Hybrid NLP framework for enhanced sentiment analysis ‎and topic detection on YouTube

Authors

  • Ramesh Babu

    Research Scholar, Department of Computer Science, Sri Venkateswara University, Tirupati - 517502, Andhra Pradesh, India

  • S. Ramakrishna

    Professor, Department of Computer Science, Sri Venkateswara University, Tirupati - 517502, Andhra Pradesh, India

  • Suneel Kumar Duvvuri

    Assistant Professor in the Department of Computer Science at Government College Autonomous, Rajahmundry

How to Cite

Babu, R. ., Ramakrishna, S. ., & Duvvuri , S. K. . (2025). Hybrid NLP framework for enhanced sentiment analysis ‎and topic detection on YouTube. International Journal of Basic and Applied Sciences, 14(1), 304-313. https://doi.org/10.14419/kft8ae18

Received date: April 1, 2025

Accepted date: May 6, 2025

Published date: May 14, 2025

DOI:

https://doi.org/10.14419/kft8ae18

Keywords:

Sentiment Analysis; Audience Engagement; Viewer Sentiments; Term-Inverse Document Frequency; Social Media Analytics; Bag of Words

Abstract

This paper introduces an advanced hybrid NLP framework designed to enhance sentiment analysis and topic detection in YouTube ‎comments. By combining feature extraction methods like Bag of Words (BoW) and TF-IDF with neural network models like LSTM and Bi-LSTM, the framework effectively uncovers latent topics and sentiment orientations. The study specifically analyzes comments on Oscar-nominated movie trailers, demonstrating the framework's ability to capture both explicit and implicit patterns of sentiment. This study shows ‎that the Bi-LSTM model with BoW features achieves the highest performance, with accuracy, precision, recall, and F1-scores nearing 90%. ‎This hybrid approach delivers practical and theoretical developments in natural language processing applications for content creators and ‎marketers to optimize engagement strategies based on user sentiment and thematic preferences‎.

