LLM Enhanced Cross Domain Aspect-based Sentiment Analysis
Author:
Affiliation:

  • Article
  • | |
  • Metrics
  • |
  • Reference [67]
  • |
  • Related
  • | | |
  • Comments
    Abstract:

    As a fine-grained sentiment analysis method, aspect-based sentiment analysis is playing an increasingly important role in many application scenarios. However, with the ubiquity of social media and online reviews, cross-domain aspect-based sentiment analysis faces two major challenges: insufficient labeled data in the target domain and textual distribution differences between the source and target domains. Currently, many data augmentation methods attempt to alleviate these issues, yet the target domain text generated by these methods often suffers from shortcomings such as lack of fluency, limited diversity of generated data, and convergent source domain. To address these issues, this study proposes a method for cross-domain aspect-based sentiment analysis based on data augmentation from a large language model (LLM). This method leverages the rich language knowledge of large language models to construct appropriate prompts for the cross-domain aspect-based sentiment analysis task. It mines similar texts between the target domain and the source domain and uses context learning to guide the LLM to generate labeled text data in the target domain with domain-associated keywords. This approach addresses the lack of data in the target domain and the domain-specificity problem, effectively improving the accuracy and robustness of cross-domain sentiment analysis. Experiments on multiple real datasets show that the proposed method can effectively enhance the performance of the baseline model in cross-domain aspect-based sentiment analysis.

    Reference
    [1] Liu B. Sentiment Analysis and Opinion Mining. Cham: Springer, 2012. 1–167. [doi: 10.1007/978-3-031-02145-9]
    [2] Hu MQ, Liu B. Mining and summarizing customer reviews. In: Proc. of the 10th ACM SIGKDD Int’l Conf. on Knowledge Discovery and Data Mining. Seattle: ACM, 2004. 168–177. [doi: 10.1145/1014052.1014073]
    [3] Liu HY, Chatterjee I, Zhou MC, Lu XS, Abusorrah A. Aspect-based sentiment analysis: A survey of deep learning methods. IEEE Trans. on Computational Social Systems, 2020, 7(6): 1358–1375.
    [4] 赵妍妍, 秦兵, 刘挺. 文本情感分析. 软件学报, 2010, 21(8): 1834–1848. http://www.jos.org.cn/1000-9825/3832.htm
    Zhao YY, Qin B, Liu T. Sentiment analysis. Ruan Jian Xue Bao/Journal of Software, 2010, 21(8): 1834–1848 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/3832.htm
    [5] 赵传君, 王素格, 李德玉. 跨领域文本情感分类研究进展. 软件学报, 2020, 31(6): 1723–1746. http://www.jos.org.cn/1000-9825/6029.htm
    Zhao CJ, Wang SG, Li DY. Research progress on cross-domain text sentiment classification. Ruan Jian Xue Bao/Journal of Software, 2020, 31(6): 1723–1746 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6029.htm
    [6] Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans. on Knowledge and Data Engineering, 2010, 22(10): 1345–1359.
    [7] Cai HJ, Xia R, Yu JF. Aspect-category-opinion-sentiment quadruple extraction with implicit aspects and opinions. In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing (Vol. 1: Long Papers). Association for Computational Linguistics, 2021. 340–350. [doi: 10.18653/v1/2021.acl-long.29]
    [8] Chen CH, Teng ZY, Wang ZQ, Zhang Y. Discrete opinion tree induction for aspect-based sentiment analysis. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers). Dublin: Association for Computational Linguistics, 2022. 2051–2064. [doi: 10.18653/v1/2022.acl-long.145]
    [9] Liu J, Teng ZY, Cui LY, Liu HM, Zhang Y. Solving aspect category sentiment analysis as a text generation task. In: Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing. Punta Cana: Association for Computational Linguistics, 2021. 4406–4416. [doi: 10.18653/v1/2021.emnlp-main.361]
    [10] Xia R, Zong CQ. A POS-based ensemble model for cross-domain sentiment classification. In: Proc. of the 5th Int’l Joint Conf. on Natural Language Processing. Chiang Mai: Asian Federation of Natural Language Processing, 2011. 614–622.
    [11] Zhou J, Tian JF, Wang R, Wu YB, Xiao WM, He L. SentiX: A sentiment-aware pre-trained model for cross-domain sentiment analysis. In: Proc. of the 28th Int’l Conf. on Computational Linguistics. Barcelona: Int’l Committee on Computational Linguistics, 2020. 568–579. [doi: 10.18653/v1/2020.coling-main.49]
    [12] Karouzos C, Paraskevopoulos G, Potamianos A. UDALM: Unsupervised domain adaptation through language modeling. In: Proc. of the 2021 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 2021. 2579–2590.
