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

International Journal of Algorithms Design and Analysis Review Original Research

Aspect-Based Sentiment Analysis Using a Hybrid Approach with Dependency Parsing

  1. Shravani B. Nikam Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik
  2. Ishika B. Mulekar Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik
  3. Diya A. Deshmukh Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik
  4. Sanuja K. Khutale Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik
  5. Neelima S. Ambekar Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik

Abstract

The rapid expansion of digital communication has resulted in an unprecedented volume of consumer-generated textual data across online reviews, social media platforms, forums, and e-commerce websites. Extracting meaningful insights from this data is increasingly important for organizations seeking to understand customer opinions, preferences, and behavioral trends. Despite significant advances in sentiment analysis, many existing approaches primarily focus on surface-level features and often overlook deeper syntactic and semantic relationships within text. This limitation can lead to fragmented or inaccurate sentiment interpretations, particularly when dealing with complex sentence structures or aspect-specific opinions. To overcome these challenges, this study proposes a unified sentiment analysis framework that integrates dependency parsing and semantic role labeling to capture both grammatical structure and contextual meaning. The proposed system constructs a hybrid feature vector by combining global review-level features with fine-grained aspect- and opinion-level features, enabling a more comprehensive representation of textual information. Furthermore, bidirectional encoder representations from transformers (BERT) are employed to classify user-generated reviews into three sentiment categories: positive, negative, and neutral. Experimental observations indicate that this integrated methodology improves sentiment classification accuracy and robustness.

Keywords

References (24)

  1. Fang X, Zhan J. Sentiment analysis using product review data. Journal of Big Data. 2015;2(1). doi:10.1186/s40537-015-0015-2
  2. Zou W, Zhang W, Tian Z, Wu W. A syntactic features and interactive learning model for aspect-based sentiment analysis. Complex & Intelligent Systems. 2024;10(4):5359-5377. doi:10.1007/s40747-024-01449-5
  3. Jiang X, Ren B, Wu Q, Wang W, Li H. DCASAM: advancing aspect-based sentiment analysis through a deep context-aware sentiment analysis model. Complex & Intelligent Systems. 2024;10(6):7907-7926. doi:10.1007/s40747-024-01570-5
  4. Toh Z, Wang W. DLIREC: Aspect Term Extraction and Term Polarity Classification System. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014). 2014:235-240. doi:10.3115/v1/s14-2038
  5. Barik K, Misra S, Ray AK, Bokolo A. LSTM‐DGWO‐Based Sentiment Analysis Framework for Analyzing Online Customer Reviews. Computational Intelligence and Neuroscience. 2023;2023(1). doi:10.1155/2023/6348831
  6. George AS, Baskar T. Leveraging big data and sentiment analysis for actionable insights: A review of data mining approaches for social media. Partners Univ Int Innov J. 2024;2(4):39–59.
  7. Talaat AS. Sentiment analysis classification system using hybrid BERT models. Journal of Big Data. 2023;10(1). doi:10.1186/s40537-023-00781-w
  8. Aziz K, Ji D, Chakrabarti P, Chakrabarti T, Iqbal MS, Abbasi R. Unifying aspect-based sentiment analysis BERT and multi-layered graph convolutional networks for comprehensive sentiment dissection. Scientific Reports. 2024;14(1). doi:10.1038/s41598-024-61886-7
  9. Gong H, Zhang S. An aspect sentiment analysis model with Aspect Gated Convolution and Dual-Feature Filtering layers. Journal of Big Data. 2024;11(1). doi:10.1186/s40537-024-00969-8
  10. Department of CSE, GMRIT, Rajam, India., Srividya K, Sowjanya AMS, Department of CS&SE, Andhra University College of Engineering , Visakhapatnam, A.P, India. Aspect Based Sentiment Analysis using POS Tagging and TFIDF. International Journal of Engineering and Advanced Technology. 2019;8(6):1960-1963. doi:10.35940/ijeat.f7935.088619
  11. Alizadeh M, Seilsepour A. A novel self-supervised sentiment classification approach using semantic labeling based on contextual embeddings. Multimedia Tools and Applications. 2024;84(12):10195-10220. doi:10.1007/s11042-024-19086-y
  12. Li X, Bing L, Li P, Lam W, Yang Z. Aspect Term Extraction with History Attention and Selective Transformation. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. 2018:4194-4200. doi:10.24963/ijcai.2018/583
  13. Wu C, Wu F, Wu S, Yuan Z, Huang Y. A hybrid unsupervised method for aspect term and opinion target extraction. Knowledge-Based Systems. 2018;148:66-73. doi:10.1016/j.knosys.2018.01.019
  14. Dai H, Song Y. Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019:5268-5277. doi:10.18653/v1/p19-1520
  15. Hussain I, Qureshi M, Ismail M, Iftikhar H, Zywiołek J, López-Gonzales JL. Optimal features selection in the high dimensional data based on robust technique: Application to different health database. Heliyon. 2024;10(17):e37241. doi:10.1016/j.heliyon.2024.e37241
  16. AL-Smadi M, Al-Ayyoub M, Al-Sarhan H, Jararweh Y. Using aspect-based sentiment analysis to evaluate Arabic news affect on readers. UCC'15: 8th IEEE/ACM International Conference on Utility and Cloud Computing, Limassol, Cyprus, 2015. p. 436–441. doi:10.1145/3233397.3233481.
  17. Phan MH, Ogunbona PO. Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020:3211-3220. doi:10.18653/v1/2020.acl-main.293
  18. Phan MH, Ogunbona PO. Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020:3211-3220. doi:10.18653/v1/2020.acl-main.293
  19. Ambekar NS, Nimkar AV. Relevant Feature Extraction to Enhance Aspect-Based Sentiment Classification Using Dependency and Bi-Tagged Features. 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT). 2023;1:1-6. doi:10.1109/icccnt56998.2023.10306576
  20. Waltinger U. An Empirical Study on Machine Learning-Based Sentiment Classification Using Polarity Clues. Lecture Notes in Business Information Processing. 2011:202-214. doi:10.1007/978-3-642-22810-0_15
  21. Chen Z, Qian T. Enhancing Aspect Term Extraction with Soft Prototypes. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020:2107-2117. doi:10.18653/v1/2020.emnlp-main.164
  22. Xu H, Liu B, Shu L, Yu PS. BERT post-training for review reading comprehension and aspect-based sentiment analysis. NAACL-HLT 2019: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA, 2019. p. 2324–2335. doi:10.18653/v1/N19-1242.
  23. Kumar A, Veerubhotla AS, Narapareddy VT, Aruru V, Neti LBM, Malapati A. Aspect term extraction for opinion mining using a Hierarchical Self-Attention Network. Neurocomputing. 2021;465:195-204. doi:10.1016/j.neucom.2021.08.133
  24. Tian Y, Chen G, Song Y. Enhancing Aspect-level Sentiment Analysis with Word Dependencies. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021:3726-3739. doi:10.18653/v1/2021.eacl-main.326