References

  1. Yosafat AR, Kurnia Y. Aplikasi Prediksi Rating Film dengan Perbandingan Metode Naïve Bayes dan KNN Berbasis Website ‎Menggunakan Framework Codeigniter. ALGOR. 2019 Oct 21;1(1):16-27.‎
  2. Widayat W. Analisis Sentimen Movie Review menggunakan Word2Vec dan metode LSTM Deep Learning. Journal Media ‎Informa tika Budidar-ma. 2021 Jul 31;5(3):1018-26.‎ https://doi.org/10.30865/mib.v5i3.3111.
  3. Putri CA. Analisis sentimen review film berbahasa Inggris dengan pendekatan bidirectional encoder representations from ‎transformers. JATISI (Jurnal Teknik Informatika dan Sistem Informasi). 2020 Jan 8;6(2):181-93.‎ https://doi.org/10.35957/jatisi.v6i2.206.
  4. Shivaprasad TK, Shetty J. Sentiment analysis of product reviews: A review. In2017 International conference on inventive ‎communication and computational technologies (ICICCT) 2017 Mar 10 (pp. 298-301). IEEE.‎ https://doi.org/10.1109/ICICCT.2017.7975207.
  5. Hamzah MB. Classification of Movie Review Sentiment Analysis Using Chi-Square and Multinomial Naïve Bayes with ‎Adaptive Boosting. Journal of Advances in Information Systems and Technology. 2021 Apr 14;3(1):67-74.‎ https://doi.org/10.15294/jaist.v3i1.49098.
  6. Putra AE, Wardhani LK. Chi-Square Feature Selection Effect on Naive Bayes Classifier Algorithm Performance For ‎Sentiment Analysis Docu-ment. In2019 7th International Conference on Cyber and IT Service Management ‎‎(CITSM) 2019 Nov 6 (Vol. 7, pp. 1-7). IEEE.‎ https://doi.org/10.1109/CITSM47753.2019.8965332.
  7. Putra AE, Wardhani LK. Chi-Square Feature Selection Effect on Naive Bayes Classifier Algorithm Performance for ‎Sentiment Analysis Document. In2019 7th International Conference on Cyber and IT Service Management ‎‎(CITSM) 2019 Nov 6 (Vol. 7, pp. 1-7). IEEE.‎ https://doi.org/10.1109/CITSM47753.2019.8965332.
  8. Jelodar H, Wang Y, Rabbani M, Ahmadi SB, Boukela L, Zhao R, Larik RS. A NLP framework based on meaningful latent-‎topic detection and sentiment analysis via fuzzy lattice reasoning on youtube comments. Multimedia Tools and ‎Applications. 2021 Jan;80:4155-81.‎ https://doi.org/10.1007/s11042-020-09755-z.
  9. Hamzah MB. Classification of Movie Review Sentiment Analysis Using Chi-Square and Multinomial Naïve Bayes with ‎Adaptive Boosting. Journal of Advances in Information Systems and Technology. 2021 Apr 14;3(1):67-74.‎ https://doi.org/10.15294/jaist.v3i1.49098.
  10. Daeli NO, Adiwijaya A. Sentiment analysis on movie reviews using Information gain and K-nearest neighbor. Journal of ‎Data Science and Its Ap-plications. 2020 May 11;3(1):1-7.‎
  11. Chauhan GS, Meena YK. YouTube video ranking by aspect-based sentiment analysis on user feedback. InSoft Computing ‎and Signal Processing: Proceedings of ICSCSP 2018, Volume 1 2019 (pp. 63-71). Springer Singapore‎ https://doi.org/10.1007/978-981-13-3600-3_6.
  12. Pang B, Lee L, Vaithyanathan S. Thumbs up? Sentiment classification using machine learning techniques. arXiv preprint ‎cs/0205070. 2002 May 28.‎
  13. Alhujaili RF, Yafooz WM. Sentiment analysis for youtube videos with user comments. In2021 International conference on ‎artificial intelligence and smart systems (ICAIS) 2021 Mar 25 (pp. 814-820). IEEE.‎ https://doi.org/10.1109/ICAIS50930.2021.9396049.
  14. Alslaity A, Orji R. Machine learning techniques for emotion detection and sentiment analysis: current state, challenges, and ‎future directions. Be-havior & Information Technology. 2024 Jan 2;43(1):139-64.‎ https://doi.org/10.1080/0144929X.2022.2156387.
  15. Bonifazi G, Cauteruccio F, Corradini E, Marchetti M, Sciarretta L, Ursino D, Virgili L. A space-time framework for ‎sentiment scope analysis in so-cial media. Big Data and Cognitive Computing. 2022 Nov 3;6(4):130.‎ https://doi.org/10.3390/bdcc6040130.
  16. Almars A, Li X, Zhao X. Modelling user attitudes using hierarchical sentiment-topic model. Data & Knowledge ‎Engineering. 2019 Jan 1; 119:139-49.‎ https://doi.org/10.1016/j.datak.2019.01.005.
  17. Yin J, Lampert A, Cameron M, Robinson B, Power R. Using social media to enhance emergency situation awareness. IEEE ‎intelligent systems. 2012 Nov 1;27(06):52-9.‎ https://doi.org/10.1109/MIS.2012.6.
  18. Kencana CG, Sibaroni Y. Klasifikasi Sentiment Analysis pada Review Buku Novel Berbahasa Inggris dengan Menggunakan ‎Metode Support Vec-tor Machine (SVM). eProceedings of Engineering. 2019 Dec 1;6(3).‎
  19. Jiawa Z, Wei L, Sili W, Heng Y. Review of methods and applications of text sentiment analysis. Data analysis and ‎knowledge discovery. 2021 Mar 19;5(6):1-3.‎
