方面级情感分析的研究与应用
Research and Application of Aspect-Based Sentiment Analysis
摘要: 在早期的细粒度情感分析任务上，主要由人工进行特征选择，人为的工作量大，传统机器学习模型如支持向量机、朴素贝叶斯等被用于情感分类，但随着近几年神经网络的兴起，多种神经网络代替人为的工作，实验效率大大地提升，因为需要挖掘人们文本表达的观点的信息，本文就多种模型应用于方面级情感分析进行研究和分析，得出其中方面词和上下文之间的语义关系影响重大，针对该方面对模型进行应用，得到效果最好的模型。
Abstract: In the early tasks of Aspect-based Sentiment Analysis, the feature selection was mainly carried out manually with a high human workload, and traditional machine learning models such as support vector machines and Naive Bayes model were used for sentiment classification. However, with the rise of neural networks in recent years, a variety of neural networks have replaced human work, and experimental efficiency has been greatly improved. Because of the need to tap into information about the views expressed in people’s texts, this paper studies and analyzes the application of various models in Aspect-based Sentiment Analysis, concluding that the semantic relationship between aspect words and context has a great influence, and that the models are applied to that aspect to obtain the best results.
文章引用：蔡佳志, 冯翱, 张举. 方面级情感分析的研究与应用[J]. 计算机科学与应用, 2022, 12(8): 2041-2049. https://doi.org/10.12677/CSA.2022.128207

参考文献

[1] 王恒, 唐孝国, 郭俊亮. 基于电商评价的文本情感分析研究与应用[J]. 黑龙江科学, 2022, 13(12): 29-31.
[2] 王海燕, 陶皖, 余玲艳, 王鸣鹃. 文本细粒度情感分析综述[J]. 河南科技学院学报(自然科学版), 2021, 49(4): 67-76.
[3] 马广兴, 曲波, 常琛, 卞浩然. 基于CNN的供热管道泄漏识别方法研究[J/OL]. 电子测量技术: 1-9. http://kns.cnki.net/kcms/detail/11.2175.TN.20220726.0942.006.html, 2022-07-27.
[4] 孙开华, 代余杰, 封晴. 基于机器学习的大数据分析和处理[J]. 中国新通信, 2021, 23(13): 65-66.
[5] Casado-Mansilla, D., Moschos, I., Kama-ra-Esteban, O., Tsolakis, A.C., Borges, C.E., Krinidis, S., et al. (2018) A Human-Centric & Context-Aware IoT Frame-work for Enhancing Energy Efficiency in Buildings of Public Use. IEEE Access, 6, 31444-31456. [Google Scholar] [CrossRef] 
[6] Jatnika, D., Bijaksana, M.A. and Suryani, A.A. (2019) Word2Vec Model Analysis for Semantic Similarities in English Words. Procedia Computer Science, 157, 160-167. [Google Scholar] [CrossRef] 
[7] Pennington, J., Socher, R. and Manning, C. (2014) Glove: Global Vectors for Word Representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, 25-29 October 2014, 1532-1543. [Google Scholar] [CrossRef] 
[8] Liu, B. (2012) Sentiment Analysis and Opinion Mining. Vol. 5, Springer, Cham, 1-167. [Google Scholar] [CrossRef] 
[9] Pontiki, M. and Pavlopoulos, J. (2014) SemEval-2014 Task 4: Aspect Based Sentiment Analysis. Proceedings of International Workshop on Semantic Evaluation, Dublin, 23-29 Au-gust 2014, 27-35. [Google Scholar] [CrossRef] 
[10] Li, X., Bing, L., Zhang, W. and Lam, W. (2019) Exploiting BERT for End-to-End Aspect-based Sentiment Analysis. Association for Computational Linguistics. Proceedings of the 5th Work-shop on Noisy User-generated Text (W-NUT 2019), Hong Kong (China), 4 November 2019, 34-41. [Google Scholar] [CrossRef] 
[11] 韩雨恒. 基于LSTM神经网络的轨道预报算法研究[J]. 科学技术创新, 2022(21): 88-91.
[12] Tang, D., Qin, B., Feng, X. and Liu, T. (2016) Effective LSTMs for Target-Dependent Sentiment Classification. Proceedings of COLING 2016, the 26th International Conference on Computational Linguis-tics: Technical Papers, Osaka, 11-16 December 2016, 3298-3307.
[13] Song, Y., Wang, J., Jiang, T., Liu, Z. and Rao, Y. (2019) Attentional Encoder Net-work for Targeted Sentiment Classification. arXiv:1902.09314.
[14] Gao, Z., Feng, A., Song, X. and Wu, X. (2019) Target-Dependent Sentiment Classification with BERT. IEEE Access, 7, 154290-154299. [Google Scholar] [CrossRef] 
[15] Xue, W. and Li, T. (2018) Aspect Based Sentiment Analysis with Gated Convolutional Networks. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Vol. 1, Melbourne, 15-20 July 20018, 2514-2523. [Google Scholar] [CrossRef] 
[16] Sun, C., Huang, L. and Qiu, X. (2019) Utilizing BERT for As-pect-Based Sentiment Analysis via Constructing Auxiliary Sentence. arXiv:1903.09588.
[17] 张亚琪. 基于BERT预训练模型的功能肽预测问题特征提取算法研究[D]: [硕士学位论文]. 长春: 吉林大学, 2022.[CrossRef] 
[18] 李铁飞, 生龙, 吴迪. BERT-TECNN模型的文本分类方法研究[J]. 计算机工程与应用, 2021, 57(18): 186-193.