    [13] Ben-David E, Rabinovitz C, Reichart R. PERL: Pivot-based domain adaptation for pre-trained deep contextualized embedding models. Trans. of the Association for Computational Linguistics, 2020, 8: 504–521.
    [14] Wu H, Shi XD. Adversarial soft prompt tuning for cross-domain sentiment analysis. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers). Dublin: Association for Computational Linguistics, 2022. 2438–2447. [doi: 10.18653/v1/2022.acl-long.174]
    [15] Wang WY, Pan SJ. Recursive neural structural correspondence network for cross-domain aspect and opinion co-extraction. In: Proc. of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne: Association for Computational Linguistics, 2018. 2171–2181. [doi: 10.18653/v1/P18-1202]
    [16] Gong C, Yu J, Xia R. Unified feature and instance based domain adaptation for aspect-based sentiment analysis. In: Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2020. 7035–7045.
    [17] Yu JF, Zhao QK, Xia R. Cross-domain data augmentation with domain-adaptive language modeling for aspect-based sentiment analysis. In: Proc. of the 61st Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers). Toronto: Association for Computational Linguistics, 2023. 1456–1470. [doi: 10.18653/v1/2023.acl-long.81]
    [18] Yang LY, Yuan LF, Cui LY, Gao WY, Zhang Y. FactMix: Using a few labeled in-domain examples to generalize to cross-domain named entity recognition. In: Proc. of the 29th Int’l Conf. on Computational Linguistics. Gyeongju: Int’l Committee on Computational Linguistics, 2022. 5360–5371.
    [19] Yu JF, Gong CG, Xia R. Cross-domain review generation for aspect-based sentiment analysis. In: Proc. of the 2021 Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, 2021. 4767–4777.
    [20] Ouyang L, Wu J, Jiang X, Almeida D, Wainwright CL, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J, Hilton J, Kelton F, Miller L, Simens M, Askell A, Welinder P, Christiano PF, Leike J, Lowe R. Training language models to follow instructions with human feedback. In: Proc. of the 36th Annual Conf. on Neural Information Processing Systems. New Orleans, 2022.
    [21] Bai YT, Jones A, Ndousse K, et al. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv:2204.05862, 2022.
    [22] Tang DY, Qin B, Feng XC, Liu T. Effective LSTMs for target-dependent sentiment classification. In: Proc. of the 26th Int’l Conf. on Computational Linguistics: Technical Papers. Osaka: The COLING 2016 Organizing Committee, 2016. 3298–3307.
    [23] Zhang B, Xu D, Zhang H, Li MZ. STCS lexicon: Spectral-clustering-based topic-specific Chinese sentiment lexicon construction for social networks. IEEE Trans. on Computational Social Systems, 2019, 6(6): 1180–1189.
    [24] 鲍小异, 姜晓彤, 王中卿, 周国栋. 基于跨语言图神经网络模型的属性级情感分类. 软件学报, 2023, 34(2): 676–689. http://www.jos.org.cn/1000-9825/6667.htm
    Bao XY, Jiang XT, Wang ZQ, Zhou GD. Cross-lingual aspect-level sentiment classification with graph neural network. Ruan Jian Xue Bao/Journal of Software, 2023, 34(2): 676–689 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6667.htm
    [25] 冯超, 黎海辉, 赵洪雅, 薛云, 唐婧尧. 基于层次注意力机制和门机制的属性级别情感分析. 中文信息学报, 2021, 35(10): 128–136.
    Feng C, Li HH, Zhao HY, Xue Y, Tang JY. Aspect-level sentiment analysis based on hierarchical attention and gate networks. Journal of Chinese Information Processing, 2021, 35(10): 128–136 (in Chinese with English abstract).
    [26] 闫金凤, 邵新慧. 基于图卷积网络的特定方面情感分析. 中文信息学报, 2022, 36(10): 135–144.
    Yan JF, Shao XH. Aspect-level sentiment analysis based on graph convolutional network. Journal of Chinese Information Processing, 2022, 36(10): 135–144 (in Chinese with English abstract).
    [27] Bao LX, Lambert P, Badia T. Attention and lexicon regularized LSTM for aspect-based sentiment analysis. In: Proc. of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop. Florence: Association for Computational Linguistics, 2019. 253–259. [doi: 10.18653/v1/P19-2035]
    [28] Ma DH, Li SJ, Zhang XD, Wang HF. Interactive attention networks for aspect-level sentiment classification. In: Proc. of the 26th Int’l Joint Conf. on Artificial Intelligence. Melbourne: AAAI Press, 2017. 4068–4074.
