{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:19:41Z","timestamp":1742962781051,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031360268"},{"type":"electronic","value":"9783031360275"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-36027-5_14","type":"book-chapter","created":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T08:02:52Z","timestamp":1688025772000},"page":"187-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Impact of\u00a0Text Pre-processing on\u00a0Classification Accuracy in\u00a0Polish"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-3356","authenticated-orcid":false,"given":"Urszula","family":"Gumi\u0144ska","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7596-0813","authenticated-orcid":false,"given":"Aneta","family":"Poniszewska-Mara\u0144da","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9295-3962","authenticated-orcid":false,"given":"Joanna","family":"Ochelska-Mierzejewska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,26]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Hedderich, M.A., et al.: A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios (2021). (https:\/\/aclanthology.org\/2021.naacl-main.201). NAACL","DOI":"10.18653\/v1\/2021.naacl-main.201"},{"key":"14_CR2","first-page":"4864","volume":"7","author":"A Tabassum","year":"2020","unstructured":"Tabassum, A., Patil, R.R.: A survey on text pre-processing & feature extraction techniques in natural language processing. Int. Res. J. Eng. Technol. 7, 4864\u20134867 (2020)","journal-title":"Int. Res. J. Eng. Technol."},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Haddi, E., Xiaohui, L., Yong, S.: The role of text pre-processing in sentiment analysis. In: International Conference on Information Technology and Quantitative Management, vol. 15, pp. 26\u201332 (2013)","DOI":"10.1016\/j.procs.2013.05.005"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Goyal, P., Pandey, S., Jain, K.: Deep Learning for Natural Language Processing: Creating Neural Networks with Python, Apress, 1st ed. Edition (2018)","DOI":"10.1007\/978-1-4842-3685-7_1"},{"key":"14_CR5","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural Machine Translation by Jointly Learning to Align and Translate (2014). ArXiv. 1409"},{"key":"14_CR6","unstructured":"Khyani, D., Siddhartha, B.S.: An interpretation of lemmatization and stemming in natural language processing. Shanghai Ligong Daxue Xuebao\/J. Univ. Shanghai Sci. Technol. 22, 350\u2013357 (2021)"},{"issue":"8","key":"14_CR7","doi-asserted-by":"publisher","first-page":"e0254937","DOI":"10.1371\/journal.pone.0254937","volume":"16","author":"S Sarica","year":"2020","unstructured":"Sarica, S., Luo, J.: Stopwords in technical language processing. PLoS ONE 16(8), e0254937 (2020)","journal-title":"PLoS ONE"},{"key":"14_CR8","first-page":"p119","volume":"4","author":"EK Abu","year":"2006","unstructured":"Abu, E.K., Khair, I.: Effects of stop words elimination for Arabic information retrieval: a comparative study. Int. J. Comput. Inf. Sci. 4, p119-133 (2006)","journal-title":"Int. J. Comput. Inf. Sci."},{"key":"14_CR9","first-page":"51","volume":"18","author":"Z Feng","year":"2006","unstructured":"Feng, Z., Fu, L.W., Xiaotie, D., Song, H.: Automatic identification of Chinese stop words. Res. Compt. Sci. 18, 51\u2013162 (2006)","journal-title":"Res. Compt. Sci."},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Camacho-Collados, J., Pilevar, M.T.: On the role of text preprocessing in neural network architectures: an evaluation study on text categorization and sentiment analysis. In: Proceedings of 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 40\u201346 (2018)","DOI":"10.18653\/v1\/W18-5406"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Al Sharou, K., Li, Z., Specia, L.: Towards a better understanding of noise in natural language processing. In: Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pp. 53\u201362, Held Online. INCOMA Ltd. (2021)","DOI":"10.26615\/978-954-452-072-4_007"},{"key":"14_CR12","unstructured":"Przybyla, O.: Issues of polish question answering. In: Proceedings of 1st Conference Information Technologies: Research and their Interdisciplinary Applications (ITRIA 2012), pp. 96\u2013102 (2012)"},{"key":"14_CR13","unstructured":"Dzmitry, B., Cho K., Bengio, I.: Neural machine translation by jointly learning to align and translate. In: Proceedings of 3rd International Conference on Learning Representations, ICLR 2015, San Diego (2015)"},{"key":"14_CR14","unstructured":"Aitken, K., Ramasesh, V., Cao, Y., Maheswaranathan, N.: Understanding how encoder-decoder architectures attend. In: proceedings of 35th Conference on Neural Information Processing Systems (NeurIPS 2021) (2021)"},{"key":"14_CR15","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of 31st Conference on Neural Information Processing Systems (NIPS 2017), USA (2017)"},{"key":"14_CR16","doi-asserted-by":"publisher","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. In: Neural Computation, vol. 9, pp. 1735\u201380 (1998). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"14_CR17","unstructured":"Tab-delimited Bilingual Sentence Pairs dataset page. http:\/\/www.manythings.org\/anki\/. Accessed 1 Feb 2023"},{"key":"14_CR18","unstructured":"Emotion Dataset for Emotion Recognition Tasks. https:\/\/www.kaggle.com\/datasets\/parulpandey\/emotion-dataset. Accessed 1 Feb 2023"},{"key":"14_CR19","doi-asserted-by":"publisher","unstructured":"Piorkowska, M., Wrobel, M.: Basic emotions. In: Encyclopedia of Personality and Individual Differences, Editors: Zeigler-Hill, V. and Shackelford, T.K (2017). https:\/\/doi.org\/10.1007\/978-3-319-28099-8-495-1","DOI":"10.1007\/978-3-319-28099-8-495-1"},{"key":"14_CR20","unstructured":"Stop words documentation. https:\/\/pypi.org\/project\/stop-words\/. Accessed 1 Feb 2023"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Kieras, W., Wolinski, M.: (In Polish) Morfeusz 2 - analizator i generator fleksyjny dla jezyka polskiego. Jezyk Polski, XCVI I(1), 75\u201383 (2017)","DOI":"10.31286\/JP.97.1.7"},{"key":"14_CR22","unstructured":"Pandas documentation. https:\/\/pandas.pydata.org\/. Accessed 1 Feb 2023"},{"key":"14_CR23","unstructured":"Gensim documentation. https:\/\/pypi.org\/project\/gensim\/. Accessed 1 Feb 2023"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Yadav, S., Shukla, S.: Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification. In: Proceedings of IEEE 6th International Conference on Advanced Computing (IACC), pp. 78\u201383 (2016)","DOI":"10.1109\/IACC.2016.25"},{"key":"14_CR25","unstructured":"Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: Proceedings of 31st International Conference on Machine Learning, ICML (2014)"},{"key":"14_CR26","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Proceedings of International Conference on Learning Representations (2013)"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-36027-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T08:04:43Z","timestamp":1688025883000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-36027-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031360268","9783031360275"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-36027-5_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"26 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2023\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"530","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":"188","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":"94","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":"35% - 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":"2,8","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":"3,2","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)"}}]}}