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’ 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’ 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.

This work focuses on determining semantically close words and using semantic similarity in general in order to improve performance in information retrieval tasks. The semantic similarity of words is an important task with many applications from information retrieval to spell checking or even document clustering and classification. Although, in languages with rich linguistic resources, the methods and tools for this task are well established, some languages do not have such tools. The first step in our experiment is to represent the words in a collection in a vector form and then define the semantic similarity of the terms using a vector similarity method. In order to tame the complexity of the task, which relies on the number of word (and, consequently, of the vector) pairs that have to be combined in order to define the semantically closest word pairs, A distributed method that runs on Apache Spark is designed to reduce the calculation time by running comparison tasks in parallel. Three alternative implementations are proposed and tested using a list of target words and seeking the most semantically similar words from a lexicon for each one of them. In a second step, we employ pre-trained multilingual sentence transformers to capture the content semantics at a sentence level and a vector-based semantic index to accelerate the searches. The code is written in MapReduce, and the experiments and results show that the proposed methods can provide an interesting solution for finding similar words or texts in the Kazakh language.

Sentiment analysis is increasingly pivotal in natural language processing (NLP), crucial for deciphering public opinions across diverse sectors. This research conducts a comparative examination of rule-based and machine learning (ML) methods in sentiment analysis, specifically targeting the Kazakh language. Given the Kazakh language's limited exposure in computational linguistics, the study meticulously evaluates datasets from news articles, literature, and Amazon product reviews, aiming to compare the efficiency, adaptability, and overall performance of these distinct approaches. Employing a detailed set of evaluation metrics such as accuracy, precision, recall, and computational efficiency, the study provides a comprehensive analysis of the strengths and limitations of rule-based techniques versus ML models like Logistic Regression, Multinomial Naive Bayes, Decision Trees, Random Forest, and XGBoost. The findings suggest rule-based methods excel in identifying nuanced emotional expressions within literary texts, while ML models demonstrate superior adaptability and robustness, particularly effective in handling the linguistic variations found in news and reviews. Despite the strengths identified, the study also reveals significant limitations of the rule-based approach, especially in broader contexts beyond literary analysis. This highlights an imperative for future research to integrate sentiment dictionaries or domain-specific lexicons that cater to a wider array of linguistic styles, potentially enhancing sentiment analysis tools' applicability in Kazakh and similar less-studied languages. This investigation contributes significantly to the sentiment analysis discourse, offering invaluable insights for both researchers and practitioners by elucidating the complexities of applying NLP technologies across diverse linguistic landscapes, thus advancing the understanding and methodologies of sentiment analysis in the Kazakh language context.