Abstract
With the pervasive use of Sentiment Analysis (SA) models in financial and social settings, performance is no longer the sole concern for reliable and accountable deployment. SA models are expected to explain their behavior and highlight textual evidence of their predictions. Recently, Explainable AI (ExAI) is enabling the “third AI wave” by providing explanations for the highly non-linear black-box deep AI models. Nonetheless, current ExAI methods, especially in the NLP field, are conducted on various datasets by employing different metrics to evaluate several aspects. The lack of a common evaluation framework is hindering the progress tracking of such methods and their wider adoption.
In this work, inspired by offline information retrieval, we propose different metrics and techniques to evaluate the explainability of SA models from two angles. First, we evaluate the strength of the extracted “rationales” in faithfully explaining the predicted outcome. Second, we measure the agreement between ExAI methods and human judgment on a homegrown dataset (Dataset and code available at https://gitlab.com/awadailab/exai-nlp-eval) to reflect on the rationales plausibility. Our conducted experiments comprise four dimensions: (1) the underlying architectures of SA models, (2) the approach followed by the ExAI method, (3) the reasoning difficulty, and (4) the homogeneity of the ground-truth rationales.
We empirically demonstrate that anchors explanations are more aligned with the human judgment and can be more confident in extracting supporting rationales. As can be foreseen, the reasoning complexity of sentiment is shown to thwart ExAI methods from extracting supporting evidence. Moreover, a remarkable discrepancy is discerned between the results of different explainability methods on the various architectures suggesting the need for consolidation to observe enhanced performance. Predominantly, transformers are shown to exhibit better explainability than convolutional and recurrent architectures. Our work paves the way towards designing more interpretable NLP models and enabling a common evaluation ground for their relative strengths and robustness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Refers to the metric hereafter.
- 2.
Instructions to labelers are provided in the supplementary material.
References
Arras, L., Horn, F., Montavon, G., Müller, K., Samek, W.: What is relevant in a text document?: an interpretable machine learning approach. arXiv preprint arXiv:1612.07843 (2016)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS One 10(7), e0130140 (2015)
Bodria, F., Panisson, A., Perotti, A., Piaggesi, S.: Explainability methods for natural language processing: applications to sentiment analysis (discussion paper) (2020)
Cer, D.E.A.: Universal sentence encoder for English. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 169–174. Association for Computational Linguistics, Brussels (2018)
Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) (2018)
Chen, H., Ji, Y.: Improving the explainability of neural sentiment classifiers via data augmentation. arXiv preprint arXiv:1909.04225 (2019)
Danilevsky, M., Qian, K., Aharonov, R., Katsis, Y., Kawas, B., Sen, P.: A survey of the state of explainable AI for natural language processing (2020)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
DeYoung, J., et al.: Eraser: a benchmark to evaluate rationalized NLP models. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4443–4458 (2020)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 1–42 (2018)
Habimana, O., Li, Y., Li, R., Gu, X., Yu, G.: Sentiment analysis using deep learning approaches: an overview. Sci. China Inf. Sci. 63(1), 1–36 (2019). https://doi.org/10.1007/s11432-018-9941-6
Hassan, A., Mahmood, A.: Deep learning approach for sentiment analysis of short texts. In: 2017 3rd International Conference on Control, Automation and Robotics (ICCAR), pp. 705–710. IEEE (2017)
Jacovi, A., Goldberg, Y.: Towards faithfully interpretable NLP systems: how should we define and evaluate faithfulness? In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4198–4205 (2020)
Jain, S., Wallace, B.C.: Attention is not explanation. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 3543–3556 (2019)
Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations (2020)
Liu, Y., et al.: Roberta: a robustly optimized Bert pretraining approach (2019)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 4765–4774 (2017)
Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, June 2011, pp. 142–150 (2011)
Mishra, P.: Explainability for Non-Linear Models, pp. 93–127. Apress, Berkeley (2022). https://doi.org/10.1007/978-1-4842-7158-2_4
Mullenbach, J., Wiegreffe, S., Duke, J., Sun, J., Eisenstein, J.: Explainable prediction of medical codes from clinical text. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long Papers), pp. 1101–1111 (2018)
Nguyen, A., Yosinski, J., Clune, J.: Understanding neural networks via feature visualization: a survey. In: Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., Müller, K.-R. (eds.) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNCS (LNAI), vol. 11700, pp. 55–76. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28954-6_4
Onan, A.: Sentiment analysis on massive open online course evaluations: a text mining and deep learning approach. Comput. Appl. Eng. Educ. 29(3), 572–589 (2021)
Pang, B., Lee, L.: Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales. In: Proceedings of the ACL (2005)
Patro, B.N., Lunayach, M., Patel, S., Namboodiri, V.P.: U-cam: visual explanation using uncertainty based class activation maps. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7444–7453 (2019)
Qin, Z., Yu, F., Liu, C., Chen, X.: How convolutional neural network see the world - a survey of convolutional neural network visualization methods (2018)
Radford, A., Jozefowicz, R., Sutskever, I.: Learning to generate reviews and discovering sentiment. arXiv preprint arXiv:1704.01444 (2017)
Rambocas, M., Gama, J., et al.: Marketing Research: The Role of Sentiment Analysis. Universidade do Porto, Faculdade de Economia do Porto, Tech. Rep. (2013)
Rambocas, M., Pacheco, B.G.: Online sentiment analysis in marketing research: a review. J. Res. Interact. Market. (2018)
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you?: explaining the predictions of any classifier (2016)
Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: high-precision model-agnostic explanations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Samek, W., Müller, K.-R.: Towards explainable artificial intelligence. In: Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., Müller, K.-R. (eds.) Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNCS (LNAI), vol. 11700, pp. 5–22. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28954-6_1
Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of Bert: smaller, faster, cheaper and lighter (2020)
Serrano, S., Smith, N.A.: Is attention interpretable? In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2931–2951 (2019)
Shi, Y., Zhu, L., Li, W., Guo, K., Zheng, Y.: Survey on classic and latest textual sentiment analysis articles and techniques. Int. J. Inf. Technol. Decis. Making 18(04), 1243–1287 (2019)
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences (2019)
De Sousa Silveira, T., Uszkoreit, H., Ai, R.: Using aspect-based analysis for explainable sentiment predictions. In: Tang, J., Kan, M.-Y., Zhao, D., Li, S., Zan, H. (eds.) NLPCC 2019. LNCS (LNAI), vol. 11839, pp. 617–627. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32236-6_56
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. arXiv preprint arXiv:1703.01365 (2017)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding (2020)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. arXiv preprint arXiv:1311.2901 (2013)
Zini, J.E., Awad, M.: On the Explainability of Natural Language Processing Deep Models. ACM Computing Surveys (2022)
Acknowledgment
This work was supported by the University Research Board (URB) and the Maroun Semaan Faculty of Engineering and Architecture (MSFEA) at the American University of Beirut.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 IFIP International Federation for Information Processing
About this paper
Cite this paper
El Zini, J., Mansour, M., Mousi, B., Awad, M. (2022). On the Evaluation of the Plausibility and Faithfulness of Sentiment Analysis Explanations. In: Maglogiannis, I., Iliadis, L., Macintyre, J., Cortez, P. (eds) Artificial Intelligence Applications and Innovations. AIAI 2022. IFIP Advances in Information and Communication Technology, vol 647. Springer, Cham. https://doi.org/10.1007/978-3-031-08337-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-08337-2_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08336-5
Online ISBN: 978-3-031-08337-2
eBook Packages: Computer ScienceComputer Science (R0)