Abstract
Due to their inherent capability in the semantic alignment of aspects and their context words, Attention and Long-Short-Term-Memory (LSTM) mechanisms are widely adopted for Aspect-Based Sentiment Classification (ABSC) tasks. Instead, it is challenging to handle long-range word dependencies on multiple entities due to the deficiency in attention mechanisms. To solve this problem, we propose a Context-Focused Aspect-Based Network to align attention before LSTM, making the model focus more on aspect-related words and ignore irrelevant words, improving the accuracy of final classification. This can either alleviate attention distraction or reinforce the text representation ability. Experiments on two benchmark datasets show that the results achieve respectable performance compared to the state-of-the-art methods available in ABSC. Our approach has the potential to improve classification accuracy by adaptively adjusting the focus on context.
- [1] . 2020. Sentiment analysis using deep learning architectures: A review. Artif. Intell. Rev. 53, 6 (2020), 4335–4385.Google Scholar
Digital Library
- [2] . 2020. Sentiment analysis based on deep learning: A comparative study. Electronics 9, 3 (2020), 483.Google Scholar
Cross Ref
- [3] . 2019. A survey on classification techniques for opinion mining and sentiment analysis. Artif. Intell. Rev. 52, 3 (2019), 1495–1545.Google Scholar
Digital Library
- [4] . 2012. Sentiment analysis and opinion mining. Synth. Lect. Hum. Lang. Technol. 5, 1 (2012), 1–167.Google Scholar
Cross Ref
- [5] . 2007. Opinion mining and sentiment analysis. Found. Trends Inf. Retriev. 2, 1–2 (2007), 1–135.Google Scholar
- [6] . 2021. Spider monkey crow optimization algorithm with deep learning for sentiment classification and information retrieval. IEEE Access 9 (2021), 24249–24262.Google Scholar
Cross Ref
- [7] . 2022. CE-text: A context-Aware and embedded text detector in natural scene images. Pattern Recogn. Lett. 159 (2022), 77–83.Google Scholar
Digital Library
- [8] . 2021. Multiple attention encoded cascade R-CNN for scene text detection. J. Vis. Commun. Image Represent. 80 (2021), 103261.Google Scholar
Digital Library
- [9] . 2020. Stimulus-driven and concept-driven analysis for image caption generation. Neurocomputing 398 (2020), 520–530.Google Scholar
Cross Ref
- [10] . 2016. Aspect level sentiment classification with deep memory network. ACM Transactions on Intelligent Systems and Technology 9, 2 (2016), 1--19.Google Scholar
- [11] . 2019. Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion. Inf. Process. Manage. 56, 4 (2019), 1245–1259.Google Scholar
Digital Library
- [12] . 2021. Deep learning for aspect-based sentiment analysis. In Proceedings of the International Conference on Machine Learning and Intelligent Systems Engineering (MLISE’21). IEEE. 267–271.Google Scholar
Cross Ref
- [13] . 2017. Interactive attention networks for aspect-level sentiment classification. arXiv preprint arXiv:1709.00893. (2017).Google Scholar
- [14] . 2020. A novel hybrid deep learning model for sentiment classification. IEEE Access 8 (2020), 58080–58093.Google Scholar
Cross Ref
- [15] . 2018. Transformation networks for target-oriented sentiment classification. arXiv:1805.01086. Retrieved from https://arxiv.org/abs/1805.01086. Google Scholar
Cross Ref
- [16] . 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805. Retrieved from https://arxiv.org/abs/1810.04805.Google Scholar
- [17] . 1997. Long short-term memory. Neural Comput. 9, 8 (1997), 1735–1780.Google Scholar
Digital Library
- [18] . 2017. Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017), 5998–6008.Google Scholar
- [19] . 2005. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18, 5-6 (2005), 602–610.Google Scholar
Digital Library
- [20] . 2012. Fine granular aspect analysis using latent structural models. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers-Volume 2. Association for Computational Linguistics, New York, NY, 333–337.Google Scholar
Digital Library
- [21] . 2009. OpinionMiner: A novel machine learning system for web opinion mining and extraction. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1195–1204.Google Scholar
Digital Library
- [22] . 2011. Target-dependent twitter sentiment classification. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. Association for Computational Linguistics, New York, NY, 151–160.Google Scholar
Digital Library
- [23] . 2014. NRC-Canada-2014: Detecting aspects and sentiment in customer reviews. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval’14). 437–442.Google Scholar
Cross Ref