  20. Chen YL, Chang CL, Yeh CS. Emotion classification of YouTube videos. Decision Support Systems. 2017 Sep 1; 101:40-‎‎50.‎ https://doi.org/10.1016/j.dss.2017.05.014.
  21. Alhujaili RF, Yafooz WM. Sentiment analysis for youtube videos with user comments. In2021 International conference on ‎artificial intelligence and smart systems (ICAIS) 2021 Mar 25 (pp. 814-820). IEEE.‎ https://doi.org/10.1109/ICAIS50930.2021.9396049.
  22. Lee CS, Osop H, Goh DH, Kelni G. Making sense of comments on YouTube educational videos: A self-directed learning ‎perspective. Online in-formation review. 2017 Sep 11;41(5):611-25‎ https://doi.org/10.1108/OIR-09-2016-0274.
  23. Nawaz S, Rizwan M, Rafiq M. Recommendation of effectiveness of YouTube video contents by qualitative sentiment ‎analysis of its comments and replies. Pakistan Journal of Science. 2019 Dec 31;71(4):91.‎
  24. Zhu Y, Wang SJ. A tangible augmented reality toy kit: Interactive solution for early childhood education. In Interactivity, ‎Game Creation, Design, Learning, and Innovation: 5th International Conference, ArtsIT 2016, and First ‎International Conference, DLI 2016, Esbjerg, Denmark, May 2–3, 2016, Proceedings 5 2017 (pp. 12-19). Springer ‎International Publishing.‎ https://doi.org/10.1007/978-3-319-55834-9_2.
  25. Hemmatian F, Sohrabi MK. A survey on classification techniques for opinion mining and sentiment analysis. Artificial ‎intelligence review. 2019 Oct 1;52(3):1495-545.‎ https://doi.org/10.1007/s10462-017-9599-6.
  26. Krouska A, Troussas C, Virvou M. The effect of preprocessing techniques on Twitter sentiment analysis. In2016 7th ‎international conference on information, intelligence, systems & applications (IISA) 2016 Jul 13 (pp. 1-5). IEEE.‎ https://doi.org/10.1109/IISA.2016.7785373.
  27. Kaur G, Malik K. A comprehensive overview of sentiment analysis and fake review detection. Mobile Radio ‎Communications and 5G Networks: Proceedings of MRCN 2020. 2020 Sep 29:293-304.‎ https://doi.org/10.1109/IISA.2016.7785373.
  28. Pal JK. Usefulness and applications of data mining in extracting information from different perspectives. Annals of library ‎and information studies. 2011;58(1):7.‎
  29. Tiwari D, Kumar M. Social media data mining techniques: A survey. In Information and Communication Technology for ‎Sustainable Development: Proceedings of ICT4SD 2018 2020 (pp. 183-194). Springer Singapore.‎ https://doi.org/10.1007/978-981-13-7166-0_18.
  30. Kaplan AM, Haenlein M. Users of the world, unite! The challenges and opportunities of social media. Business horizons. ‎‎2010 Jan 1;53(1):59-68‎ https://doi.org/10.1016/j.bushor.2009.09.003.
  31. Nandi G, Das A. A survey on using data mining techniques for online social network analysis. International Journal of ‎Computer Science Issues (IJCSI). 2013 Nov 1;10(6):162‎
  32. Hamdi E, Rady S, Aref M. A deep learning Architecture with word Embeddings to classify Sentiment in Twitter. ‎InProceedings of the Interna-tional Conference on Advanced Intelligent Systems and Informatics 2020 2021 (pp. ‎‎115-125). Springer International Publishing.‎ https://doi.org/10.1007/978-3-030-58669-0_10.
  33. Kumar PK, Kumar I. Emotion detection and sentiment analysis of text. InProceedings of the International Conference on ‎Innovative Computing & Communication (ICICC) 2021 Jul 12.‎ https://doi.org/10.2139/ssrn.3884914.
  34. Han H, Zhang Y, Zhang J, Yang J, Wang Y. A Hybrid Sentiment Analysis Method. In The 10th International Conference on ‎Computer Engineer-ing and Networks 2021 (pp. 1138-1146). Springer Singapore.‎ https://doi.org/10.1007/978-981-15-8462-6_130.
  35. Singh R, Tiwari A. Youtube comments sentiment analysis. Int. J. Sci. Res. Eng. Manag. (IJSREM, no. May, p. 5, ‎‎2021,[Online]. Available: https://www. researchgate. net/publication/351351202. 2021.‎
  36. Kavitha KM, Shetty A, Abreo B, D’Souza A, Kondana A. Analysis and classification of user comments on YouTube ‎videos. Procedia Computer Science. 2020 Jan 1;177:593-8.‎ https://doi.org/10.1016/j.procs.2020.10.084.
  37. Lorentz I, Singh G. Sentiment Analysis on Youtube Comments to Predict Youtube Video Like Proportions.‎
  38. Pokharel R, Bhatta D. Classifying youtube comments based on sentiment and type of sentence. arXiv preprint ‎arXiv:2111.01908. 2021 Oct 31.‎
  39. ‎Nahas N, Swetha P, Nandakumar R. Classifiers for Sentiment Analysis of YouTube Comments: A Comparative Study. In ‎International Conference on Machine Learning,‎
