{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T08:30:31Z","timestamp":1762072231202,"version":"build-2065373602"},"reference-count":30,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T00:00:00Z","timestamp":1666569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>The rapid development of natural language processing and deep learning techniques has boosted the performance of related algorithms in several linguistic and text mining tasks. Consequently, applications such as opinion mining, fake news detection or document classification that assign documents to predefined categories have significantly benefited from pre-trained language models, word or sentence embeddings, linguistic corpora, knowledge graphs and other resources that are in abundance for the more popular languages (e.g., English, Chinese, etc.). Less represented languages, such as the Kazakh language, balkan languages, etc., still lack the necessary linguistic resources and thus the performance of the respective methods is still low. In this work, we develop a model that classifies scientific papers written in the Kazakh language using both text and image information and demonstrate that this fusion of information can be beneficial for cases of languages that have limited resources for machine learning models\u2019 training. With this fusion, we improve the classification accuracy by 4.4499% compared to the models that use only text or only image information. The successful use of the proposed method in scientific documents\u2019 classification paves the way for more complex classification models and more application in other domains such as news classification, sentiment analysis, etc., in the Kazakh language.<\/jats:p>","DOI":"10.3390\/bdcc6040123","type":"journal-article","created":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T08:19:06Z","timestamp":1666599546000},"page":"123","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Classification of Scientific Documents in the Kazakh Language Using Deep Neural Networks and a Fusion of Images and Text"],"prefix":"10.3390","volume":"6","author":[{"given":"Andrey","family":"Bogdanchikov","sequence":"first","affiliation":[{"name":"Department of Computer Science, Suleyman Demirel University, Kaskelen 040900, Kazakhstan"}]},{"given":"Dauren","family":"Ayazbayev","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Suleyman Demirel University, Kaskelen 040900, Kazakhstan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0876-8167","authenticated-orcid":false,"given":"Iraklis","family":"Varlamis","sequence":"additional","affiliation":[{"name":"Department of Informatics and Telematics, Harokopio University of Athens, 17779 Athenes, Greece"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1007\/s00778-003-0100-6","article-title":"THESUS: Organizing Web document collections based on link semantics","volume":"12","author":"Halkidi","year":"2003","journal-title":"VLDB J."},{"key":"ref_2","first-page":"167","article-title":"Improving information retrieval using document clusters and semantic synonym extraction","volume":"36","author":"Bharathi","year":"2012","journal-title":"J. Theor. Appl. Inf. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/jdwm.2007070101","article-title":"Multi-label classification: An overview","volume":"3","author":"Tsoumakas","year":"2007","journal-title":"Int. J. Data Warehous. Min. (IJDWM)"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kowsari, K., Jafari Meimandi, K., Heidarysafa, M., Mendu, S., Barnes, L., and Brown, D. (2019). Text classification algorithms: A survey. Information, 10.","DOI":"10.3390\/info10040150"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1016\/j.ipm.2019.05.003","article-title":"The impact of deep learning on document classification using semantically rich representations","volume":"56","author":"Kastrati","year":"2019","journal-title":"Inf. Process. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"87562","DOI":"10.1109\/ACCESS.2020.2993191","article-title":"Graph-based text representation and matching: A review of the state of the art and future challenges","volume":"8","author":"Osman","year":"2020","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Babi\u0107, K., Martin\u010di\u0107-Ip\u0161i\u0107, S., and Me\u0161trovi\u0107, A. (2020). Survey of neural text representation models. Information, 11.","DOI":"10.3390\/info11110511"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Deoras, A., Povey, D., Burget, L., and \u010cernock\u00fd, J. (2011, January 11\u201315). Strategies for training large scale neural network language models. Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, Waikoloa, HI, USA.","DOI":"10.1109\/ASRU.2011.6163930"},{"key":"ref_9","unstructured":"Pollak, S., and Pelicon, A. (2022, January 1\u20133). EMBEDDIA project: Cross-Lingual Embeddings for Less-Represented Languages in European News Media. Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, Ghent, Belgium."},{"key":"ref_10","unstructured":"Ul\u010dar, M., and Robnik-\u0160ikonja, M. (2019). High quality ELMo embeddings for seven less-resourced languages. In Proceedings of the 12th Conference on Language Resources and Evaluation, Marseille, France, 13\u201315 May 2020; pp. 4731\u20134738. arXiv."},{"key":"ref_11","unstructured":"Khusainova, A., Khan, A., and Rivera, A.R. (2019). Sart-similarity, analogies, and relatedness for tatar language: New benchmark datasets for word embeddings evaluation. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yessenbayev, Z., Kozhirbayev, Z., and Makazhanov, A. (2020, January 7\u20138). KazNLP: A pipeline for automated processing of texts written in Kazakh language. Proceedings of the International Conference on Speech and Computer, St. Petersburg, Russia.","DOI":"10.1007\/978-3-030-60276-5_63"},{"key":"ref_13","unstructured":"Makhambetov, O., Makazhanov, A., Yessenbayev, Z., Matkarimov, B., Sabyrgaliyev, I., and Sharafudinov, A. (2013, January 18\u201321). Assembling the kazakh language corpus. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Seattle, WA, USA."},{"key":"ref_14","unstructured":"Makazhanov, A., Sultangazina, A., Makhambetov, O., and Yessenbayev, Z. (2015, January 17\u201319). Syntactic annotation of kazakh: Following the universal dependencies guidelines. Proceedings of the 3rd International Conference on Computer Processing in Turkic Languages, Kazan, Russia."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yelibayeva, G., Sharipbay, A., Bekmanova, G., and Omarbekova, A. (2021, January 5\u20137). Ontology-Based Extraction of Kazakh Language Word Combinations in Natural Language Processing. Proceedings of the International Conference on Data Science, E-learning and Information Systems 2021, Petra, Jordan.","DOI":"10.1145\/3460620.3460631"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Haisa, G., and Altenbek, G. (2022). Deep Learning with Word Embedding Improves Kazakh Named-Entity Recognition. Information, 13.","DOI":"10.3390\/info13040180"},{"key":"ref_17","unstructured":"Cai, Y.L., Ji, D., and Cai, D. (2010, January 15\u201318). A KNN Research Paper Classification Method Based on Shared Nearest Neighbor. Proceedings of the NTCIR-8 Workshop Meeting, Tokyo, Japan."},{"key":"ref_18","unstructured":"Zhang, M., Gao, X., Cao, M.D., and Ma, Y. (September, January 30). Neural networks for scientific paper classification. Proceedings of the First International Conference on Innovative Computing, Information and Control-Volume I (ICICIC\u201906), Beijing, China."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"12082","DOI":"10.1088\/1742-6596\/1235\/1\/012082","article-title":"Scientific documents classification using support vector machine algorithm","volume":"1235","author":"Jaya","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1186\/s13673-019-0192-7","article-title":"Research paper classification systems based on TF-IDF and LDA schemes","volume":"9","author":"Kim","year":"2019","journal-title":"Hum.-Cent. Comput. Inf. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1007\/s11192-019-03206-9","article-title":"P2V: Large-scale academic paper embedding","volume":"121","author":"Zhang","year":"2019","journal-title":"Scientometrics"},{"key":"ref_22","first-page":"108","article-title":"Domain-specific word embeddings for patent classification","volume":"53","author":"Risch","year":"2019","journal-title":"Data Technol. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1007\/s11192-022-04419-1","article-title":"A multi-view method of scientific paper classification via heterogeneous graph embeddings","volume":"127","author":"Lv","year":"2022","journal-title":"Scientometrics"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.patrec.2022.02.015","article-title":"Exploring multi-tasking learning in document attribute classification","volume":"157","author":"Mondal","year":"2022","journal-title":"Pattern Recognit. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Harisinghaney, A., Dixit, A., Gupta, S., and Arora, A. (2014, January 6\u20138). Text and image based spam email classification using KNN, Na\u00efve Bayes and Reverse DBSCAN algorithm. Proceedings of the 2014 International Conference on Reliability Optimization and Information Technology (ICROIT), Faridabad, India.","DOI":"10.1109\/ICROIT.2014.6798302"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Audebert, N., Herold, C., Slimani, K., and Vidal, C. (2019). Multimodal deep networks for text and image-based document classification. In Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, W\u00fcrzburg, Germany, 16\u201320 September 2019; pp. 427\u2013443. arXiv.","DOI":"10.1007\/978-3-030-43823-4_35"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"i468","DOI":"10.1093\/bioinformatics\/btab331","article-title":"Utilizing image and caption information for biomedical document classification","volume":"37","author":"Li","year":"2021","journal-title":"Bioinformatics"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"baaa024","DOI":"10.1093\/database\/baaa024","article-title":"Integrating image caption information into biomedical document classification in support of biocuration","volume":"2020","author":"Jiang","year":"2020","journal-title":"Database"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Kaur, G., Kaushik, A., and Sharma, S. (2019). Cooking is creating emotion: A study on hinglish sentiments of youtube cookery channels using semi-supervised approach. Big Data Cogn. Comput., 3.","DOI":"10.3390\/bdcc3030037"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Shah, S.R., Kaushik, A., Sharma, S., and Shah, J. (2020). Opinion-mining on marglish and devanagari comments of youtube cookery channels using parametric and non-parametric learning models. Big Data Cogn. Comput., 4.","DOI":"10.3390\/bdcc4010003"}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/6\/4\/123\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:01:37Z","timestamp":1760144497000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/6\/4\/123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,24]]},"references-count":30,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["bdcc6040123"],"URL":"https:\/\/doi.org\/10.3390\/bdcc6040123","relation":{},"ISSN":["2504-2289"],"issn-type":[{"type":"electronic","value":"2504-2289"}],"subject":[],"published":{"date-parts":[[2022,10,24]]}}}