I

Indonesian Sentiment

Developed by taufiqdp
Fine-tuned from a pre-trained Indonesian BERT model, used for sentiment analysis of Indonesian comments and reviews, and can classify text into three categories: negative, neutral, and positive.
Downloads 1,830
Release Time : 10/25/2023

Model Overview

This model is a fine-tuned version of IndoBERT Base Uncased, specifically designed for the sentiment analysis task of Indonesian text.

Model Features

Dedicated to Indonesian
Based on a pre-trained BERT model for Indonesian, optimized specifically for Indonesian text
Three-category sentiment analysis
Can accurately classify Indonesian comment text into three categories: negative, neutral, or positive
High performance
Achieved an accuracy of 95.69% on the evaluation dataset

Model Capabilities

Indonesian text classification
Sentiment analysis
Comment and review analysis

Use Cases

Customer feedback analysis
Product review analysis
Analyze the sentiment tendency of Indonesian product reviews on e-commerce platforms
Accurately identify users' satisfaction with products
Service evaluation monitoring
Monitor the sentiment tendency of hotel or restaurant service evaluations
Detect service problems in a timely manner and make improvements
Social media monitoring
Brand reputation monitoring
Analyze the sentiment tendency of Indonesian discussions about brands on social media
Understand the public's overall attitude towards the brand
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase