STM Journals Peer-reviewed research from Consortium e-Learning Network

International Journal of Computer Science Languages Review Article

Optimized Sentiment Analysis Through TextBlob and Hybrid RNN Models

  1. Pulkit Tiwari Department of Computer Science and Engineering, JECRC University, Jaipur
  2. Bhavna Sharma Department of Computer Science and Engineering, JECRC University, Jaipur

Abstract

In today’s world, analyzing people’s feelings from what they write online has become very important. This is because there is a large amount of content created by users. To make this analysis accurate and fast, we present a method. This method uses a mix of two approaches: one that looks up words in a dictionary and another that uses computer learning. TextBlob is an affordable tool for getting an initial idea of how people feel. However, it sometimes misses complex emotions because it uses simple rules. To fix this, our system combines TextBlob with a special kind of computer learning model. This model incorporates two kinds of recurrent neural networks: long short-term memory (LSTM) and gated recurrent unit (GRU) architectures. These networks are good at understanding text because they can look at the sentence, not just individual words. When we prepare our data, we use TextBlob to get an idea of how positive or negative the text’s. We then use this information to help our model understand the context better. By doing this, our model becomes more accurate and faster to train. We tested our approach. Found that it works well, especially when we use certain types of computer learning embeddings like LSTM, BiLSTM, and GRU. Our method provides a balance between being accurate and not taking too much computer power. This means it can handle a lot of data and still give results. Overall, our approach is a solution for analyzing people’s feelings from what they write online. It helps us understand and interpret volumes of user-generated content more effectively. Sentiment analysis has become essential for understanding and interpreting volumes of user-generated content. The proposed system combines TextBlob with a deep learning architecture built on LSTM and GRU networks for sentiment analysis. A sentiment analysis framework that integrates lexicon-based methods with deep learning techniques offers a balanced solution that improves generalization while maintaining computational efficiency.

Keywords

References (26)

