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

Year : 2025 | Volume : 04 | Issue : 01 | Page : 01 09
    By

    Shravani B. Nikam,

  • Ishika B. Mulekar,

  • Diya A. Deshmukh,

  • Sanuja K. Khutale,

  • Neelima S. Ambekar,

  1. Student, Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik, Maharashtra, India
  2. Student, Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik, Maharashtra, India
  3. Student, Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik, Maharashtra, India
  4. Student, Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik, Maharashtra, India
  5. Assistant Professor, Department of Artificial Intelligence and Data Science, MET Bhujbal Knowledge City, Nashik, Maharashtra, India

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: Bidirectional encoder representations from transformers (BERT), consumer behavior, dependency parsing, hybrid feature extraction, semantic role labeling, sentiment analysis, text classification

[This article belongs to International Journal of Algorithms Design and Analysis Review ]

How to cite this article:
Shravani B. Nikam, Ishika B. Mulekar, Diya A. Deshmukh, Sanuja K. Khutale, Neelima S. Ambekar. Aspect-Based Sentiment Analysis Using a Hybrid Approach with Dependency Parsing. International Journal of Algorithms Design and Analysis Review. 2025; 04(01):01-09.
How to cite this URL:
Shravani B. Nikam, Ishika B. Mulekar, Diya A. Deshmukh, Sanuja K. Khutale, Neelima S. Ambekar. Aspect-Based Sentiment Analysis Using a Hybrid Approach with Dependency Parsing. International Journal of Algorithms Design and Analysis Review. 2025; 04(01):01-09. Available from: https://journals.stmjournals.com/ijadar/article=2025/view=232459


References

  1. Fang X, Zhan J. Sentiment analysis using product review data. J Big Data. 2015;2(1):5. 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 Intell Syst. 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 Intell Syst. 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. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), Dublin, Ireland, 2014. p. 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. Comput Intell Neurosci. 2023;2023:6348831. doi:10.1155/2023/6348831. PubMed: 36820054.
  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. J Big Data. 2023;10(1):110. 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. Sci Rep. 2024;14(1):14646. doi:10.1038/s41598-024-61886-7. PubMed: 38918461.
  9. Gong H, Zhang S. An aspect sentiment analysis model with Aspect Gated convolution and Dual-Feature Filtering layers. J Big Data. 2024;11(1):111. doi:10.1186/s40537-024-00969-8.
  10. Srividya K, Sowjanya AMS. Aspect based sentiment analysis using POS tagging and TFIDF. Int J Eng Adv Technol. 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. Multimed Tools Appl. 2025;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. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence; 2018. p. 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. Knowl-Based Syst. 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. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics; 2019. p. 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. PubMed: 39296019.
  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. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics; 2020. p. 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. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics; 2020. p. 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. In: 14th International Conference on Computing Communication and Networking Technologies (ICCCNT); 2023. p. 1–6. doi:10.1109/ICCCNT56998.2023.10306576.
  20. Waltinger U. An empirical study on machine learning-based sentiment classification using polarity clues. In: Filipe J, Cordeiro J, editors. WEBIST 2010: Web Information Systems and Technologies. Lecture Notes in Business Information Processing, vol 75. Berlin, Heidelberg: Springer; 2011. p. 189–198. doi:10.1007/978-3-642-22810-0_15.
  21. Chen Z, Qian T. Enhancing aspect term extraction with soft prototypes. EMNLP 2020: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, Online, 2020. p. 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. EACL 2021: 16th Conference of the European Chapter of the Association for Computational Linguistics, Online, 2021. p. 3726–3739. doi:10.18653/v1/2021.eacl-main.326.
Regular Issue Subscription Original Research
Volume 04
Issue 01
Received 16/06/2025
Accepted 12/09/2025
Published 18/11/2025
Publication Time 155 Days
282

Login


My IP

PlumX Metrics