- [24] . 2014. Adaptive recursive neural network for target-dependent twitter sentiment classification. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: Short Papers, Volume 2. 49–54.Google Scholar
Cross Ref
- [25] . 2016. Effective LSTMs for target-dependent sentiment classification. In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers (COLING’16). 3298–3307.Google Scholar
- [26] . 2014. Neural machine translation by jointly learning to align and translate. arXiv:1409.0473. Retrieved from https://arxiv.org/abs/1409.0473.Google Scholar
- [27] . 2017. Attention is all you need. In Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS’17). 6000–6010.Google Scholar
- [28] . 2015. Document modeling with gated recurrent neural network for sentiment classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’15). 1422–1432.Google Scholar
Cross Ref
- [29] . 2016. Attention-based LSTM for aspect-level sentiment classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’16). 606–615.Google Scholar
Cross Ref
- [30] . 2015. A neural attention model for abstractive sentence summarization. arXiv:1509.00685. Retrieved from https://arxiv.org/abs/1509.00685.Google Scholar
- [31] . 2017. Recurrent attention network on memory for aspect sentiment analysis. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’17). 452–461.Google Scholar
Cross Ref
- [32] . 2018. Aspect sentiment classification with both word-level and clause-level attention networks. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’18). 4439–4445.Google Scholar
Cross Ref
- [33] . 2016. Hierarchical attention networks for document classification. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1480–1489.Google Scholar
Cross Ref
- [34] . 2018. Aspect level sentiment classification with attention-over-attention neural networks. In International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation. Springer, Cham. 197–206.Google Scholar
Cross Ref
- [35] . 2018. A position-aware bidirectional attention network for aspect-level sentiment analysis. In Proceedings of the 27th International Conference on Computational Linguistics. 774–784.Google Scholar
- [36] . 2015. Gated feedback recurrent neural networks. In Proceedings of the International Conference on Machine Learning. 2067–2075.Google Scholar
- [37] . 2018. Content attention model for aspect based sentiment analysis. In Proceedings of the World Wide Web Conference. 1023–1032.Google Scholar
Digital Library
- [38] . 2018. Multi-grained attention network for aspect-level sentiment classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’18). 3433–3442.Google Scholar
Cross Ref
- [39] 2020. Aspect-based sentiment classification with multi-attention network. Neurocomputing 388, (2020), 135–143.Google Scholar
Digital Library
- [40] . 2019. A challenge dataset and effective models for aspect-based sentiment analysis. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 6281–6286.Google Scholar
Cross Ref
- [41] . 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. 249–256.Google Scholar
- [42] . 2014. Glove: Global vectors for word representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14). 1532–1543.Google Scholar
Cross Ref
- [43] . 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https://arxiv.org/abs/1412.6980.Google Scholar
Index Terms
A Context-focused Attention Evolution Model for Aspect-based Sentiment Classification
Recommendations
Aspect-level Sentiment Classification with HEAT (HiErarchical ATtention) Network
CIKM '17: Proceedings of the 2017 ACM on Conference on Information and Knowledge ManagementAspect-level sentiment classification is a fine-grained sentiment analysis task, which aims to predict the sentiment of a text in different aspects. One key point of this task is to allocate the appropriate sentiment words for the given aspect.Recent ...
Explaining a neural attention model for aspect-based sentiment classification using diagnostic classification
SAC '21: Proceedings of the 36th Annual ACM Symposium on Applied ComputingMany high performance machine learning models for Aspect-Based Sentiment Classification (ABSC) produce black box models, and therefore barely explain how they classify a certain sentiment value towards an aspect. In this paper, we propose explanation ...
Modeling Multi-aspect Relationship with Joint Learning for Aspect-Level Sentiment Classification
Database Systems for Advanced ApplicationsAbstractAspect-level sentiment classification is a crucial branch for sentiment classification. Most of the existing work focuses on how to model the semantic relationship between the aspect and the sentence, while the relationships among the multiple ...






Comments