{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T14:20:07Z","timestamp":1768832407749,"version":"3.49.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"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":["Adv Data Anal Classif"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s11634-022-00522-6","type":"journal-article","created":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T02:02:47Z","timestamp":1665626567000},"page":"725-744","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["On smoothing and scaling language model for sentiment based information retrieval"],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2301-4803","authenticated-orcid":false,"given":"Fatma","family":"Najar","sequence":"first","affiliation":[]},{"given":"Nizar","family":"Bouguila","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,13]]},"reference":[{"key":"522_CR1","doi-asserted-by":"publisher","DOI":"10.1561\/9781601982957","volume-title":"Learning deep architectures for AI","author":"Y Bengio","year":"2009","unstructured":"Bengio Y (2009) Learning deep architectures for AI. Now Publishers Inc, Norwell"},{"key":"522_CR2","doi-asserted-by":"crossref","unstructured":"Bouguila N, Ziou D (2004) Improving content based image retrieval systems using finite multinomial dirichlet mixture. In: Proceedings of the 2004 14th IEEE Signal Processing Society Workshop Machine Learning for Signal Processing, 2004., pp. 23\u201332. IEEE","DOI":"10.1109\/MLSP.2004.1422956"},{"key":"522_CR3","doi-asserted-by":"crossref","unstructured":"Burges C, Shaked T, Renshaw E, Lazier A, Deeds M, Hamilton N, Hullender G (2005) Learning to rank using gradient descent. In: Proceedings of the 22nd international conference on Machine learning, pp. 89\u201396","DOI":"10.1145\/1102351.1102363"},{"key":"522_CR4","doi-asserted-by":"crossref","unstructured":"Coletta LF, da\u00a0Silva NF, Hruschka ER, Hruschka ER (2014) Combining classification and clustering for tweet sentiment analysis. In: 2014 Brazilian conference on intelligent systems, pp. 210\u2013215. IEEE","DOI":"10.1109\/BRACIS.2014.46"},{"key":"522_CR5","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.dss.2014.07.003","volume":"66","author":"NF Da Silva","year":"2014","unstructured":"Da Silva NF, Hruschka ER, Hruschka ER Jr (2014) Tweet sentiment analysis with classifier ensembles. Decis Support Syst 66:170\u2013179","journal-title":"Decis Support Syst"},{"key":"522_CR6","unstructured":"Davidov D, Tsur O, Rappoport A (2010) Enhanced sentiment learning using twitter hashtags and smileys. In: Coling 2010: Posters, pp. 241\u2013249"},{"key":"522_CR7","doi-asserted-by":"crossref","unstructured":"Fan Y, Guo J, Lan Y, Xu J, Zhai C, Cheng X (2018) Modeling diverse relevance patterns in ad-hoc retrieval. In: The 41st international ACM SIGIR conference on research and development in information retrieval, pp. 375\u2013384","DOI":"10.1145\/3209978.3209980"},{"key":"522_CR8","doi-asserted-by":"crossref","unstructured":"Feng SL, Manmatha R, Lavrenko V (2004) Multiple bernoulli relevance models for image and video annotation. In: Proceedings of the 2004 IEEE Computer society conference on computer vision and pattern recognition, 2004. CVPR 2004., vol.\u00a02. IEEE","DOI":"10.1109\/CVPR.2004.1315274"},{"issue":"3","key":"522_CR9","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/s10791-008-9045-0","volume":"11","author":"N Fuhr","year":"2008","unstructured":"Fuhr N (2008) A probability ranking principle for interactive information retrieval. Inf Retr. 11(3):251\u2013265","journal-title":"Inf Retr."