• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2022, Volume: 15, Issue: 30, Pages: 1484-1494

Original Article

Using XAI Techniques to Persuade Text Classifier Results: A Case Study of Covid-19 Tweets

Received Date:17 February 2022, Accepted Date:14 July 2022, Published Date:09 August 2022


Background: To offer a transparent decision support system able of classifying tweets’ sentiment into positive, neutral, and negative sentiment and explains the prediction result by XAI techniques Methods: We started by data preprocessing phase. For data representation, we used TF-IDF, and we applied four machine-learning algorithms including Naive Bayes, random forest, logistic regression, and support vector machine, as well as four deep learning RNN, LSTM, GRU, and Bi-directional RNN. To raise model trust, we used LIME and SHAP to improve model explainability. Findings: The empirical findings show that the Logistic Regression model and SVM model using the TF-IDF feature extraction approach have the best performance when compared to the other models, with an average accuracy of 84% and 86% respectively. The data balancing step pushed the accuracy of the Random Forest model from 47% to 73%, other models slightly changed. The performance of deep learning models was better than traditional machine learning models, LSTM and GRU achieve approximately 78%, and Bi-directional RNN achieve 79% for dataset 2. Novelty and applications: we propose a highly accurate approach for SA which has been tested on two datasets. Also, to increase trust in model prediction, we explain the predicted sentiment.

Keywords: Explainable Artificial Intelligent (XAI); Sentiment Analysis; Covid19; Deep Learning; machine learning


  1. Giachanou A, Crestani F. Like It or Not: A Survey of Twitter Sentiment Analysis Methods. J ACM Comput. Surv. 2016;49(2). Available from: https://doi.org/10.1145/2938640
  2. Pang B, Lee L. Opinion Mining and Sentiment Analysis. . Foundations and Trends® in Information Retrieval. 2008;2. Available from: https://doi.org/10.1561/1500000011
  3. Duncan B, Zhang Y. Neural networks for sentiment analysis on Twitter. 2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC). 2015;2015:6–8.
  4. Cho K, Merrienboer BV, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, et al. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics. 2014.
  5. Yang CC. Explainable Artificial Intelligence for Predictive Modeling in Healthcare. Journal of Healthcare Informatics Research. 2022;6(2):228–239. Available from: https://doi.org/10.1007/s41666-022-00114-1
  6. Bangyal WH, Qasim R, Rehman NU, Ahmad Z, Dar H, Rukhsar L, et al. Detection of Fake News Text Classification on COVID-19 Using Deep Learning Approaches. Computational and Mathematical Methods in Medicine. 2021;2021:1–14. Available from: https://doi.org/10.1109/ACCESS.2018.2870052
  7. Cirqueira D, Almeida F, Cakir G, Jacob A, Lobato F, Bezbradica M, et al. Explainable Sentiment Analysis Application for Social Media Crisis Management in Retail. Proceedings of the 4th International Conference on Computer-Human Interaction Research and Applications. 2020. Available from: https://doi.org/10.5220/0010215303190328
  8. Malhotra D, Saini P, Singh AK. Explaining Deep Learning-Based Classification of Textual Tweets. Data Analytics and Management. Singapore; Singapore. Springer. 2021.
  9. Chakraborty K, Bhatia S, Bhattacharyya S, Platos J, Bag R, Hassanien AE. Sentiment Analysis of COVID-19 tweets by Deep Learning Classifiers—A study to show how popularity is affecting accuracy in social media. Applied Soft Computing. 2020;97:106754. Available from: https://doi.org/10.1016/j.asoc.2020.106754
  10. Gite S, Khatavkar H, Kotecha K, Srivastava S, Maheshwari P, Pandey N. Explainable stock prices prediction from financial news articles using sentiment analysis. Peer Journal of Computer Science. 2021;7:e340. Available from: https://doi.org/10.7717/peerj-cs.340
  11. Wisesty UN, Rismala R, Munggana W, Purwarianti A. Comparative Study of Covid-19 Tweets Sentiment Classification Methods. 2021 9th International Conference on Information and Communication Technology. 2021;2021:3–5.
  12. Reshi AA, Rustam F, Aljedaani W, Shafi S, Alhossan A, Alrabiah Z, et al. COVID-19 Vaccination-Related Sentiments Analysis: A Case Study Using Worldwide Twitter Dataset. Healthcare. 2022;10(3):411. Available from: https://doi.org/10.3390/healthcare10030411
  13. Lamsal R. Design and analysis of a large-scale COVID-19 tweets dataset. Applied Intelligence. 2021;51(5):2790–2804. Available from: https://doi.org/10.1007/s10489-020-02029-z
  14. Padurariu C, Breaban ME. Dealing with Data Imbalance in Text Classification. Procedia Computer Science. 2019;159:736–745. Available from: https://doi.org/10.1016/j.procs.2019.09.229
  15. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research. 2002;16:321–357. Available from: https://doi.org/10.1613/jair.953
  16. Jiao Q, Zhang S. A Brief Survey of Word Embedding and Its Recent Development. 2021 IEEE 5th Advanced Information Technology Electronic and Automation Control Conference (IAEAC). 2021;2021:12–14. Available from: https://doi.org/10.1109/IAEAC50856.2021.9390956
  17. Pennington J, Socher R, Manning C. Glove: Global Vectors for Word Representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics. 2014.
  18. Arrieta AB, Díaz-Rodríguez N, Ser JD, Bennetot A, Tabik S, Barbado A, et al. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion. 2020;58:82–115. Available from: https://doi.org/10.1016/j.inffus.2019.12.012
  19. Lundberg SM, Lee SI, Guyon I, Luxburg UV, Bengio S, Wallach H, et al. A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems. 2017;30:4765–74.


© 2022 Hamed et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.