Augment-sentiment-finnlp-th: An Open-source Thai Sentiment Analysis Model - Free Deployment with an Evaluation Accuracy of 74.15%

Home

Augment Sentiment Finnlp Th

Developed by nlp-chula

Thai sentiment analysis model fine-tuned from WangchanBERTa, achieving 74.15% accuracy on the evaluation set

Large Language Model

Transformers

#Thai sentiment analysis #Fine-tuned model #High accuracy

Downloads 68

Release Time : 9/19/2023

Model Overview

This model is a Thai text sentiment analysis model fine-tuned from the WangchanBERTa architecture, primarily used for analyzing sentiment tendencies in Thai text

Model Features

Thai sentiment analysis

Sentiment analysis capability specifically optimized for Thai text

Based on WangchanBERTa

Utilizes a pre-trained model optimized for Thai as the foundation

Moderate accuracy

Achieves 74.15% classification accuracy on the evaluation set

Model Capabilities

Thai text classification

Sentiment tendency analysis

Use Cases

Social media analysis

Comment sentiment analysis

Analyze sentiment tendencies in Thai social media comments

Can identify positive, negative and other sentiment tendencies

Market research

Product feedback analysis

Analyze Thai users' sentiment towards products

Helps understand product acceptance in the Thai market

Property	Details
Base Model	airesearch/wangchanberta-base-att-spm-uncased
Tags	generated_from_trainer
Metrics	accuracy

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7909	1.0	1024	0.8396	0.6304
0.6024	2.0	2048	0.6650	0.7267
0.4188	3.0	3072	0.6999	0.7489
0.2708	4.0	4096	0.8684	0.7415

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

Augment Sentiment Finnlp Th

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 augment-sentiment-finnlp-th

🚀 Quick Start

📚 Documentation

Model Information

Training and Evaluation

Training Hyperparameters

Training Results

Framework Versions