kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университет10.55452/1998-6688-2023-20-4-10-26kaz29-860Research ArticleКОМПЬЮТЕРНЫЕ НАУКИCOMPUTER SCIENCEОТ СЛОВ К ПАРАГРАФАМ: МОДЕЛИРОВАНИЕ ДИНАМИКИ НАСТРОЕНИЙ В «ЗАПИСКАХ ИЗ ПОДПОЛЬЯ» С ПОМОЩЬЮ GPT-4 ЧЕРЕЗ ОПИСАТЕЛЬНЫЕ МЕТОДЫ И ДИФФЕРЕНЦИАЛЬНЫЕ УРАВНЕНИЯFrom words to paragraphs: modeling sentiment dynamics in ‘notes from underground’ with GPT-4 via descriptive methods and differential equationshttps://orcid.org/0000-0003-0692-0265ДюранВ.DuranV.

факультет психологии

76000, г. Ыгдыр

Psychology Department

76000, Iğdır

volkan.duran8@gmail.comhttps://orcid.org/0000-0001-9886-244XХазарЭ.HazarE.

Математический факультет

76000, г. Ыгдыр

Mathematics Department

76000, Iğdır

elman.hazar@igdir.edu.trhttps://orcid.org/0000-0002-3221-9352АхметовИ.AkhmetovI.

050000, г. Алматы, ул. Курмангазы, 29

29 Kurmangazy St., Almaty, 050000

i.akhmetov@kbtu.kzhttps://orcid.org/0000-0002-8685-9355ПакА.PakA.

050000, г. Алматы, ул. Курмангазы, 29

29 Kurmangazy St., Almaty, 050000

a.pak@kbtu.kzУниверситет ЫгдырТурцияIğdır UniversityTurkeyИнститут информационных и вычислительных технологий (ИИВТ)КазахстанInstitute of Information and Computational Technologies (IICT)Kazakhstan2023201220232041026Copyright © Дюран В., Хазар Э., Ахметов И., Пак А., 20232023Дюран В., Хазар Э., Ахметов И., Пак А.Duran V., Hazar E., Akhmetov I., Pak A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/860

В данном исследовании рассматривается, как изменяются значения настроения в первой части книги «Записки из подполья» Федора Достоевского, озаглавленной как «Подполье», от слов к предложениям и абзацам. Используя языковую модель GPT-4, мы провели описательный анализ стандартизированных значений настроения и рассчитали кумулятивные траектории настроения по тексту. Затем мы создали модели дифференциальных уравнений для моделирования оттенков настроения с помощью регрессионного анализа. Полученные нами результаты свидетельствуют о том, что от слов к абзацам настроение становится менее негативным, что указывает на то, что контекст регулирует негативность. Настроение абзацев также было более стабильным и отличалось меньшей вариативностью. Наблюдалась дуга повествования с первоначальным снижением, за которым следовал подъем настроения. Абзацы имели самые высокие исходные настроения, что говорит о том, что они способны отражать более тонкий контекст. Абзацы быстро теряли краткосрочное настроение, но дольше всего сохраняли долгосрочное настроение, что согласуется с тем, что абзацы сохраняют общее настроение текста с течением времени. Полученные результаты позволяют предположить, что существует сложная динамика между языковыми единицами, способствующая ощутимой стабильности настроения. Количественные показатели распада являются полезными индикаторами, но не в полной мере характеризуют стабильность настроения.

This study examines how the sentiment values in the first part of the book entitled as “Underground” of Fyodor Dostoevsky’s “Notes from Underground” change from words to sentences to paragraphs. Using the GPT-4 language model, we conducted a descriptive analysis of standardized sentiment values and calculated cumulative sentiment trajectories over the text. We then created differential equation models to model the sentiment tones using regression analysis. Our findings suggest that sentiment becomes less negative from words to paragraphs, indicating that context moderates negativity. Paragraph sentiment was also more stable with lower variability. There was a narrative arc of initial decline followed by an upward turn in sentiment. Paragraphs had the highest baseline sentiment, suggesting that they are able to capture more nuanced context. Paragraphs lost short-term sentiment quickly but retained longterm sentiment longest, aligning with paragraphs maintaining overall text sentiment over time. These findings suggest that there are complex dynamics between linguistic units contributing to perceived stability of sentiment. Quantitative decay rates are useful indicators but do not fully characterize sentiment stability.

анализ настроенийдифференциальные уравненияGPT-4аппроксимация кривойиерархический регрессионный анализSentiment analysisdifferential equationsGPT-4curve fittinghierarchical regression analysisThis research is conducted within the Committee of Science of the Ministry of Education and Science of the Republic of Kazakhstan under the grant number AP09260670 “Development of methods and algorithms for augmentation of input data for modifying vector embeddings of words”.ReferencesMisuraca M., Forciniti A., Scepi G., Spano M. (2020) Sentiment Analysis for Education with R: packages, methods and practical applications. arXiv:2005,12840.Misuraca M., Forciniti A., Scepi G., Spano M. (2020) Sentiment Analysis for Education with R: packages, methods and practical applications. arXiv:2005,12840.Dietz-Uhler B. & Hurn E.J. (2013) Using learning analytics to predict (and improve) student success: A faculty perspective. Journal of Interactive Online Learning, 12, pp. 17–26.Dietz-Uhler B. & Hurn E.J. (2013) Using learning analytics to predict (and improve) student success: A faculty perspective. Journal of Interactive Online Learning, 12, pp. 17–26.Liu B. (2012) Sentiment Analysis and Opinion Mining. https://www.cs.uic.edu/~liub/FBS/SentimentAnalysis-and-OpinionMining.pdf.Liu B. (2012) Sentiment Analysis and Opinion Mining. https://www.cs.uic.edu/~liub/FBS/SentimentAnalysis-and-OpinionMining.pdf.Wankhade M., Rao A.C.S. & Kulkarni C. (2022) A survey on sentiment analysis methods, applications, and challenges. Artif Intell Rev 55, pp. 5731–5780. https://doi.org/10.1007/s10462-022-10144-1.Wankhade M., Rao A.C.S. & Kulkarni C. (2022) A survey on sentiment analysis methods, applications, and challenges. Artif Intell Rev 55, pp. 5731–5780. https://doi.org/10.1007/s10462-022-10144-1.Xing FZ, Cambria E., Welsch RE (2018) Natural language based financial forecasting: a survey. Artif Intell Rev 50(1), pp. 49–73.Xing FZ, Cambria E., Welsch RE (2018) Natural language based financial forecasting: a survey. Artif Intell Rev 50(1), pp. 49–73.Collomb A., Costea C., Joyeux D., Hasan O., Brunie L. (2014) A Study and Comparison of Sentiment Analysis Methods for Reputation Evaluation. Rapport de Recherche RR-LIRIS-2014-002.Collomb A., Costea C., Joyeux D., Hasan O., Brunie L. (2014) A Study and Comparison of Sentiment Analysis Methods for Reputation Evaluation. Rapport de Recherche RR-LIRIS-2014-002.Hemmatian F., Sohrabi MK (2019). A survey on classification techniques for opinion mining and sentiment analysis. Artif Intell Rev 52(3), pp. 1495–1545. https://doi.org/10.1007/s10462-017-9599-6.Hemmatian F., Sohrabi MK (2019). A survey on classification techniques for opinion mining and sentiment analysis. Artif Intell Rev 52(3), pp. 1495–1545. https://doi.org/10.1007/s10462-017-9599-6.Pontiki M. et al. (2016) SemEval-2016 task 5: aspect based sentiment analysis. In: Proceedings of the 10th international workshop on semantic evaluation (SemEval-2016), Association for Computational Linguistics, San Diego, CA, pp. 19–30.Pontiki M. et al. (2016) SemEval-2016 task 5: aspect based sentiment analysis. In: Proceedings of the 10th international workshop on semantic evaluation (SemEval-2016), Association for Computational Linguistics, San Diego, CA, pp. 19–30.Yadav A., Vishwakarma DK (2020) Sentiment analysis using deep learning architectures: a review. Artif Intell Rev 53(6), pp. 4335–4385.Yadav A., Vishwakarma DK (2020) Sentiment analysis using deep learning architectures: a review. Artif Intell Rev 53(6), pp. 4335–4385.Do H.H., Prasad P., Maag A., Alsadoon A. (2019) Deep learning for aspect-based sentiment analysis: a comparative review. Expert Syst Appl 118, pp. 272–299.Do H.H., Prasad P., Maag A., Alsadoon A. (2019) Deep learning for aspect-based sentiment analysis: a comparative review. Expert Syst Appl 118, pp. 272–299.Zhang L., Wang S., Liu B. (2018) Deep learning for sentiment analysis: a survey. Wiley Interdiscip Rev 8(4), pp. e1253.Zhang L., Wang S., Liu B. (2018) Deep learning for sentiment analysis: a survey. Wiley Interdiscip Rev 8(4), pp. e1253.Maglogiannis I. et al. (2020) A deep learning approach to aspect-based sentiment prediction. In: Artificial intelligence applications and innovations16th IFIP WG 125 international conference, AIAI 2020, Neos Marmaras, Greece, June 5–7, 2020. Proceedings, Part I 583, pp. 397–408.Maglogiannis I. et al. (2020) A deep learning approach to aspect-based sentiment prediction. In: Artificial intelligence applications and innovations16th IFIP WG 125 international conference, AIAI 2020, Neos Marmaras, Greece, June 5–7, 2020. Proceedings, Part I 583, pp. 397–408.Meškelė D., Frasincar F. (2020) Aldonar: a hybrid solution for sentence-level aspect-based sentiment analysis using a lexicalized domain ontology and a regularized neural attention model. Inf Process Manag 57(3), pp. 102211. https://doi.org/10.1016/j.ipm.2020.102211.Meškelė D., Frasincar F. (2020) Aldonar: a hybrid solution for sentence-level aspect-based sentiment analysis using a lexicalized domain ontology and a regularized neural attention model. Inf Process Manag 57(3), pp. 102211. https://doi.org/10.1016/j.ipm.2020.102211.Schouten K. & Frasincar F. (2018) Ontology-driven sentiment analysis of product and service aspects. In 15th Extended Semantic Web Conference (ESWC 2018), LNCS, Springer International Publishing ,vol. 10360, pp. 608–623.Schouten K. & Frasincar F. (2018) Ontology-driven sentiment analysis of product and service aspects. In 15th Extended Semantic Web Conference (ESWC 2018), LNCS, Springer International Publishing ,vol. 10360, pp. 608–623.Birjali M., Kasri M., Beni-Hssane A. (2021) A comprehensive survey on sentiment analysis: approaches, challenges and trends. Knowl-Based Syst 226, pp. 107134.Birjali M., Kasri M., Beni-Hssane A. (2021) A comprehensive survey on sentiment analysis: approaches, challenges and trends. Knowl-Based Syst 226, pp. 107134.Leippold, M. (2023) Sentiment spin: Attacking financial sentiment with GPT-3. Finance Research Letters. https://doi.org/10.1016/j.frl.2023.103957.Leippold, M. (2023) Sentiment spin: Attacking financial sentiment with GPT-3. Finance Research Letters. https://doi.org/10.1016/j.frl.2023.103957.Fan, David P., Cook, R. Dennis (2003) A differential equation model for predicting public opinions and behaviors from persuasive information: Application to the index of consumer sentiment. The Journal of Mathematical Sociology, 27(1), pp. 29–51. doi:10.1080/00222500305886.Fan, David P., Cook, R. Dennis (2003) A differential equation model for predicting public opinions and behaviors from persuasive information: Application to the index of consumer sentiment. The Journal of Mathematical Sociology, 27(1), pp. 29–51. doi:10.1080/00222500305886.Casillo M. et al. (2020) Chat-bot: a cultural heritage aware teller-bot for supporting touristic experiences. Pattern Recogn Lett 131, pp. 234–243. https://doi.org/10.1016/j.patrec.2020.01.003.Casillo M. et al. (2020) Chat-bot: a cultural heritage aware teller-bot for supporting touristic experiences. Pattern Recogn Lett 131, pp. 234–243. https://doi.org/10.1016/j.patrec.2020.01.003.Chang M. et al. (2020) Building ontology-driven tutoring models for intelligent tutoring systems using data mining. IEEE Access 8, pp. 48151–48162. https://doi.org/10.1109/ACCESS.2020.2979281.Chang M. et al. (2020) Building ontology-driven tutoring models for intelligent tutoring systems using data mining. IEEE Access 8, pp. 48151–48162. https://doi.org/10.1109/ACCESS.2020.2979281.Colace F. de Santo M., Greco L. (2014) Safe: a sentiment analysis framework for e-learning. Int J Emerg Technol Learn 9(6), pp. 37–41. https://doi.org/10.3991/ijet.v9i6.4110.Colace F. de Santo M., Greco L. (2014) Safe: a sentiment analysis framework for e-learning. Int J Emerg Technol Learn 9(6), pp. 37–41. https://doi.org/10.3991/ijet.v9i6.4110.D’Aniello G., Gaeta M. & La Rocca I. (2022) KnowMIS-ABSA: an overview and a reference model for applications of sentiment analysis and aspect-based sentiment analysis. Artif Intell Rev 55, pp. 5543–5574. https://doi.org/10.1007/s10462-021-10134-9.D’Aniello G., Gaeta M. & La Rocca I. (2022) KnowMIS-ABSA: an overview and a reference model for applications of sentiment analysis and aspect-based sentiment analysis. Artif Intell Rev 55, pp. 5543–5574. https://doi.org/10.1007/s10462-021-10134-9.Chen Z., Liu Y. & Sun H. (2021) Physics-informed learning of governing equations from scarce data. Nat Commun 12. https://doi.org/10.1038/s41467-021-26434-1.Chen Z., Liu Y. & Sun H. (2021) Physics-informed learning of governing equations from scarce data. Nat Commun 12. https://doi.org/10.1038/s41467-021-26434-1.Belsley D.A., Kuh E. & Welsch R.E. (1980) Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. New York: Wiley.Belsley D.A., Kuh E. & Welsch R.E. (1980) Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. New York: Wiley.Alpar R. (2022) Uygulamalı İstatistik ve Geçerlik Güvenirlik. Ankara: Detay Yayıncılık.Alpar R. (2022) Uygulamalı İstatistik ve Geçerlik Güvenirlik. Ankara: Detay Yayıncılık.Schmidt M.D. & Lipson H. (2009) Distilling free-form natural laws from experimental data. Science 324, pp. 81–5.Schmidt M.D. & Lipson H. (2009) Distilling free-form natural laws from experimental data. Science 324, pp. 81–5.Xue L. & Zou H. (2006) Parameter Estimation for Differential Equation Models Using a Framework of Measurement Error in Regression Models. Journal of the American Statistical Association, 101(475), pp. 1570– 1583. https://doi.org/10.1198/016214506000000691.Xue L. & Zou H. (2006) Parameter Estimation for Differential Equation Models Using a Framework of Measurement Error in Regression Models. Journal of the American Statistical Association, 101(475), pp. 1570– 1583. https://doi.org/10.1198/016214506000000691.

The authors declare that there are no conflicts of interest present.