},{"key":"522_CR10","doi-asserted-by":"crossref","unstructured":"Gao J, Pantel P, Gamon M, He X, Deng L (2014) Modeling interestingness with deep neural networks. In: Conference on empirical methods in natural language processing (EMNLP)","DOI":"10.3115\/v1\/D14-1002"},{"key":"522_CR11","unstructured":"Go A, Bhayani R, Huang L (2009) Twitter sentiment classification using distant supervision. CS224N project report, Stanford 1(12)"},{"key":"522_CR12","doi-asserted-by":"crossref","unstructured":"Guo J, Fan Y, Ai Q, Croft WB (2016) A deep relevance matching model for ad-hoc retrieval. In: Proceedings of the 25th ACM international on conference on information and knowledge management, pp. 55\u201364","DOI":"10.1145\/2983323.2983769"},{"key":"522_CR13","doi-asserted-by":"crossref","unstructured":"Htait A, Fournier S, Bellot P, Azzopardi L, Pasi G (2020) Using sentiment analysis for pseudo-relevance feedback in social book search. In: Proceedings of the 2020 ACM SIGIR on international conference on theory of information retrieval, pp. 29\u201332","DOI":"10.1145\/3409256.3409847"},{"key":"522_CR14","unstructured":"Hu B, Lu Z, Li H, Chen Q (2014) Convolutional neural network architectures for matching natural language sentences. In: Z.\u00a0Ghahramani, M.\u00a0Welling, C.\u00a0Cortes, N.\u00a0Lawrence, K.Q. Weinberger (eds.) Advances in neural information processing systems, vol.\u00a027. Curran Associates, Inc"},{"key":"522_CR15","doi-asserted-by":"crossref","unstructured":"Huang PS, He X, Gao J, Deng L, Acero A, Heck L (2013) Learning deep structured semantic models for web search using clickthrough data. In: Proceedings of the 22nd ACM international conference on Information and Knowledge Management, pp. 2333\u20132338","DOI":"10.1145\/2505515.2505665"},{"key":"522_CR16","doi-asserted-by":"crossref","unstructured":"Hui K, Yates A, Berberich K, De\u00a0Melo G (2018) Co-pacrr: A context-aware neural ir model for ad-hoc retrieval. In: Proceedings of the eleventh ACM international conference on web search and data mining, pp. 279\u2013287","DOI":"10.1145\/3159652.3159689"},{"key":"522_CR17","doi-asserted-by":"publisher","first-page":"23253","DOI":"10.1109\/ACCESS.2017.2776930","volume":"6","author":"Z Jianqiang","year":"2018","unstructured":"Jianqiang Z, Xiaolin G, Xuejun Z (2018) Deep convolution neural networks for twitter sentiment analysis. IEEE Access 6:23253\u201323260","journal-title":"IEEE Access"},{"key":"522_CR18","doi-asserted-by":"crossref","unstructured":"Kalchbrenner N, Grefenstette E, Blunsom P (2014) A convolutional neural network for modelling sentences. In: Proc 52nd Annu Meet Assoc Comput Linguistics, pp. 655\u2013666","DOI":"10.3115\/v1\/P14-1062"},{"key":"522_CR19","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.eswa.2016.05.038","volume":"61","author":"AU Kauer","year":"2016","unstructured":"Kauer AU, Moreira VP (2016) Using information retrieval for sentiment polarity prediction. Expert Syst Appl 61:282\u2013289","journal-title":"Expert Syst Appl"},{"key":"522_CR20","unstructured":"Lavrenko V (2004) A generative theory of relevance. Ph.D. thesis"},{"key":"522_CR21","first-page":"260","volume-title":"ACM SIGIR Forum","author":"V Lavrenko","year":"2017","unstructured":"Lavrenko V, Croft WB (2017) Relevance-based language models. ACM SIGIR Forum, vol 51. ACM, New York NY, USA, pp 260\u2013267"},{"key":"522_CR22","doi-asserted-by":"crossref","unstructured":"Metzler D, Lavrenko V, Croft WB (2004) Formal multiple-bernoulli models for language modeling. In: Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 540\u2013541","DOI":"10.1145\/1008992.1009110"},{"key":"522_CR23","doi-asserted-by":"crossref","unstructured":"Mitra B, Craswell N (2017) Neural models for information retrieval. arXiv preprint arXiv:1705.01509","DOI":"10.1145\/3018661.3022755"},{"key":"522_CR24","doi-asserted-by":"crossref","unstructured":"Monti GS, Mateu-Figueras