# SHAP values for Explaining CNN-based Text Classification Models

arXiv: https://arxiv.org/abs/2008.11825 · HTML: https://mlsanity.com/paper/2008.11825/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2020.

## Built on by (most cited first, 12 of 12)

- [Model Explainability in Deep Learning Based Natural Language Processing](https://mlsanity.com/paper/2106.07410/) (2021)
- [Interpretation of Black Box NLP Models: A Survey](https://mlsanity.com/paper/2203.17081/) (2022)
- [Realised Volatility Forecasting: Machine Learning via Financial Word Embedding](https://mlsanity.com/paper/2108.00480/) (2021)
- [Self-interpretable Convolutional Neural Networks for Text Classification](https://mlsanity.com/paper/2105.08589/) (2021)
- [Utilizing Explainable AI for improving the Performance of Neural Networks](https://mlsanity.com/paper/2210.04686/) (2022)
- [Sentiment Analysis in Finance: From Transformers Back to eXplainable Lexicons (XLex)](https://mlsanity.com/paper/2306.03997/) (2023)
- [Evaluating ChatGPT on Nuclear Domain-Specific Data](https://mlsanity.com/paper/2409.00090/) (2024)
- [Classification of Safety Events at Nuclear Sites using Large Language Models](https://mlsanity.com/paper/2409.00091/) (2024)
- [Transparent AI for Mathematics: Transformer-Based Large Language Models for Mathematical Entity Relationship Extraction with XAI](https://mlsanity.com/paper/2603.06348/) (2026)
- [Should ChatGPT and Bard Share Revenue with Their Data Providers? A New Business Model for the AI Era](https://mlsanity.com/paper/2305.02555/) (2023)
- [Explainable Risk Classification in Financial Reports](https://mlsanity.com/paper/2405.01881/) (2024)
- [Explainable AI: A Combined XAI Framework for Explaining Brain Tumour Detection Models](https://mlsanity.com/paper/2602.05240/) (2026)

## Abstract (arXiv)

Deep neural networks are increasingly used in natural language processing (NLP) models. However, the need to interpret and explain the results from complex algorithms are limiting their widespread adoption in regulated industries such as banking. There has been recent work on interpretability of machine learning algorithms with structured data. But there are only limited techniques for NLP applications where the problem is more challenging due to the size of the vocabulary, high-dimensional nature, and the need to consider textual coherence and language structure. This paper develops a methodology to compute SHAP values for local explainability of CNN-based text classification models. The approach is also extended to compute global scores to assess the importance of features. The results are illustrated on sentiment analysis of Amazon Electronic Review data.