Oliy va o’rta maxsus ta’lim vazirligi O’zbekiston milliy universiteti xorijiy filologiya fakulteti

Xulosa:

Xulosa qilib aytganda ijtimoiy tarmoqlarning tez sur'atlarda o'sib borishi shu qadar kengaydiki, ma’lumotlar hajmining har o'n sakkiz oyda ikki barobar oshishini ko'rsatmoqda. Fikrlarni tahlil qilish deb ham ataladigan sentiment tahlili tabiiy tilni qayta ishlashning eng faol tadqiqot yo'nalishlaridan biriga aylandi. Uning qo'llanilishi, biznes xizmatlaridan tortib, siyosiy kompaniyalargacha keng tarqalgan. Axborot urushlari paytida matnni avtomatik tahlil qilish eng muhim vazifalardan biridir.

XXI asrda jamoatchilik fikri hamma narsadan ustundir. U bilan hech narsa muvaffaqiyatsiz bo'lmaydi, usiz hech narsa muvaffaqiyatga erisha olmaydi.

Foydalanilgan adabiyotlar ro’yhati:

1. Sanatbek Matlatipov, Elmurod Kuriyozov, Miguel A.Alonso, Corlos Gomez Rodriguez. Deep learningvs. Classic Models on a New Uzbek Sentiment Analysis Dataset.// Journal HumanLanguage Technologies as a Challenge for Computer Science and Linguistics. 2019. Pages 258-262

2. E.Kuriyozov, S. Matlatipov. Building a new Sentiment Analysis Dataset for Uzbek Language and Creating Baseline Models.// Multidisciplinary Digital Publishing Institute Proceedings. 2019.-№1. Pages 37.

3. Bo Pang, Lillian Lee, Shivakumar Vaithyanathan Thumbs up? Sentiment Classification using Machine Learning Techniques // — 2002. — С. 79–86.

4. Abadi, Martin et al., 2015. TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org.

4. Barnes, Jeremy, Roman Klinger, Sabine Schulte im Walde, 2017. Assessing state-of-the-art sentiment models on state-of-art sentiment datasets. arXiv preprint arXiv: 1709.04219.

5. Chen, Yanqing and Steven Skiena, 2014. Buildingsentiment lexicons for all major languages. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Vol. 2: Short Papers). Baltimore,Maryland: Association for Computational Linguistics.

6. Гедранович, Б.А., Гедранович, А.Б. Отношение К Высшему Образованию: Сентимент-Анализ Данных Микроблогов. Инновационные Образовательные Технологии.-2013.-№ 1 (33).-С. 46-54. 7. Dehkharghani R., Saygin Y., Yanikoglu B. et al. SentiTurkNet: a Turkish polarity lexicon for sentiment analysis. Language Resources and Evaluation. -2016. 50. -P. 667–685 8. Bing Liu Sentiment Analysis and Opinion Mining Synthesis Lectures on Human Language Technologies, May 2012, Vol. 5, No. 1 , Pages 1-167 (https://www.doi.org/10.2200/S00416ED1V01Y201204HLT016 ) 9. Türkmenoğlu C., Tantuğ A. C. Conference: ICML 2014 (International Conference on Machine Learning) At: Beijing Volume: WISDOM'14 (Workshop on Issues of Sentiment Discovery and Opinion Mining)(ICML 2014, June 25th, Beijing) 10. Yergesh, B.; Bekmanova, G., Sharipbay A. Sentiment analysis of Kazakh text and their polarity. Web Intelligence, vol. 17, no. 1, pp. 9-15, 2019. 11. Юрганов А. А. Сентимент-Анализ Как Инструмент Исследования Текстов. Проблемы Современной Науки И Образования. -2017. -№ 29 (111). -С. 39-41 12. Посевкина Р. В. , Бессмертный И. А. Применение Сентимент-Анализа Текстов Для Оценки Общественного Мнения. Научно-Технический Вестник Информационных технологий, Механики И Оптики. -2015. -№ 1 (111). -С. 169-171. 13. Дуля Т. С. , Богданов А.Л. Сентимент-Анализ Коротких Русскоязычных Текстов в Социальных Медиа. Статья В Сборнике Трудов Конференции. -2018. С. -159-168 14. Loukachevitch N. V., Moscow, Russia., Rusnachenko N. L., Computational Linguistics аnd Intellectual Technologies. 2020. Pages 541-552 15. Кирсанов А. В. Google prediction. Как средство cентимент-анализа сообщения в социальных сетях. Наука. Техника и Образование /Science, technology and education. -2015, -№ 6 (12).