  1. Maria H, Subhashni R. Hybrid lexicon and transformer-based sentiment analysis of student feedback for faculty evaluation: A speech-to-text approach. Commun Appl Nonlinear Anal. 2025;32(2):610–622.
  2. Department of Computer Sciences, College of Science for Women, University of Babylon, Babylon, Iraq, Zahraa Z, Computer sciences department, College of Science for Women, University of Babylon, Iraq, Department of Computer Sciences, University of Technology, Baghdad, Iraq, Attia H, Ali YH. Optimized and Comprehensive Fake Review Detection based on Harris Hawks optimization integrated with Machine Learning Techniques. Journal of Cybersecurity and Information Management. 2025;15(1):11-21. doi:10.54216/jcim.150102
  3. Tayal N, Singh M, Raj M. A BERT-based technique on IMDb for false movie review detection. J Electr Syst. 2024;20(10s):5322–5333.
  4. Malik F, Fuzail M, Aslam N, Sarwar R, Abid K, Maqbool MS, et al. A hybrid machine learning model to predict sentiment analysis on X. J Comput Biomed Inform. 2024;6(2):64–79.
  5. Sablok B, Tyagi A, Dharmander, Malik MHS, Chaturvedi DS, Sureshwati D. NLP Models for Sentiment Analysis of Twitter Data. International Journal for Research in Applied Science and Engineering Technology. 2025;13(4):3544-3552. doi:10.22214/ijraset.2025.68682
  6. İsenkul M. Optimizing the Sentiment Recognition in Spotify Playlists Through Ensemble-Based Approaches. Acta Infologica. 2025;9(1):74-89. doi:10.26650/acin.1604272
  7. Mamillapalli A, Ogunleye B, Timoteo Inacio S, Shobayo O. GRUvader: Sentiment-Informed Stock Market Prediction. Mathematics. 2024;12(23):3801. doi:10.3390/math12233801
  8. Malik N, Bilal M. Natural language processing for analyzing online customer reviews: a survey, taxonomy, and open research challenges. PeerJ Computer Science. 2024;10:e2203. doi:10.7717/peerj-cs.2203
  9. Ashbaugh L, Zhang Y. A Comparative Study of Sentiment Analysis on Customer Reviews Using Machine Learning and Deep Learning. Computers. 2024;13(12):340. doi:10.3390/computers13120340
  10. Alsubaie MS, Atawneh SH, Abual-Rub MS. Building machine learning model with hybrid feature selection technique for keylogger detection. Int J Adv Soft Comput Appl. 2023 Jul;15(2). doi:10.15849/IJASCA.230720.03.
  11. Elsadig MA, Gafar A. An ensemble model to detect packet length covert channels. International Journal of Electrical and Computer Engineering (IJECE). 2023;13(5):5296. doi:10.11591/ijece.v13i5.pp5296-5304
  12. Sharma P, Sharma A. Online K-means clustering with adaptive dual cost functions. 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT). 2017:793-799. doi:10.1109/icicict1.2017.8342665
  13. Sharma A, Sharma A. KNN-DBSCAN: Using k-nearest neighbor information for parameter-free density based clustering. 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT). 2017:787-792. doi:10.1109/icicict1.2017.8342664
  14. Magade K, Sharma A. Significant role of IoT in Cyber-Physical Systems, Context Awareness, and Ambient Intelligence. The Next Generation Innovation in IoT and Cloud Computing with Applications. 2024:16-34. doi:10.1201/9781003406723-2
  15. Kumar V, Gupta SK, Hussain A, Sharma A. A systematic approach to prevent threats using IDS in IoT-based devices. GMSARN Int J. 2025;19(1):107–112.
  16. Hussain A, Obaid AJ, Tyagi G, Sharma A. The Next Generation Innovation in IoT and Cloud Computing with Applications. 2024. doi:10.1201/9781003406723
  17. Garg P, Sharma A. A distributed algorithm for local decision of cluster heads in wireless sensor networks. 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI). 2017:2411-2415. doi:10.1109/icpcsi.2017.8392150
  18. A. Kadheem Hammood B, T. Sadiq A. ENSEMBLE MACHINE LEARNING APPROACH FOR IOT INTRUSION DETECTION SYSTEMS. Iraqi Journal for Computers and Informatics. 2023;49(2):93-99. doi:10.25195/ijci.v49i2.458
  19. Ding W, Popoola S. An Ensemble Learning Voting Technique for Network Intrusion Detection Systems. 2023. doi:10.21203/rs.3.rs-2989954/v1
  20. Afrifa S, Varadarajan V, Appiahene P, Zhang T, Domfeh EA. Ensemble Machine Learning Techniques for Accurate and Efficient Detection of Botnet Attacks in Connected Computers. Eng. 2023;4(1):650-664. doi:10.3390/eng4010039
  21. Titl V, Mazrekaj D, Schiltz F. Identifying Politically Connected Firms: A Machine Learning Approach*. Oxford Bulletin of Economics and Statistics. 2023;86(1):137-155. doi:10.1111/obes.12586
  22. Afriyie JK, Tawiah K, Pels WA, Addai-Henne S, Dwamena HA, Owiredu EO, et al. A supervised machine learning algorithm for detecting and predicting fraud in credit card transactions. Decision Analytics Journal. 2023;6:100163. doi:10.1016/j.dajour.2023.100163
  23. Talman A, Apidianaki M, Chatzikyriakidis S, Tiedemann J. How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets. Proceedings of the 11th Joint Conference on Lexical and Computational Semantics. 2022:226-233. doi:10.18653/v1/2022.starsem-1.20
  24. El Alami H, Najid A. Energy-efficient fuzzy logic cluster head selection in wireless sensor networks. 2016 International Conference on Information Technology for Organizations Development (IT4OD). 2016:1-7. doi:10.1109/it4od.2016.7479300
  25. Kaissar A, Nassif AB, Injadat M. A Survey on Network Intrusion Detection using Convolutional Neural Network. ITM Web of Conferences. 2022;43:01003. doi:10.1051/itmconf/20224301003
  26. Yang D, Mai Ngoc K, Shin I, Lee KH, Hwang M. Ensemble-Based Out-of-Distribution Detection. Electronics. 2021;10(5):567. doi:10.3390/electronics10050567