O‘ZBEK TILI MATNLARINI LOGISTIK REGRESSIYA USULI ASOSIDA SENTIMENT TAHLIL QILISH

Botir Elov; Abdulla Abdullayev

Авторы

Botir Elov Alisher Navoiy nomidagi Toshkent davlat o‘zbek tili va adabiyoti universiteti
Abdulla Abdullayev Urganch innovatsion university

Ключевые слова:

Logistik Regressiya, sentiment tahlil, mashinali o‘qitish, NLP oʻzbek tili matnlari, TF-IDF vektorizatsiyasi, L2 regulyarizatsiyasi, maʼlumotlar toʻplami (dataset), aniqlik (Accuracy)

Аннотация

Sentiment tahlili matnlarning hissiy ohangini aniqlashda muhim ahamiyatga ega bo‘lib, ushbu tadqiqotda Logistik Regressiya (Logistic Regression, LR) usuli yordamida o‘zbek tili matnlarining hissiy ohangi tahlil qilinadi. Tadqiqotning asosiy maqsadi o‘zbek tili matnlarini ijobiy, salbiy yoki neytral toifalarga ajratish uchun LR modelini qo‘llash va uning samaradorligini baholashdan iborat. Ushbu maqsadga erishish uchun o‘zbek tili milliy korpusidan olingan matnlar to‘plami ishlatilib, matnlar avval tozalangan va tokenizatsiya qilingan. Modelni o‘qitish jarayonida matnlarning vektorlashtirilgan ko‘rinishini yaratish uchun TF-IDF usuli qo‘llanilgan. Tadqiqot natijalari shuni ko‘rsatadiki, LR usuli o‘zbek tili matnlarini sentiment tahlil qilishda 77.88% dan yuqori aniqlik va yuqori F1-score ko‘rsatkichlariga erishgan. Modelning samaradorligini oshirish maqsadida turli parametrlar sinovdan o‘tkazilgan hamda matnni oldindan qayta ishlash usullari optimallashtirilgan. Ushbu tadqiqot o‘zbek tili uchun sentiment tahlilining kelajakdagi rivojlanishiga hissa qo‘shadi va LR usulining boshqa tillardagi samaradorligi bilan taqqoslash imkonini beradi. Shuningdek, maqolada modelning cheklovlari ko‘rsatilib, kelajakda chuqur o‘rganish usullarini qo‘llash bo‘yicha takliflar berilgan.

Библиографические ссылки

Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. arXiv preprint cs/0205070.

Cox, D. R. (1958). The regression analysis of binary sequences. Journal of the Royal Statistical Society Series B: Statistical Methodology, 20(2), 215-232.

Hastie, T., Tibshirani, R., Friedman, J. H., & Friedman, J. H. (2009). The elements of statistical learning: data mining, inference, and prediction (Vol. 2, pp. 1-758). New York: springer.

Ng, A. Y. (2004, July). Feature selection, L 1 vs. L 2 regularization, and rotational invariance. In Proceedings of the twenty-first international conference on Machine learning (p. 78).

Fan, R. E., Chang, K. W., Hsieh, C. J., Wang, X. R., & Lin, C. J. (2008). LIBLINEAR: A library for large linear classification. the Journal of machine Learning research, 9, 1871-1874.

Frank, E., & Bouckaert, R. R. (2006). Naive bayes for text classification with unbalanced classes. In Knowledge Discovery in Databases: PKDD 2006: 10th European Conference on Principles and Practice of Knowledge Discovery in Databases Berlin, Germany, September 18-22, 2006 Proceedings 10 (pp. 503-510). Springer Berlin Heidelberg.

Pimpalkar, A. (2022). MBiLSTMGloVe: Embedding GloVe knowledge into the corpus using multi-layer BiLSTM deep learning model for social media sentiment analysis. Expert Systems With Applications, 203, 117581.

Quesada, O., Lauzon, M., Buttle, R., Wei, J., Suppogu, N., Cook-Wiens, G., ... & Merz, C. N. B. (2023). Fitness attenuates long-term cardiovascular outcomes in women with ischemic heart disease and metabolic syndrome. American Journal of Preventive Cardiology, 14, 100498.

Xue, Y., Wang, X., & Gao, Z. (2019, November). Multi-classfication sentiment analysis based on the fused model. In 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI) (pp. 1771-1775). IEEE.

Elov, B. B., Khamroeva, S. M., Alayev, R. H., Khusainova, Z. Y., & Yodgorov, U. S. (2023). Methods of processing the uzbek language corpus texts. International Journal of Open Information Technologies, 11(12), 143-151.

Boltayeviç, E. B., Yuldashevna, X. Z., Mamurjonovna, U. S., Ermamatovich, N. S., Kızı, A. Ş. A., & Shavkatjon, M. (2024, October). Algorithms for Parsing Roots and Stems of Words in Uzbek Language. In 2024 9th International Conference on Computer Science and Engineering (UBMK) (pp. 126-130). IEEE.

Elov, B. (2024). MATNLI MA’LUMOTLARNI WORD2VEC, GLOVE VA FASTTEXT CHUQUR O ‘RGANISH USULLARI VOSITASIDA QAYTA ISHLASH. DIGITAL TRANSFORMATION AND ARTIFICIAL INTELLIGENCE, 2(5), 225-259.