Abstract
Aspect-Based Sentiment Classification (ABSC) models are increasingly utilised given the surge in opinionated text displayed on the Web. This paper aims to explain the outcome of a black box state-of-the-art deep learning model used for ABSC, LCR-Rot-hop++. We compare two sampling methods that feed an interpretability algorithm which is based on local linear approximations (LIME). One of the sampling methods, SS, swaps out different words from the original sentence with other similar words to create neighbours to the original sentence. The second method, SSb, uses SS and then filters its neighbourhood to better balance the sentiment proportions in the localities created. We use a 2016 restaurant reviews dataset for ternary classification and we judge the interpretability algorithms based on their hit rate and fidelity. We find that SSb can improve neighbourhood sentiment balance compared to SS, reducing bias for the majority class, while simultaneously increasing the performance of LIME.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Brauwers, G., Frasincar, F.: A survey on aspect-based sentiment classification. ACM Comput. Surv. 55(4), 65:1–65:37 (2023)
Du, M., Liu, N., Hu, X.: Techniques for interpretable machine learning. arXiv preprint arXiv:1808.00033 (2018)
Godbole, S., Roy, S.: Text classification, business intelligence, and interactivity: automating C-SAT analysis for services industry. In: 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2008), pp. 911–919. ACM (2008)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Pedreschi, D., Giannotti, F.: A survey of methods for explaining black box models. arXiv preprint arXiv:1802.01933 (2018)
Kunal, G., Frasincar, F., Truşcă, M.M.: Explaining a deep neural model with hierarchical attention for aspect-based sentiment classification. In: Di Noia, T., Ko, I.Y., Schedl, M., Ardito, C. (eds.) ICWE 2022. LNCS, vol. 13362, pp. 268–282. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-09917-5_18
Liu, B.: Sentiment Analysis: Mining Opinions, Sentiments, and Emotions, 2nd edn. Cambridge University Press, Cambridge (2020)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: 31st Annual Conference on Neural Information Processing Systems (NIPS 2017), vol. 30, pp. 4765–4774 (2017)
Meijer, L., Frasincar, F., Truşcă, M.M.: Explaining a neural attention model for aspect-based sentiment classification using diagnostic classification. In: 36th ACM/SIGAPP Symposium on Applied Computing (SAC 2021), pp. 821–827. ACM (2021)
Molnar, C.: Interpretable machine learning. In: Second International Workshop in eXplainable Knowledge Discovery in Data Mining (XKDD 2020). CCIS, vol. 1323, p. 414. Springer, Cham (2020)
Pastor, E., Baralis, E.: Explaining black box models by means of local rules. In: 34th ACM/SIGAPP Symposium on Applied Computing (SAC 2019), pp. 510–517. ACM (2019)
Pontiki, M., et al.: SemEval-2016 task 5: aspect based sentiment analysis. In: 10th International Workshop on Semantic Evaluation (SemEval 2016), pp. 19–30. ACL (2016)
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should I trust you?”: explaining the predictions of any classifier. In: 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2016), pp. 1135–1144. ACM (2016)
Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: high-precision model-agnostic explanations. In: Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018), vol. 32, pp. 1527–1535. AAAI Press (2018)
Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., Zhong, C.: Interpretable machine learning: fundamental principles and 10 grand challenges. Stat. Surv. 16, 1–85 (2022)
Schouten, K., Frasincar, F.: Survey on aspect-level sentiment analysis. IEEE Trans. Knowl. Data Eng. 28(3), 813–830 (2016)
Schouten, K., Frasincar, F., de Jong, F.: Ontology-enhanced aspect-based sentiment analysis. In: Cabot, J., De Virgilio, R., Torlone, R. (eds.) ICWE 2017. LNCS, vol. 10360, pp. 302–320. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-60131-1_17
Singla, Z., Randhawa, S., Jain, S.: Statistical and sentiment analysis of consumer product reviews. In: 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT 2017), pp. 1–6. IEEE (2017)
Truşcă, M.M., Frasincar, F.: Survey on aspect detection for aspect-based sentiment analysis. Artif. Intell. Rev. 56(5), 3797–3846 (2023)
Truşcǎ, M.M., Wassenberg, D., Frasincar, F., Dekker, R.: A hybrid approach for aspect-based sentiment analysis using deep contextual word embeddings and hierarchical attention. In: Bielikova, M., Mikkonen, T., Pautasso, C. (eds.) ICWE 2020. LNCS, vol. 12128, pp. 365–380. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-50578-3_25
Wallaart, O., Frasincar, F.: A hybrid approach for aspect-based sentiment analysis using a lexicalized domain ontology and attentional neural models. In: Hitzler, P., et al. (eds.) ESWC 2019. LNCS, vol. 11503, pp. 363–378. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-21348-0_24
Zheng, S., Xia, R.: Left-center-right separated neural network for aspect-based sentiment analysis with rotatory attention. arXiv preprint arXiv:1802.00892 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Miron, V., Frasincar, F., Truşcǎ, M.M. (2023). Explaining a Deep Learning Model for Aspect-Based Sentiment Classification Using Post-hoc Local Classifiers. In: Métais, E., Meziane, F., Sugumaran, V., Manning, W., Reiff-Marganiec, S. (eds) Natural Language Processing and Information Systems. NLDB 2023. Lecture Notes in Computer Science, vol 13913. Springer, Cham. https://doi.org/10.1007/978-3-031-35320-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-35320-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35319-2
Online ISBN: 978-3-031-35320-8
eBook Packages: Computer ScienceComputer Science (R0)