, Q.M., Li, P.F.: Chinese text similarity method research by combining semantic analysis with statistics. Jisuanji Yingyong Yanjiu 29(3), 833\u2013836 (2012)","journal-title":"Jisuanji Yingyong Yanjiu"},{"key":"2_CR21","unstructured":"LTP-Cloud: Language Technology Platform Cloud (2017). https:\/\/www.ltp-cloud.com"}],"container-title":["Lecture Notes in Computer Science","Big Data \u2013 BigData 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-94301-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T08:32:29Z","timestamp":1710232349000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-94301-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319943008","9783319943015"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-94301-5_2","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":"21 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BIGDATA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seattle, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"25 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bigdata2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.bigdatacongress.org\/2018\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"www.confhub.com","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"97","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}