G, Pawlowsky-Glahn V (2011) Notes on the scaled dirichlet distribution. Compositional data analysis, pp. 128\u2013138","DOI":"10.1002\/9781119976462.ch10"},{"key":"522_CR25","unstructured":"Nallapati R (2006) The smoothed dirichlet distribution: Understanding cross-entropy ranking in information retrieval. Ph.D. thesis, University of Massachusetts Amherst"},{"key":"522_CR26","unstructured":"Nallapati R, Minka T, Robertson S (2006) The smoothed-dirichlet distribution: a new building block for generative models. CIIR Technical Report http:\/\/www.cs.cmu.edu\/~nmramesh\/sd_tc.pdf"},{"key":"522_CR27","doi-asserted-by":"crossref","unstructured":"Oboh BS, Bouguila N (2017) Unsupervised learning of finite mixtures using scaled dirichlet distribution and its application to software modules categorization. In: 2017 IEEE International Conference on Industrial Technology (ICIT), pp. 1085\u20131090","DOI":"10.1109\/ICIT.2017.7915513"},{"key":"522_CR28","doi-asserted-by":"crossref","unstructured":"Pang B, Lee L (2004) A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In: Proceedings of the 42th annual meeting of the association of computational linguistics (ACL), pp. 271\u2013278","DOI":"10.3115\/1218955.1218990"},{"key":"522_CR29","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-25518-7_20","volume-title":"Semantic web evaluation challenges","author":"G Petrucci","year":"2015","unstructured":"Petrucci G, Dragoni M (2015) An information retrieval-based system for multi-domain sentiment analysis. Semantic web evaluation challenges. Springer, Cham, pp 234\u2013243"},{"issue":"4","key":"522_CR30","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/s10791-009-9123-y","volume":"13","author":"T Qin","year":"2010","unstructured":"Qin T, Liu TY, Xu J, Li H (2010) LETOR: a benchmark collection for research on learning to rank for information retrieval. Inf Retrieval 13(4):346\u2013374","journal-title":"Inf Retrieval"},{"key":"522_CR31","doi-asserted-by":"crossref","unstructured":"Rath TM, Lavrenko V, Manmatha R (2003) A statistical approach to retrieving historical manuscript images without recognition. Tech. rep, Space and Naval Warfare Systems Center San Diego CA","DOI":"10.21236\/ADA477875"},{"key":"522_CR32","unstructured":"Rendle S, Freudenthaler C, Gantner Z, Schmidt-Thieme L (2012) BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618"},{"key":"522_CR33","doi-asserted-by":"crossref","unstructured":"Robertson SE (1977) The probability ranking principle in IR. Journal of documentation","DOI":"10.1108\/eb026647"},{"key":"522_CR34","doi-asserted-by":"crossref","unstructured":"Rosenthal S, Ritter A, Nakov P, Stoyanov V (2014) SemEval-2014 task 9: Sentiment analysis in Twitter. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp. 73\u201380. Association for Computational Linguistics, Dublin, Ireland","DOI":"10.3115\/v1\/S14-2009"},{"key":"522_CR35","unstructured":"Saif H, Fernandez M, He Y, Alani H (2013) Evaluation datasets for twitter sentiment analysis a survey and a new dataset, the STS-gold. CEUR Workshop Proceedings, 1096, 9\u201321 . https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-84908157393 &partnerID=40 &md5=cc68d8aa78e8b62f4f1724747bbdd1dc"},{"issue":"7","key":"522_CR36","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1016\/j.ijar.2008.11.006","volume":"50","author":"R Salakhutdinov","year":"2009","unstructured":"Salakhutdinov R, Hinton G (2009) Semantic hashing. Int J Approx Reason 50(7):969\u2013978","journal-title":"Int J Approx Reason"},{"key":"522_CR37","doi-asserted-by":"crossref","unstructured":"Shen Y, He X, Gao J, Deng L, Mesnil G (2014) Learning semantic representations using convolutional neural networks for web search. In: Proceedings of the 23rd international