    [29] Chen P, Sun ZQ, Bing LD, Yang W. Recurrent attention network on memory for aspect sentiment analysis. In: Proc. of the 2017 Conf. on Empirical Methods in Natural Language Processing. Copenhagen: Association for Computational Linguistics, 2017. 452–461. [doi: 10.18653/v1/D17-1047]
    [30] Li X, Bing LD, Zhang WX, Lam W. Exploiting BERT for end-to-end aspect-based sentiment analysis. In: Proc. of the 5th Workshop on Noisy User-generated Text. Hong Kong: Association for Computational Linguistics, 2019. 34–41. [doi: 10.18653/v1/D19-5505]
    [31] Huang BX, Carley KM. Syntax-aware aspect level sentiment classification with graph attention networks. In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019. 5469–5477. [doi: 10.18653/v1/D19-1549]
    [32] Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou YQ, Li W, Liu PJ. Exploring the limits of transfer learning with a unified text-to-text Transformer. The Journal of Machine Learning Research, 2020, 21(1): 140.
    [33] Lewis M, Liu YH, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proc. of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2020. 7871–7880. [doi: 10.18653/v1/2020.acl-main.703]
    [34] Zhang WX, Li X, Deng Y, Bing LD, Lam W. Towards generative aspect-based sentiment analysis. In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing. Association for Computational Linguistics, 2021. 504–510.
    [35] Yan H, Dai JQ, Ji T, Qiu XP, Zhang Z. A unified generative framework for aspect-based sentiment analysis. In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing. Association for Computational Linguistics, 2021. 2416–2429.
    [36] Lu YJ, Liu Q, Dai D, Xiao XY, Lin HY, Han XP, Sun L, Wu H. Unified structure generation for universal information extraction. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers). Dublin: Association for Computational Linguistics, 2022. 5755–5772. [doi: 10.18653/v1/2022.acl-long.395]
    [37] Fei H, Wu SQ, Li JY, Li BB, Li F, Qin LB, Zhang MS, Zhang M, Chua TS. LasUIE: Unifying information extraction with latent adaptive structure-aware generative language model. In: Proc. of the 36th Annual Conf. on Neural Information Processing Systems. New Orleans, 2022.
    [38] 赵光耀, 吕成国, 付国宏, 刘宗林, 梁春丰, 刘涛. 基于领域特有情感词注意力模型的跨领域属性情感分析. 中文信息学报, 2021, 35(6): 93–102.
    Zhao GY, Lv CG, Fu GH, Liu ZL, Liang CF, Liu T. Domain specific sentiment words based attention model for cross-domain attribute-oriented sentiment analysis. Journal of Chinese Information Processing, 2021, 35(6): 93–102 (in Chinese with English abstract).
    [39] Blitzer J, Dredze M, Pereira F. Biographies, Bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. In: Proc. of the 45th Annual Meeting of the Association of Computational Linguistics. Prague: Association for Computational Linguistics, 2007. 440–447.
    [40] Ziser Y, Reichart R. Task refinement learning for improved accuracy and stability of unsupervised domain adaptation. In: Proc. of the 57th Annual Meeting of the Association for Computational Linguistics. Florence: Association for Computational Linguistics, 2019. 5895–5906. [doi: 10.18653/v1/P19-1591]
    [41] Du CN, Sun HF, Wang JY, Qi Q, Liao JX. Adversarial and domain-aware BERT for cross-domain sentiment analysis. In: Proc. of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2020. 4019–4028.
    [42] Xue QM, Zhang W, Zha HY. Improving domain-adapted sentiment classification by deep adversarial mutual learning. In: Proc. of the 34th AAAI Conf. on Artificial Intelligence, the 32nd Innovative Applications of Artificial Intelligence Conf., and the 10th AAAI Symp. on Educational Advances in Artificial Intelligence. New York: AAAI Press, 2020. 9362–9369. [doi: 10.1609/aaai.v34i05.6477]
    [43] Li BH, Hou YT, Che WX. Data augmentation approaches in natural language processing: A survey. AI Open, 2022, 3: 71–90.
    [44] Li JJ, Yu JF, Xia R. Generative cross-domain data augmentation for aspect and opinion co-extraction. In: Proc. of the 2022 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Seattle: Association for Computational Linguistics, 2022. 4219–4229. [doi: 10.18653/v1/2022.naacl-main.312]
    [45] Zhao WX, Zhou K, Li JY, Tang TY, Wang XL, Hou YP, Min YQ, Zhang BC, Zhang JJ, Dong ZC, Du YF, Yang C, Chen YS, Chen ZP, Jiang JH, Ren RY, Li YF, Tang XY, Liu ZK, Liu PY, Nie JY, Wen JR. A survey of large language models. arXiv:2303.18223, 2023.
    [46] Brown TB, Mann B, Ryder N, et al. Language models are few-shot learners. In: Proc. of the 34th Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2020. 159.
    [47] Touvron H, Lavril T, Izacard G, Martinet X, Lachaux MA, Lacroix T, Rozière B, Goyal N, Hambro E, Azhar F, Rodriguez A, Joulin A, Grave E, Lample G. LLaMa: Open and efficient foundation language models. arXiv:2302.13971, 2023.
    [48] Jiao WX, Wang WX, Huang JT, Wang X, Shi SM, Tu ZP. Is ChatGPT a good translator? Yes with GPT-4 as the engine. arXiv:2301.08745, 2023.
    [49] Wang ZZ, Xie QM, Ding ZX, Feng Y, Xia R. Is ChatGPT a good sentiment analyzer? A preliminary study. arXiv:2304.04339, 2023.
    [50] Gao TY, Yao XC, Chen DQ. SimCSE: Simple contrastive learning of sentence embeddings. In: Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2021. 6894–6910.
    [51] Rose S, Engel D, Cramer N, Cowley W. Automatic keyword extraction from individual documents. In: Berry MW, Kogan J, eds. Text Mining: Applications and Theory. Chichester: Wiley, 2010. 1–20. [doi: 10.1002/9780470689646.ch1]
    [52] Zhang ZS, Zhang A, Li M, Smola A. Automatic chain of thought prompting in large language models. In: Proc. of the 11th Int’l Conf. on Learning Representations. Kigali: OpenReview.net, 2023.
    [53] Pontiki M, Galanis D, Pavlopoulos J, Papageorgiou H, Androutsopoulos I, Manandhar S. SemEval-2014 task 4: Aspect based sentiment analysis. In: Proc. of the 8th Int’l Workshop on Semantic Evaluation. Dublin: Association for Computational Linguistics, 2014. 27–35. [doi: 10.3115/v1/S14-2004]
    [54] Pontiki M, Galanis D, Papageorgiou H, Manandhar S, Androutsopoulos I. SemEval-2015 task 12: Aspect based sentiment analysis. In: Proc. of the 9th Int’l Workshop on Semantic Evaluation (SemEval 2015). Denver: Association for Computational Linguistics, 2015. 486–495. [doi: 10.18653/v1/S15-2082]
    [55] Pontiki M, Galanis D, Papageorgiou H, Androutsopoulos I, Manandhar S, Al-Smadi M, Al-Ayyoub M, Zhao YY, Qin B, De Clercq O, Hoste V, Apidianaki M, Tannier X, Loukachevitch N, Kotelnikov E, Bel N, Jiménez-Zafra SM, Eryiğit G. SemEval-2016 task 5: Aspect based sentiment analysis. In: Proc. of the 10th Int’l Workshop on Semantic Evaluation. San Diego: Association for Computational Linguistics, 2016. 19–30. [doi: 10.18653/v1/S16-1002]
    [56] Toprak C, Jakob N, Gurevych I. Sentence and expression level annotation of opinions in user-generated discourse. In: Proc. of the 48th Annual Meeting of the Association for Computational Linguistics. Uppsala: Association for Computational Linguistics, 2010. 575–584.
    [57] Kingma DP, Ba J. Adam: A method for stochastic optimization. In: Proc. of the 3rd Int’l Conf. on Learning Representations. San Diego, 2015.
    [58] Devlin J, Chang MW, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional Transformers for language understanding. In: Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long and Short Papers). Minneapolis: Association for Computational Linguistics, 2019. 4171–4186. [doi: 10.18653/v1/N19-1423]
    [59] Ben-David E, Oved N, Reichart R. PADA: Example-based prompt learning for on-the-fly adaptation to unseen domains. Trans. of the Association for Computational Linguistics, 2022, 10: 414–433.
    [60] Wei J, Zou K. EDA: Easy data augmentation techniques for boosting performance on text classification tasks. In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing (EMNLP-IJCNLP). Hong Kong, China: Association for Computational Linguistics, 2019. 6382–6388. [doi: 10.18653/v1/D19-1670]
    [61] Ioffe S. Improved consistent sampling, weighted Minhash and L1 sketching. In: Proc. of the 10th IEEE Int’l Conf. on Data Mining. Sydney: IEEE, 2010. 246–255. [doi: 10.1109/ICDM.2010.80]
    Related
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

李诗晨,王中卿,周国栋.大语言模型驱动的跨领域属性级情感分析.软件学报,2025,36(2):644-659

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:August 31,2023
  • Revised:December 06,2023
  • Online: May 29,2024
  • Published: February 06,2025
You are the first2033772Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address:4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code:100190
Phone:010-62562563 Fax:010-62562533 Email:jos@iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063