Russian Federation
Russian Federation
The paper presents a predictive bibliometric study of trending topics in the PubMed collection in the field of sentiment analysis of texts based on dictionaries. The design of the present study uses a collection of scientific articles indexed in the PubMed bibliographic database. 147 articles that had the keywords “sentiment analysis” and “dictionary” in the titles and abstracts were retrieved from the mentioned base. A significant increase (21 times over 6 years) in the number of annually published similar articles was revealed. The rating of relevant keywords in the selected articles was calculated and presented. Among the relevant keywords, trending keywords with predicted long-term trend growth were identified. A semantic map of trending keywords is drawn, containing information on the novelty and longevity of trends. As a result of visual analysis of the semantic map, two trending topics were determined: (1) well-being issues, (2) patient and customer satisfaction. Well-being issues include trending subtopics: loneliness, depression, resilience to such problems, and strategies of their coping.
natural language processing, formal linguistic models, bibliometrical analysis, sentiment analysis, semantic map, long-term prediction of transformation of scientific trending topics, PubMed database collection
1. Qi Y. Sentiment analysis using Twitter data: a comparative application of lexicon-and machine-learning-based approach [Text] / Y. Qi, Z. Shabrina. – Social network analysis and mining. – 2023. – 13(1). – 31. DOI: https://doi.org/10.1007/s13278-023-01030-x
2. Hutto C. Vader: A parsimonious rule-based model for sentiment analysis of social media text [Text] / C. Hutto, E. Gilbert. – Proceedings of the international AAAI conference on web and social media. – 2014. – Vol. 8. – No. 1. – Pp. 216–225. DOI: https://doi.org/10.1609/icwsm.v8i1.14550
3. Gandy L.M. Public Health Discussions on Social Media: Evaluating Automated Sentiment Analysis Methods [Text] / L.M. Gandy [et al.]. – JMIR Formative Research. – 2025. – 9(1). – e57395. DOI: https://doi.org/10.2196/57395
4. Shah H.A. Mapping loneliness through comparative analysis of USA and India using social intelligence analysis [Text] / H.A. Shah, M. Househ. – BMC public health. – 2024. – 24(1). – 253. DOI: https://doi.org/10.1186/s12889-023-17630-3
5. Valdez D. Social media insights into US mental health during the COVID-19 pandemic: longitudinal analysis of Twitter data [Text] / D. Valdez [et al.]. – Journal of medical Internet research. – 2020. – 22(12). – e21418. DOI: https://doi.org/10.2196/21418
6. Hswen Y. Sentiments of Individuals with Interstitial Cystitis/Bladder Pain Syndrome Toward Pentosan Polysulfate Sodium: Infodemiology Study [Text] / Y. Hswen [et al.]. – JMIR Formative Research. – 2025. – 9(1). – e54209. DOI: https://doi.org/10.2196/54209
7. Rao S.A. Social media responses to elective surgery cancellations in the wake of COVID-19 [Text] / S. A. Rao [et al.]. – Annals of surgery. – 2020. – 272(3). – e246–e248. DOI: https://doi.org/10.1097/SLA.0000000000004106
8. Oduntan A. “I Let Depression and Anxiety Drown Me…”: Identifying Factors Associated With Resilience Based on Journaling Using Machine Learning and Thematic Analysis [Text] / A. Oduntan [et al.]. – IEEE journal of biomedical and health informatics. – 2022. – 26(7), 3397-3408. DOI: https://doi.org/10.1109/JBHI.2022.3149862
9. Vought V. Application of sentiment and word frequency analysis of physician review sites to evaluate refractive surgery care [Text] / V. Vought [et al.]. – Advances in Ophthalmology Practice and Research. – 2024. – 4(2). – Pp. 78–83. DOI: https://doi.org/10.1016/j.aopr.2024.03.002
10. Pleerux N. Sentiment analysis of restaurant customer satisfaction during COVID-19 pandemic in Pattaya, Thailand [Text] / N. Pleerux, A. Nardkulpat. – Heliyon. – 2023. – Vol. 9. – Issue 11. – e22193. DOI: https://doi.org/10.1016/j.heliyon.2023.e22193
11. Prokhorenkova L. CatBoost: unbiased boosting with categorical features [Text] / L. Prokhorenkova [et al.]. – Advances in neural information processing systems. – Vol. 32. – Montreal, QC, 2018. – P. 6638–6648. EDN: https://elibrary.ru/NRYEVS
12. Charnine M. Research trending topic prediction as cognitive enhancement [Text] / M. Charnine [et al.]. – 2021 international conference on cyberworlds (CW). – IEEE. – 2021. – Pp. 217–220. – DOI:https://doi.org/10.1109/CW52790.2021.00044. EDN: https://elibrary.ru/BAZEZF
13. Charnine M. Visualization of Research Trending Topic Prediction: Intelligent Method for Data Analysis [Text] / M. Charnine, A. Tishchenko, L. Kochiev. – Proceedings of the 31th International Conference on Computer Graphics and Vision. – 2021. – Vol. 2. – P. 1028–1037. DOI: https://doi.org/10.20948/graphicon-2021-3027-1028-1037; EDN: https://elibrary.ru/PTCLJF
14. Mohammed I. Building lexicon-based sentiment analysis model for low-resource languages [Text] / I. Mohammed, R. Prasad. – MethodsX. – 2023. – 11. – 102460. DOI: https://doi.org/10.1016/j.mex.2023.102460
