6 results
Search Results
Now showing 1 - 6 of 6
Item Open Access SENTIMENT ANALYSIS OF UNIVERSITY FEEDBACK OPINION OF STUDENTS ABOUT AN EDUCATIONAL PART IN KAZAKH LANGUAGE USING MULTIBINOMIAL NAIVE BAYES CLASSIFIER(СДУ хабаршысы - 2019, 2019) A. Serek; M. ZhaparovAbstract. In this paper, the system which identifies the sentiment, (aka meaning) of a kazakh phrase, (whether it is a positive, or a negative) have been implemented using MultiBinomial Naive Bayes Classifier and achieved accuracy approximately 71 % on the dataset about university feedback across students on its educational component in order to help administrative staff to evaluate the current state of education in the university and make some decisions on its basis. We consider it to be a good result, given that the data was small in size, so that there were only few collected samples. The importance of the work that we did not find any paper which performed sentiment analysis using MultiBinomial Naive Bayes classifier on an agglutinative language. It can be argued, that the model can be successfully generalized in other educational organizations pursuing the same cause as it was identified in the above-mentioned rationale. The limitation of the paper is that only one algorithm has been applied to it, and the dataset size is small.Item Open Access DETECTING SOCIAL CONFLICTS IN KINDERGARTENS USING DEEPLEARNING AND COMPUTER VISION(SDU University, 2025) Dina KengesbayEarly conflict detection in kindergartens plays a significant role in ensuring a harmonious learningatmosphere and in promoting the social growth of young children. While most previous works have onlyaddressed conflict detection through adults, in this paper, we specifically address conflict detection inkindergartens using deep learning, utilizing both spatial and temporal information to improve performance.The application of deep learning and computer vision in automatically detecting and analyzing earlyconflicts among young children is discussed in this paper. Using video footage, we leverage state-of-the-art RNNs and 3D CNNs for high-accuracy detection of conflict instances. Crucial visual cues—facialexpressions, gestures, poses, vocal tone, and movement—are examined for the extraction of tension oraggression signs. The model is evaluated on real kindergarten video data, with promising conflict detectionand classification results. The findings indicate the potential of AI-supported tools in assisting teachers inclass management, child behavior monitoring, early intervention mechanisms, and the fostering of a goodsocial environment.Item Open Access KAZAKH NAMES GENERATOR USING DEEP LEARNING(ВЕСТНИК КАЗАХСТАНСКО-БРИТАНСКОГО ТЕХНИЧЕСКОГО УНИВЕРСИТЕТА, №4, 2020) Nurmambetov D.; Dauylov S.; Bogdanchikov A.In recent years, sentiment analysis of e-mail messages or social media posts is becoming very popular. It can help people define if they are reading something positive or negative. On the same time, there are some services on the Internet that can help you find or create a new name. When processing the creation, they check the name in other popular languages, so your name does not mean inappropriate things in other languages. For this they bill for 25 thousand US dollars. If there are such services, then there is a demand. In this study, sentiment analysis of e-mails was implemented with using StanfordNLP [1] lemmatizer and classic machine learning algorithms as a classifier. It is applied to real e-mails from Russian speaking mailbox, which means there are both English and Russian messages. Thus, language identification is also added as preprocessing step. In this study only binary sentiment analysis was made, but it can be improved with adding several emotions to be detected. Then another model generates Kazakh names using neural networks, where all Kazakh names data has been collected through various websites. The sentiment analysis model gives 81% accuracy and the joint use of two models allow us to generate new Kazakh names, which are checked with Russian language if they mean something inappropriate. The result can be improved with checking with other languages.Item Open Access REALIZATION OF ALGORITHM OF SELF-GENERATING NEURAL NETWORKS(Faculty of Engineering and Natural Sciences, 2019) Abdikhaliyev Y.The development of various spheres of human activity is associated with the generation and accumulation of a huge amount of data that can contain the most important practical information. However, significant benefit from this information can be extracted only with proper processing and analysis of this data. Recently, there has been an increased interest in the field of artificial intelligence, and methods of automating the extraction of knowledge based on data mining are actively developing. Self-generating neural networks are built on the principle of biological, of course, with a number of assumptions, they have a huge number of simple processes with many connections. Like the human brain, these networks | are capable of learning. Self-generating neural networks find their application in areas such as computer vision, speech recognition, processing of natural language, etc. The thesis provides an‘analysis of the development of the theory of neural networks, their classification and mathematical formulation of the task of recognizing pattern recognition.Item Open Access COMPARISON OF DIFFERENT CLASSIFICATION MODELS FOR SENTIMENT ANALYSIS(СДУ хабаршысы - 2023, 2023) Makhul M.Abstract. In this work, we explored sentiment analysis techniques of texts using the example of product comments in the Kazakh language. To do this, we used machine learning methods such as Naive Bayes, Random Forest, Logistic Regression and Support Vector Machine, as well as text processing tools: CountVectorizer and TfidfVectorizer. In the process of work, experiments were carried out with different configurations of models and parameters of vectorizers. To assess the quality of the models, we used accuracy, precision, recall and F1-score metrics. The research findings indicated that the application of machine learning techniques make it possible to achieve high accuracy in sentiment analysis of comments. The best results were obtained using the Support Vector Machine and TfidfVectorizer. This study can be used to further improve the systems for sentiment analysis of comments in the Kazakh language, which can be useful in monitoring public opinion in various areas, including business.Item Open Access FAST AND RELATIVELY ACCURATE SENTIMENT ANALYSIS FOR THE KAZAKH LANGUAGE(2022 International Young Scholars' Conference, 2022) N. ManteyevaAbstract This paper constructs a fast and accurate sentiment analysis model for the Kazakh language. The main method for text classification is based on TF-IDF-based tokens trained with Logistic Regression. The processing and modeling stages are fully implemented in the PySpark framework. The proposed method has shown an accuracy level of 82% on an evenly distributed test dataset. As a byproduct of the work, we have collected a list of words in the Kazakh language that could signal the negativity/positivity of the given review.