  40. Deep Learning and Computational Intelligence for Wireless Communication 2023 Jun 22 (pp. 443-451). Cham: Springer ‎Nature Switzerland.‎
  41. Jha A, Jha A, Sindhavad A, Yadav R, Dalvi A, Siddavatam I. Rating YouTube Videos: An Improvised and Effective ‎Approach. In International Conference on Advancements in Smart Computing and Information Security 2022 Nov ‎‎25 (pp. 169-179). Cham: Springer Nature Switzerland.‎ https://doi.org/10.1007/978-3-031-23092-9_14.
  42. Attewell P, Monaghan D. Data mining for the social sciences: An introduction. Univ of California Press; 2015.‎
  43. Wawre SV, Deshmukh SN. Sentiment classification using machine learning techniques. International Journal of Science and ‎Research (IJSR). 2016 Apr;5(4):819-21.‎ https://doi.org/10.21275/v5i4.NOV162724.
  44. Bhavitha BK, Rodrigues AP, Chiplunkar NN. Comparative study of machine learning techniques in sentimental analysis. ‎In2017 International con-ference on inventive communication and computational technologies (ICICCT) 2017 Mar ‎‎10 (pp. 216-221). IEEE.‎ https://doi.org/10.1109/ICICCT.2017.7975191.
  45. Gao K, Xu H, Wang J. A rule-based approach to emotion cause detection for Chinese micro-blogs. Expert Systems with ‎Applications. 2015 Jun 1;42(9):4517-28.‎ https://doi.org/10.1016/j.eswa.2015.01.064.
  46. Kaur G, Malik K. A comprehensive overview of sentiment analysis and fake review detection. Mobile Radio ‎Communications and 5G Networks: Proceedings of MRCN 2020. 2020 Sep 29:293-304.‎ https://doi.org/10.1007/978-981-15-7130-5_22.
  47. Hamdi E, Rady S, Aref M. A deep learning Architecture with word Embeddings to classify Sentiment in Twitter. ‎InProceedings of the Interna-tional Conference on Advanced Intelligent Systems and Informatics 2020 2021 (pp. ‎‎115-125). Springer International Publishing.‎ https://doi.org/10.1007/978-3-030-58669-0_10.
  48. Han H, Zhang Y, Zhang J, Yang J, Wang Y. A Hybrid Sentiment Analysis Method. InThe 10th International Conference on ‎Computer Engineering and Networks 2021 (pp. 1138-1146). Springer Singapore.‎ https://doi.org/10.1007/978-981-15-8462-6_130.
  49. Rabeya T, Ferdous S, Ali HS, Chakraborty NR. A survey on emotion detection: A lexicon based backtracking approach for ‎detecting emotion from Bengali text. In2017 20th international conference of computer and information technology ‎‎(ICCIT) 2017 Dec 22 (pp. 1-7). IEEE.‎ https://doi.org/10.1109/ICCITECHN.2017.8281855.
  50. Jelodar H, Wang Y, Rabbani M, Ahmadi SB, Boukela L, Zhao R, Larik RS. A NLP framework based on meaningful latent-‎topic detection and sentiment analysis via fuzzy lattice reasoning on youtube comments. Multimedia Tools and ‎Applications. 2021 Jan; 80:4155-81.‎ https://doi.org/10.1007/s11042-020-09755-z.
  51. Almanie T, Aldayel A, Alkanhal G, Alesmail L, Almutlaq M, Althunayan R. Saudi mood: a real-time informative tool for ‎visualizing emotions in Saudi Arabia using twitter. In2018 21st Saudi computer society national computer ‎conference (NCC) 2018 Apr 25 (pp. 1-6). IEEE.‎ https://doi.org/10.1109/NCG.2018.8593165.
  52. Dave A, Bharti S, Patel S, Mishra SK. A real-time sentiments analysis system using Twitter data. In Intelligent and Cloud ‎Computing: Proceedings of ICICC 2019, Volume 2 2021 (pp. 251-258). Springer Singapore.‎ https://doi.org/10.1007/978-981-15-6202-0_25.
  53. Balakrishnan V, Lok PY, Abdul Rahim H. A semi-supervised approach in detecting sentiment and emotion based on ‎digital payment reviews. The Journal of Supercomputing. 2021 Apr;77(4):3795-810.‎ https://doi.org/10.1007/s11227-020-03412-w.
  54. Kumar PK, Kumar I. Emotion detection and sentiment analysis of text. InProceedings of the International Conference on ‎Innovative Computing & Communication (ICICC) 2021 Jul 12.‎ https://doi.org/10.2139/ssrn.3884914.
  55. Shah B, Shah M. A survey on machine learning and deep learning based approaches for sarcasm identification in social ‎media. InData Science and Intelligent Applications: Proceedings of ICDSIA 2020 2021 (pp. 247-259). Springer ‎Singapore.‎ https://doi.org/10.1007/978-981-15-4474-3_29

Downloads

How to Cite

Babu, R. ., Ramakrishna, S. ., & Duvvuri , S. K. . (2025). Hybrid NLP framework for enhanced sentiment analysis ‎and topic detection on YouTube. International Journal of Basic and Applied Sciences, 14(1), 304-313. https://doi.org/10.14419/kft8ae18

Received date: April 1, 2025

Accepted date: May 6, 2025

Published date: May 14, 2025