{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:26:35Z","timestamp":1757611595218,"version":"3.44.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863302"},{"type":"electronic","value":"9783030863319"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86331-9_23","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"351-363","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Sparse Document Analysis Using Beta-Liouville Naive Bayes with Vocabulary Knowledge"],"prefix":"10.1007","author":[{"given":"Fatma","family":"Najar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nizar","family":"Bouguila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"issue":"3","key":"23_CR1","first-page":"62","volume":"19","author":"M Abbas","year":"2019","unstructured":"Abbas, M., Memon, K.A., Jamali, A.A., Memon, S., Ahmed, A.: Multinomial Naive Bayes classification model for sentiment analysis. IJCSNS 19(3), 62 (2019)","journal-title":"IJCSNS"},{"issue":"4","key":"23_CR2","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1145\/582415.582416","volume":"20","author":"G Amati","year":"2002","unstructured":"Amati, G., Van Rijsbergen, C.J.: Probabilistic models of information retrieval based on measuring the divergence from randomness. ACM Trans. Inf. Syst. (TOIS) 20(4), 357\u2013389 (2002)","journal-title":"ACM Trans. Inf. Syst. (TOIS)"},{"unstructured":"Bai, J., Nie, J.Y., Paradis, F.: Using language models for text classification. In: Proceedings of the Asia Information Retrieval Symposium, Beijing, China (2004)","key":"23_CR3"},{"issue":"4","key":"23_CR4","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1109\/TKDE.2007.190726","volume":"20","author":"N Bouguila","year":"2008","unstructured":"Bouguila, N.: Clustering of count data using generalized Dirichlet multinomial distributions. IEEE Trans. Knowl. Data Eng. 20(4), 462\u2013474 (2008)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"12","key":"23_CR5","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TKDE.2009.42","volume":"21","author":"N Bouguila","year":"2009","unstructured":"Bouguila, N.: A model-based approach for discrete data clustering and feature weighting using MAP and stochastic complexity. IEEE Trans. Knowl. Data Eng. 21(12), 1649\u20131664 (2009)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"2","key":"23_CR6","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1109\/TNN.2010.2091428","volume":"22","author":"N Bouguila","year":"2010","unstructured":"Bouguila, N.: Count data modeling and classification using finite mixtures of distributions. IEEE Trans. Neural Netw. 22(2), 186\u2013198 (2010)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"2","key":"23_CR7","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.patrec.2011.09.037","volume":"33","author":"N Bouguila","year":"2012","unstructured":"Bouguila, N.: Infinite Liouville mixture models with application to text and texture categorization. Pattern Recognit. Lett. 33(2), 103\u2013110 (2012)","journal-title":"Pattern Recognit. Lett."},{"issue":"3","key":"23_CR8","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/s10044-011-0236-8","volume":"16","author":"N Bouguila","year":"2013","unstructured":"Bouguila, N.: On the smoothing of multinomial estimates using Liouville mixture models and applications. Pattern Anal. Appl. 16(3), 349\u2013363 (2013)","journal-title":"Pattern Anal. Appl."},{"issue":"7","key":"23_CR9","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1016\/j.jvcir.2010.04.001","volume":"21","author":"N Bouguila","year":"2010","unstructured":"Bouguila, N., Ghimire, M.N.: Discrete visual features modeling via leave-one-out likelihood estimation and applications. J. Vis. Commun. Image Represent. 21(7), 613\u2013626 (2010)","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"4","key":"23_CR10","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/j.jvcir.2007.02.005","volume":"18","author":"N Bouguila","year":"2007","unstructured":"Bouguila, N., Ziou, D.: Unsupervised learning of a finite discrete mixture: applications to texture modeling and image databases summarization. J. Vis. Commun. Image Represent. 18(4), 295\u2013309 (2007)","journal-title":"J. Vis. Commun. Image Represent."},{"doi-asserted-by":"crossref","unstructured":"Davidson, T., Warmsley, D., Macy, M., Weber, I.: Automated hate speech detection and the problem of offensive language. In: Proceedings of the International AAAI Conference on Web and Social Media, vol. 11 (2017)","key":"23_CR11","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"23_CR12","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.patcog.2016.02.004","volume":"55","author":"E Epaillard","year":"2016","unstructured":"Epaillard, E., Bouguila, N.: Proportional data modeling with hidden Markov models based on generalized Dirichlet and Beta-Liouville mixtures applied to anomaly detection in public areas. Pattern Recognit. 55, 125\u2013136 (2016)","journal-title":"Pattern Recognit."},{"unstructured":"Eyheramendy, S., Lewis, D.D., Madigan, D.: On the Naive Bayes model for text categorization (2003)","key":"23_CR13"},{"unstructured":"Fan, W., Bouguila, N.: Learning finite Beta-Liouville mixture models via variational Bayes for proportional data clustering. In: Rossi, F. (ed.) IJCAI 2013, Proceedings of the 23rd International Joint Conference on Artificial Intelligence, Beijing, China, 3\u20139 August 2013, pp. 1323\u20131329. IJCAI\/AAAI (2013)","key":"23_CR14"},{"issue":"11","key":"23_CR15","doi-asserted-by":"publisher","first-page":"1850","DOI":"10.1109\/TNNLS.2013.2268461","volume":"24","author":"W Fan","year":"2013","unstructured":"Fan, W., Bouguila, N.: Online learning of a Dirichlet process mixture of Beta-Liouville distributions via variational inference. IEEE Trans. Neural Networks Learn. Syst. 24(11), 1850\u20131862 (2013)","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"doi-asserted-by":"crossref","unstructured":"Kadam, S., Gala, A., Gehlot, P., Kurup, A., Ghag, K.: Word embedding based multinomial Naive Bayes algorithm for spam filtering. In: 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), pp. 1\u20135. IEEE (2018)","key":"23_CR16","DOI":"10.1109\/ICCUBEA.2018.8697601"},{"doi-asserted-by":"crossref","unstructured":"Madsen, R.E., Kauchak, D., Elkan, C.: Modeling word burstiness using the Dirichlet distribution. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 545\u2013552 (2005)","key":"23_CR17","DOI":"10.1145\/1102351.1102420"},{"unstructured":"McCallum, A., Nigam, K., et al.: A comparison of event models for Naive Bayes text classification. In: AAAI-98 Workshop on Learning for Text Categorization, vol. 752, pp. 41\u201348. Citeseer (1998)","key":"23_CR18"},{"doi-asserted-by":"crossref","unstructured":"Mohammad, S., Bravo-Marquez, F.: Emotion intensities in tweets. In: Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), pp. 65\u201377. Association for Computational Linguistics, Vancouver, Canada, August 2017","key":"23_CR19","DOI":"10.18653\/v1\/S17-1007"},{"key":"23_CR20","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/978-3-030-47358-7_45","volume-title":"Advances in Artificial Intelligence","author":"F Najar","year":"2020","unstructured":"Najar, F., Bouguila, N.: Happiness analysis with fisher information of Dirichlet-multinomial mixture model. In: Goutte, C., Zhu, X. (eds.) Canadian AI 2020. LNCS (LNAI), vol. 12109, pp. 438\u2013444. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-47358-7_45"},{"unstructured":"Rennie, J.D., Shih, L., Teevan, J., Karger, D.R.: Tackling the poor assumptions of Naive Bayes text classifiers. In: Proceedings of the 20th International Conference on Machine Learning (ICML 2003), pp. 616\u2013623 (2003)","key":"23_CR21"},{"key":"23_CR22","first-page":"417","volume":"11","author":"NFY Singer","year":"1999","unstructured":"Singer, N.F.Y.: Efficient Bayesian parameter estimation in large discrete domains. Adv. Neural. Inf. Process. Syst. 11, 417 (1999)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"23_CR23","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1137\/0141015","volume":"41","author":"B Sivazlian","year":"1981","unstructured":"Sivazlian, B.: On a multivariate extension of the gamma and beta distributions. SIAM J. Appl. Math. 41(2), 205\u2013209 (1981)","journal-title":"SIAM J. Appl. Math."},{"doi-asserted-by":"crossref","unstructured":"Willems, D., Vuurpijl, L.: A Bayesian network approach to mode detection for interactive maps. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol. 2, pp. 869\u2013873. IEEE (2007)","key":"23_CR24","DOI":"10.1109\/ICDAR.2007.4377039"},{"issue":"2","key":"23_CR25","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s10618-008-0101-6","volume":"18","author":"TT Wong","year":"2009","unstructured":"Wong, T.T.: Alternative prior assumptions for improving the performance of Na\u00efve Bayesian classifiers. Data Min. Knowl. Disc. 18(2), 183\u2013213 (2009)","journal-title":"Data Min. Knowl. Disc."},{"doi-asserted-by":"crossref","unstructured":"Xiao, Y., Lin, C., Jiang, Y., Chu, X., Shen, X.: Reputation-based QoS provisioning in cloud computing via Dirichlet multinomial model. In: 2010 IEEE International Conference on Communications, pp. 1\u20135. IEEE (2010)","key":"23_CR26","DOI":"10.1109\/ICC.2010.5502407"},{"doi-asserted-by":"crossref","unstructured":"Yuan, Q., Cong, G., Thalmann, N.M.: Enhancing Naive Bayes with various smoothing methods for short text classification. In: Proceedings of the 21st International Conference on World Wide Web, pp. 645\u2013646 (2012)","key":"23_CR27","DOI":"10.1145\/2187980.2188169"},{"key":"23_CR28","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.patcog.2019.05.038","volume":"95","author":"N Zamzami","year":"2019","unstructured":"Zamzami, N., Bouguila, N.: A novel scaled Dirichlet-based statistical framework for count data modeling: unsupervised learning and exponential approximation. Pattern Recogn. 95, 36\u201347 (2019)","journal-title":"Pattern Recogn."},{"issue":"2","key":"23_CR29","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1145\/984321.984322","volume":"22","author":"C Zhai","year":"2004","unstructured":"Zhai, C., Lafferty, J.: A study of smoothing methods for language models applied to information retrieval. ACM Trans. Inf. Syst. (TOIS) 22(2), 179\u2013214 (2004)","journal-title":"ACM Trans. Inf. Syst. (TOIS)"},{"key":"23_CR30","first-page":"1617","volume":"17","author":"J Zhang","year":"2004","unstructured":"Zhang, J., Ghahramani, Z., Yang, Y.: A probabilistic model for online document clustering with application to novelty detection. Adv. Neural. Inf. Process. Syst. 17, 1617\u20131624 (2004)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86331-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:05:17Z","timestamp":1756937117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86331-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863302","9783030863319"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86331-9_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"340","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":"182","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":"0","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":"54% - 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":"2.9","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":"4.9","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Additionally, 13 competition reports are included.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}