# PRFashion24: A Dataset for Sentiment Analysis of Fashion Products Reviews in Persian

arXiv: https://arxiv.org/abs/2405.18060 · HTML: https://mlsanity.com/paper/2405.18060/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 17 references that are in the map.
- First posted on arXiv 28 May 2024.

## Builds on (most cited first, 3 of 3)

- [Sentiment Analysis of Persian-English Code-mixed Texts](https://mlsanity.com/paper/2102.12700/) (2021)
- [Jointly Modeling Aspect and Polarity for Aspect-based Sentiment Analysis in Persian Reviews](https://mlsanity.com/paper/2109.07680/) (2021)
- [Sentiment Analysis of Fashion Related Posts in Social Media](https://mlsanity.com/paper/2111.07815/) (2021)

## Built on by (most cited first, 1 of 1)

- [Exa-PSD: a new Persian sentiment analysis dataset on Twitter](https://mlsanity.com/paper/2602.20892/) (2026)

## Abstract (arXiv)

The PRFashion24 dataset is a comprehensive Persian dataset collected from various online fashion stores, spanning from April 2020 to March 2024. With 767,272 reviews, it is the first dataset in its kind that encompasses diverse categories within the fashion industry in the Persian language. The goal of this study is to harness deep learning techniques, specifically Long Short-Term Memory (LSTM) networks and a combination of Bidirectional LSTM and Convolutional Neural Network (BiLSTM-CNN), to analyze and reveal sentiments towards online fashion shopping. The LSTM model yielded an accuracy of 81.23%, while the BiLSTM-CNN model reached 82.89%. This research aims not only to introduce a diverse dataset in the field of fashion but also to enhance the public's understanding of opinions on online fashion shopping, which predominantly reflect a positive sentiment. Upon publication, both the optimized models and the PRFashion24 dataset will be available on GitHub.