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.

Distributed Systems are widely used in industrial projects and scientific research. The Apache Hadoop environment, which works on the MapReduce paradigm, lost popularity because new, modern tools were developed. For example, Apache Spark is preferred in some cases since it uses RAM resources to hold intermediate calculations; therefore, it works faster and is easier to use. In order to take full advantage of it, users must think about the MapReduce concept. In this paper, a usual solution and MapReduce solution of ten problems were compared by their pseudocodes and categorized into five groups. According to these groups’ descriptions and pseudocodes, readers can get a concept of MapReduce without taking specific courses. This paper proposes a five-category classification methodology to help distributed-system users learn the MapReduce paradigm fast. The proposed methodology is illustrated with ten tasks. Furthermore, statistical analysis is carried out to test if the proposed classification methodology affects learner performance. The results of this study indicate that the proposed model outperforms the traditional approach with statistical significance, as evidenced by a p-value of less than 0.05. The policy implication is that educational institutions and organizations could adopt the proposed classification methodology to help learners and employees acquire the necessary knowledge and skills to use distributed systems effectively.

This research introduces a novel recommender system for adapting single-machine problems to distributed systems within the MapReduce (MR) framework, integrating knowledge and text-based approaches. Categorizing common problems by five MR categories, the study develops and tests a tutorial with promising results. Expanding the dataset, machine learning models recommend solutions for distributed systems. Results demonstrate the logistic regression model's effectiveness, with a hybrid approach showing adaptability. The study contributes to advancing the adaptation of single-machine problems to distributed systems MR, presenting a novel framework for tailored recommendations, thereby enhancing scalability and efficiency in data processing workflows. Additionally, it fosters innovation in distributed computing paradigms.