Weighted Words Multi-Domain Model for Aspect-Opinion Pairs Extraction

Mohammadi, Atefeh; Pajoohan, Mohammad Reza; Zareh Bidoki, Ali Mohammad

doi:10.22061/jecei.2025.11741.832

تعداد نشریات	11
تعداد شماره‌ها	234
تعداد مقالات	2,381
تعداد مشاهده مقاله	3,802,087
تعداد دریافت فایل اصل مقاله	2,763,590

	Weighted Words Multi-Domain Model for Aspect-Opinion Pairs Extraction
Journal of Electrical and Computer Engineering Innovations (JECEI)
مقاله 5، دوره 14، شماره 1، مهر 2026، صفحه 41-54 اصل مقاله (1.2 M)
نوع مقاله: Original Research Paper
شناسه دیجیتال (DOI): 10.22061/jecei.2025.11741.832
نویسندگان
Atefeh Mohammadi؛ Mohammad Reza Pajoohan^* ؛ Ali Mohammad Zareh Bidoki
Department of Computer Engineering, Yazd University, Yazd, Iran.
تاریخ دریافت: 01 اسفند 1403، تاریخ بازنگری: 27 اردیبهشت 1404، تاریخ پذیرش: 16 خرداد 1404
چکیده
Background and Objectives: In Natural Language Processing (NLP), sentiment analysis is crucial for understanding and extracting aspects and opinions expressed in textual data. Recent methods have emphasized determining polarity in multi-domain sentiment analysis while giving less attention to aspect and opinion extraction. Furthermore, the terms that convey aspects and opinions may have different importance in different domains, and this difference should be considered to enhance the extraction of aspect-opinion pairs. Methods: To address these challenges, we propose a Weighted Words Multi-Domain (WWMD) model for aspect-opinion pairs extraction, consisting of a self-attention mechanism and a dense network. The self-attention mechanism extracts each word's importance according to the sentence's overall meaning. The dense network is used for domain prediction. It assigns greater weight to words relevant to each domain, which leads to considering the different significance of terms across various contexts. Adding an attention mechanism to the domain module allows for a clearer understanding of different aspects and opinions across various domains. We utilize a two-channel approach, one channel extracts aspects and opinions, while the other extracts the relationships between them. The weighted words extracted by our model are simultaneously considered as the input for both channels. Results: Using weighted words specific to each domain, improves the model output. Conclusion: Evaluation results on benchmark datasets demonstrate the superiority of the proposed model compared to state-of-the-art techniques.
کلیدواژه‌ها
Multi-domain؛ Opinion entities؛ Sentiment analysis؛ Attention network

مراجع
[1] T. Shaik, X. Tao, C. Dann, H. Xie, Y. Li, L. Galligan, "Sentiment analysis and opinion mining on educational data: A survey," Nat. Lang. Process. J., 2: 100003, 2023. [2] H. Zhao, L. Huang, R. Zhang, Q. Lu, H. Xue, "Spanmlt: A span-based multi-task learning framework for pair-wise aspect and opinion terms extraction," in Proc. the 58th annual meeting of the association for computational linguistics: 3239-3248, 2020. [3] H. T. Phan, N. T. Nguyen, D. Hwang, Y. S. Seo, "M2SA: A novel dataset for multi-level and multi-domain sentiment analysis," J. Inf. Telecommun., 7(4): 494-512, 2023. [4] N. Gupta, R. Agrawal, "Application and techniques of opinion mining," in Hybrid computational intelligence: Elsevier, pp: 1-23, 2020. [5] S. Chen, Y. Wang, J. Liu, Y. Wang, "Bidirectional machine reading comprehension for aspect sentiment triplet extraction," in Proc. the AAAI Conference on Artificial Intelligence, 35(14): 12666-12674, 2021. [6] Z. Yuan, S. Wu, F. Wu, J. Liu, Y. Huang, "Domain attention model for multi-domain sentiment classification," Knowledge-Based Syst., 155: 1-10, 2018. [7] S. Wang, Y. Zhu, W. Gao, M. Cao, M. Li, "Emotion-semantic-enhanced bidirectional LSTM with multi-head attention mechanism for microblog sentiment analysis," Information, 11(5): 280, 2020. [8] D. Chen, W. Su, P. Wu, B. Hua, "Joint multimodal sentiment analysis based on information relevance," Inf. Process. Manag., 60(2): 103193, 2023. [9] A. Ghorbanali, M. K. Sohrabi, "Exploiting bi-directional deep neural networks for multi-domain sentiment analysis using capsule network," Multimedia Tools Appl., 82(15): 22943-22960, 2023. [10] D. Bollegala, D. Weir, J. Carroll, "Cross-domain sentiment classification using a sentiment sensitive thesaurus," IEEE Trans. Knowl. Data Eng., 25(8): 1719-1731, 2012. [11] S. Chen, J. Liu, Y. Wang, W. Zhang, Z. Chi, "Synchronous double-channel recurrent network for aspect-opinion pair extraction," in Proc. the 58th Annual Meeting of the Association for Computational Linguistics: 6515-6524, 2020. [12] R. Liu, Y. Shi, C. Ji, M. Jia, "A survey of sentiment analysis based on transfer learning," IEEE access, 7: 85401-85412, 2019. [13] A. M. M. Yazdian-Dehkordi, M. Nematbakhsh, "Identification of implicit features using persian language rules and sentiments clustering," Tabriz J. Electr. Eng., 50(3): 1395-1404, 2020. [14] M. Hu, B. Liu, "Mining and summarizing customer reviews," in Proc. the tenth ACM SIGKDD international conference on Knowledge discovery and data mining: 168-177, 2004. [15] A. M. M-R. Pajoohan, M. Montazeri, "Identification of explicit features in persian comments," J. Comput. Secur., 6: 1-11, 2019. [16] K. Shu, A. Sliva, S. Wang, J. Tang, H. Liu, "Fake news detection on social media: A data mining perspective," ACM SIGKDD Explorations Newsletter, 19(1): 22-36, 2017. [17] A. Kumar, A. S. Veerubhotla, V. T. Narapareddy, V. Aruru, L. B. M. Neti, A. Malapati, "Aspect term extraction for opinion mining using a hierarchical self-attention network," Neurocomputing, 465: 195-204, 2021. [18] R. Satapathy, S. R. Pardeshi, E. Cambria, "Polarity and subjectivity detection with multitask learning and bert embedding," Future Internet, 14(7): 191, 2022. [19] J. Shobana, M. Murali, "An improved self attention mechanism based on optimized BERT-BiLSTM model for accurate polarity prediction," Comput. J., 6(5): 1279-1294, 2023. [20] H. S. Sharaf Al-deen, Z. Zeng, R. Al-sabri, A. Hekmat, "An improved model for analyzing textual sentiment based on a deep neural network using multi-head attention mechanism," Appl. Syst. Innovation, 4(4): 85, 2021. [21] Y. Fu, J. Liao, Y. Li, S. Wang, D. Li, X. Li, "Multiple perspective attention based on double BiLSTM for aspect and sentiment pair extract," Neurocomputing, 438: 302-311, 2021. [22] K. H. Alyoubi, A. Sharma, "Deep recurrent neural model for multi domain sentiment analysis with attention mechanism," Wireless Pers. Commun., 130(1): 43-60, 2023. [23] N. A. Abdullah, A. Feizollah, A. Sulaiman, N. B. Anuar, "Challenges and recommended solutions in multi-source and multi-domain sentiment analysis," IEEE Access, 7: 144957-144971, 2019. [24] L. P. Hung, S. Alias, "Beyond sentiment analysis: A review of recent trends in text based sentiment analysis and emotion detection," J. Adv. Comput. Intell. Intell. Inf., 27(1): 84-95, 2023. [25] K. Bhattacharjee, R. Gangadharaiah, "Document-level supervision for multi-aspect sentiment analysis without fine-grained labels," arXiv preprint arXiv:2310.06940, 2023. [26] J. Lafferty, A. McCallum, F. Pereira, "Conditional random fields: Probabilistic models for segmenting and labeling sequence data," in Icml, 1(2): 3, Williamstown, MA, 2001. [27] H. Cai et al., "Memd-absa: a multi-element multi-domain dataset for aspect-based sentiment analysis," arXiv preprint arXiv:2306.16956, 2023. [28] H. Chen, Z. Zhai, F. Feng, R. Li, X. Wang, "Enhanced multi-channel graph convolutional network for aspect sentiment triplet extraction," in Proc. the 60th Annual Meeting of the Association for Computational Linguistics (volume 1: long papers): 2974-2985, 2022. [29] Z. Zhai, H. Chen, F. Feng, R. Li, X. Wang, "COM-MRC: a context-masked machine reading comprehension framework for aspect sentiment triplet extraction," in Proc. the 2022 Conference on Empirical Methods in Natural Language Processing: 3230-3241, 2022. [30] L. Xianlong, M. Yang, Y. Wang, "Tagging-assisted generation model with encoder and decoder supervision for aspect sentiment triplet extraction," in Proc. the 2023 Conference on Empirical Methods in Natural Language Processing: 2078-2093, 2023. [31] J. Yang, F. Dai, F. Li, Y. Xue, "Span-based pair-wise aspect and opinion term joint extraction with contrastive learning," in Proc. CCF International Conference on Natural Language Processing and Chinese Computing: 17-29, 2023. [32] P. Li, P. Li, X. Xiao, "Aspect-pair supervised contrastive learning for aspect-based sentiment analysis," Knowledge-Based Syst., 274: 110648, 2023. [33] S. Yang, X. Jiang, H. Zhao, W. Zeng, H. Liu, Y. Jia, "FaiMA: Feature-aware in-context learning for multi-domain aspect-based sentiment analysis," arXiv preprint arXiv:2403.01063, 2024.
آمار تعداد مشاهده مقاله: 283 تعداد دریافت فایل اصل مقاله: 29

سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب

پیوندهای مفید

آمار

Weighted Words Multi-Domain Model for Aspect-Opinion Pairs Extraction