# Arabic Sentiment Analysis with Noisy Deep Explainable Model

arXiv: https://arxiv.org/abs/2309.13731 · HTML: https://mlsanity.com/paper/2309.13731/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 51 references that are in the map.
- First posted on arXiv 24 Sep 2023.

## Builds on (most cited first, 12 of 12)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [Adding Gradient Noise Improves Learning for Very Deep Networks](https://mlsanity.com/paper/1511.06807/) (2015)
- [KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media](https://mlsanity.com/paper/2007.13184/) (2020)
- [Adversarial Noise Layer: Regularize Neural Network By Adding Noise](https://mlsanity.com/paper/1805.08000/) (2018)
- [LABR: A Large Scale Arabic Sentiment Analysis Benchmark](https://mlsanity.com/paper/1411.6718/) (2014)
- [ArSentD-LEV: A Multi-Topic Corpus for Target-based Sentiment Analysis in Arabic Levantine Tweets](https://mlsanity.com/paper/1906.01830/) (2019)
- [A review of sentiment analysis research in Arabic language](https://mlsanity.com/paper/2005.12240/) (2020)
- [AraBERT and Farasa Segmentation Based Approach For Sarcasm and Sentiment Detection in Arabic Tweets](https://mlsanity.com/paper/2103.01679/) (2021)
- [Actionable and Political Text Classification using Word Embeddings and LSTM](https://mlsanity.com/paper/1607.02501/) (2016)
- [Combining Context-Free and Contextualized Representations for Arabic Sarcasm Detection and Sentiment Identification](https://mlsanity.com/paper/2103.05683/) (2021)

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

- [A comprehensive survey of contemporary Arabic sentiment analysis: Methods, Challenges, and Future Directions](https://mlsanity.com/paper/2502.03827/) (2025)
- [Why Current XAI Is Not Enough for Arabic NLP: A Critical Survey of the Explainability Gap](https://mlsanity.com/paper/2608.26144/) (2026)

## Abstract (arXiv)

Sentiment Analysis (SA) is an indispensable task for many real-world applications. Compared to limited resourced languages (i.e., Arabic, Bengali), most of the research on SA are conducted for high resourced languages (i.e., English, Chinese). Moreover, the reasons behind any prediction of the Arabic sentiment analysis methods exploiting advanced artificial intelligence (AI)-based approaches are like black-box - quite difficult to understand. This paper proposes an explainable sentiment classification framework for the Arabic language by introducing a noise layer on Bi-Directional Long Short-Term Memory (BiLSTM) and Convolutional Neural Networks (CNN)-BiLSTM models that overcome over-fitting problem. The proposed framework can explain specific predictions by training a local surrogate explainable model to understand why a particular sentiment (positive or negative) is being predicted. We carried out experiments on public benchmark Arabic SA datasets. The results concluded that adding noise layers improves the performance in sentiment analysis for the Arabic language by reducing overfitting and our method outperformed some known state-of-the-art methods. In addition, the introduced explainability with noise layer could make the model more transparent and accountable and hence help adopting AI-enabled system in practice.