conference on world wide web, pp. 373\u2013374","DOI":"10.1145\/2567948.2577348"},{"issue":"1","key":"522_CR38","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1002\/asi.21662","volume":"63","author":"M Thelwall","year":"2012","unstructured":"Thelwall M, Buckley K, Paltoglou G (2012) Sentiment strength detection for the social web. J Am Soc Inform Sci Technol 63(1):163\u2013173","journal-title":"J Am Soc Inform Sci Technol"},{"key":"522_CR39","doi-asserted-by":"crossref","unstructured":"Vosoughi S, Zhou H, Roy D (2016) Enhanced twitter sentiment classification using contextual information. Proceedings of the 6th workshop on computational approaches to subjectivity, sentiment and social media analysis","DOI":"10.18653\/v1\/W15-2904"},{"key":"522_CR40","doi-asserted-by":"crossref","unstructured":"Wang J, Yu L, Zhang W, Gong Y, Xu Y, Wang B, Zhang P, Zhang D (2017) Irgan: A minimax game for unifying generative and discriminative information retrieval models. In: Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval, pp. 515\u2013524","DOI":"10.1145\/3077136.3080786"},{"key":"522_CR41","doi-asserted-by":"crossref","unstructured":"Wei X, Croft WB (2006) Lda-based document models for ad-hoc retrieval. In: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 178\u2013185","DOI":"10.1145\/1148170.1148204"},{"key":"522_CR42","first-page":"29","volume-title":"European conference on information retrieval","author":"X Yi","year":"2009","unstructured":"Yi X, Allan J (2009) A comparative study of utilizing topic models for information retrieval. European conference on information retrieval. Springer, Berlin, pp 29\u201341"},{"issue":"2","key":"522_CR43","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1111\/coin.12246","volume":"36","author":"N Zamzami","year":"2020","unstructured":"Zamzami N, Alsuroji R, Eromonsele O, Bouguila N (2020) Proportional data modeling via selection and estimation of a finite mixture of scaled Dirichlet distributions. Comput Intell 36(2):459\u2013485","journal-title":"Comput Intell"},{"key":"522_CR44","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 (2019) A novel scaled dirichlet-based statistical framework for count data modeling: Unsupervised learning and exponential approximation. Pattern Recogn 95:36\u201347","journal-title":"Pattern Recogn"},{"key":"522_CR45","doi-asserted-by":"crossref","unstructured":"Zhai C, Lafferty J (2017) A study of smoothing methods for language models applied to ad hoc information retrieval. In: ACM SIGIR Forum, vol.\u00a051, pp. 268\u2013276. ACM New York, NY, USA","DOI":"10.1145\/3130348.3130377"},{"key":"522_CR46","doi-asserted-by":"crossref","unstructured":"Zhang Y, Zhang J, Cui Z, Wu S, Wang L (2021) A graph-based relevance matching model for ad-hoc retrieval. arXiv preprint arXiv:2101.11873","DOI":"10.1609\/aaai.v35i5.16599"}],"container-title":["Advances in Data Analysis and Classification"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11634-022-00522-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11634-022-00522-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11634-022-00522-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,5]],"date-time":"2024-10-05T18:09:54Z","timestamp":1728151794000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11634-022-00522-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,13]]},"references-count":46,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["522"],"URL":"https:\/\/doi.org\/10.1007\/s11634-022-00522-6","relation":{},"ISSN":["1862-5347","1862-5355"],"issn-type":[{"value":"1862-5347","type":"print"},{"value":"1862-5355","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,13]]},"assertion":[{"value":"29 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}