bert-fa-base-uncased-sentiment-snappfood Open-source Model - Empowering the Processing of Multiple Persian NLP Tasks

Bert Fa Base Uncased Sentiment Snappfood

Developed by HooshvareLab

A Transformer-based Persian language understanding model, with a reconstructed vocabulary and fine-tuned on new Persian corpora, suitable for various Persian NLP tasks.

Text Classification OtherOpen Source License:Apache-2.0 #Persian Sentiment Analysis #Transformer Architecture #Multi-domain Adaptation

Downloads 22.56k

Release Time : 3/2/2022

Model Overview

ParsBERT v2.0 is a Transformer model optimized for Persian, primarily used for natural language understanding tasks such as sentiment analysis.

Model Features

Optimized Persian Vocabulary

Reconstructed vocabulary to better adapt to Persian language characteristics

Multi-domain Applicability

Fine-tuned on new Persian corpora, enhancing usability across other domains

High-performance Sentiment Analysis

Outstanding performance on multiple Persian sentiment analysis datasets

Model Capabilities

Persian Text Understanding

Sentiment Classification

User Comment Analysis

Use Cases

Sentiment Analysis

SnappFood Comment Analysis

Analyze sentiment tendencies in user comments on the SnappFood platform

F1 score reached 87.98

Digikala Comment Analysis

Analyze sentiment in user comments on the Digikala e-commerce platform

🚀 ParsBERT (v2.0)

A Transformer-based Model for Persian Language Understanding

We reconstructed the vocabulary and fine-tuned ParsBERT v1.1 on new Persian corpora to enable the use of ParsBERT in other scenarios. For the latest information on previous and current models, please follow the ParsBERT repository.

🚀 Quick Start

✨ Features

ParsBERT v2.0 is designed to classify text, like comments, based on emotional bias. It has been tested on three well - known Persian datasets for sentiment analysis.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

You can perform sentiment analysis using ParsBERT through the provided notebooks. For sentiment analysis, you can use the following notebook:

Task	Notebook
Sentiment Analysis

📚 Documentation

Persian Sentiment [Digikala, SnappFood, DeepSentiPers]

The goal is to classify text (e.g., comments) according to their emotional bias. Three well - known datasets were tested: Digikala user comments, SnappFood user comments, and DeepSentiPers in both binary - form and multi - form types.

SnappFood

Snappfood is an online food delivery company. Its user comments dataset contains 70,000 comments with two labels (polarity classification):

Happy
Sad

Label	#
Negative	35000
Positive	35000

Download You can download the dataset from here

Results

The following table summarizes the F1 score obtained by ParsBERT compared to other models and architectures.

Dataset	ParsBERT v2	ParsBERT v1	mBERT	DeepSentiPers
SnappFood User Comments	87.98	88.12*	87.87	-

🔧 Technical Details

No technical details are provided in the original document, so this section is skipped.

📄 License

This project is licensed under the Apache - 2.0 license.

BibTeX entry and citation info

Please cite in publications as the following:

@article{ParsBERT,
    title={ParsBERT: Transformer-based Model for Persian Language Understanding},
    author={Mehrdad Farahani, Mohammad Gharachorloo, Marzieh Farahani, Mohammad Manthouri},
    journal={ArXiv},
    year={2020},
    volume={abs/2005.12515}
}

Questions?

Post a Github issue on the ParsBERT Issues repo.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご