# On Sensitivity of Deep Learning Based Text Classification Algorithms to Practical Input Perturbations

arXiv: https://arxiv.org/abs/2201.00318 · HTML: https://mlsanity.com/paper/2201.00318/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 2 Jan 2022.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Text Classification Algorithms: A Survey](https://mlsanity.com/paper/1904.08067/) (2019)
- [Challenges in Deploying Machine Learning: a Survey of Case Studies](https://mlsanity.com/paper/2011.09926/) (2020)
- [Robustness Gym: Unifying the NLP Evaluation Landscape](https://mlsanity.com/paper/2101.04840/) (2021)
- [A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1510.03820/) (2015)
- [Evaluating the Robustness of Neural Language Models to Input Perturbations](https://mlsanity.com/paper/2108.12237/) (2021)
- [A C-LSTM Neural Network for Text Classification](https://mlsanity.com/paper/1511.08630/) (2015)
- [Robustness Testing of Language Understanding in Task-Oriented Dialog](https://mlsanity.com/paper/2012.15262/) (2020)
- [L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset](https://mlsanity.com/paper/2103.11408/) (2021)
- [Deep Learning for Hindi Text Classification: A Comparison](https://mlsanity.com/paper/2001.10340/) (2020)
- [Experimental Evaluation of Deep Learning models for Marathi Text Classification](https://mlsanity.com/paper/2101.04899/) (2021)
- [Evaluating Deep Learning Approaches for Covid19 Fake News Detection](https://mlsanity.com/paper/2101.04012/) (2021)
- [Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training](https://mlsanity.com/paper/2009.12064/) (2020)
- [Comparative Study of Long Document Classification](https://mlsanity.com/paper/2111.00702/) (2021)
- [Assessing Robustness of Text Classification through Maximal Safe Radius Computation](https://mlsanity.com/paper/2010.02004/) (2020)
- [Training and Prediction Data Discrepancies: Challenges of Text Classification with Noisy, Historical Data](https://mlsanity.com/paper/1809.04019/) (2018)
- [ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models](https://mlsanity.com/paper/2102.00238/) (2021)
- [Model Robustness with Text Classification: Semantic-preserving adversarial attacks](https://mlsanity.com/paper/2008.05536/) (2020)

## Built on by (most cited first, 2 of 2)

- [Stance Detection: A Practical Guide to Classifying Political Beliefs in Text](https://mlsanity.com/paper/2305.01723/) (2023)
- [Curating Stopwords in Marathi: A TF-IDF Approach for Improved Text Analysis and Information Retrieval](https://mlsanity.com/paper/2406.11029/) (2024)

## Abstract (arXiv)

Text classification is a fundamental Natural Language Processing task that has a wide variety of applications, where deep learning approaches have produced state-of-the-art results. While these models have been heavily criticized for their black-box nature, their robustness to slight perturbations in input text has been a matter of concern. In this work, we carry out a data-focused study evaluating the impact of systematic practical perturbations on the performance of the deep learning based text classification models like CNN, LSTM, and BERT-based algorithms. The perturbations are induced by the addition and removal of unwanted tokens like punctuation and stop-words that are minimally associated with the final performance of the model. We show that these deep learning approaches including BERT are sensitive to such legitimate input perturbations on four standard benchmark datasets SST2, TREC-6, BBC News, and tweet_eval. We observe that BERT is more susceptible to the removal of tokens as compared to the addition of tokens. Moreover, LSTM is slightly more sensitive to input perturbations as compared to CNN based model. The work also serves as a practical guide to assessing the impact of discrepancies in train-test conditions on the final performance of models.