# Political Sentiment Analysis of Persian Tweets Using CNN-LSTM Model

arXiv: https://arxiv.org/abs/2307.07740 · HTML: https://mlsanity.com/paper/2307.07740/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 67 references that are in the map.
- First posted on arXiv 15 Jul 2023.

## Builds on (most cited first, 6 of 6)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects](https://mlsanity.com/paper/2004.02806/) (2020)
- [ParsBERT: Transformer-based Model for Persian Language Understanding](https://mlsanity.com/paper/2005.12515/) (2020)
- [Sentiment Analysis on Speaker Specific Speech Data](https://mlsanity.com/paper/1802.06209/) (2018)
- [Sentiment Analysis for Education with R: packages, methods and practical applications](https://mlsanity.com/paper/2005.12840/) (2020)
- [TweeNLP: A Twitter Exploration Portal for Natural Language Processing](https://mlsanity.com/paper/2106.10512/) (2021)

## Abstract (arXiv)

Sentiment analysis is the process of identifying and categorizing people's emotions or opinions regarding various topics. The analysis of Twitter sentiment has become an increasingly popular topic in recent years. In this paper, we present several machine learning and a deep learning model to analysis sentiment of Persian political tweets. Our analysis was conducted using Bag of Words and ParsBERT for word representation. We applied Gaussian Naive Bayes, Gradient Boosting, Logistic Regression, Decision Trees, Random Forests, as well as a combination of CNN and LSTM to classify the polarities of tweets. The results of this study indicate that deep learning with ParsBERT embedding performs better than machine learning. The CNN-LSTM model had the highest classification accuracy with 89 percent on the first dataset and 71 percent on the second dataset. Due to the complexity of Persian, it was a difficult task to achieve this level of efficiency. The main objective of our research was to reduce the training time while maintaining the model's performance. As a result, several adjustments were made to the model architecture and parameters. In addition to achieving the objective, the performance was slightly improved as well.