indobert

The first-ever vast natural language processing benchmark for Indonesian Language. We provide multiple downstream tasks, pre-trained IndoBERT models, and a starter code! (AACL-IJCNLP 2020)

IndoLEM is a comprehensive Indonesian NLU benchmark, comprising three pillars NLP task: morpho-syntax, semantic, and discourse. Presented in COLING 2020.

The first large-scale summarization corpus for the Indonesian language. AACL 2020.

indoBERT Base-Uncased fine-tuned on Translated Squad v2.0

DAC Unpad 2021 Final, predicting government sentiment analytics topic of PPKM COVID-19 Policy

A fine tuned IndoBERT model for University Sentiment On Social Media

Model analisis sentimen berbasis IndoBERT yang dapat memprediksi 6 jenis emosi dalam suatu kalimat, yaitu marah, sedih, senang, cinta, takut, dan jijik.

Just an example of how to use indobenchmark transformer (IndoBERT, IndoGPT, IndoBertTweet) in hugging face.

Sistem klasifikasi teks berbahasa Indonesia untuk mendeteksi bahasa kasar menggunakan IndoBERT dan menyediakan layanan inferensi melalui REST API berbasis FastAPI.

Web-based hoax detection using IndoBert Fine-tuned model

A simple implementation of IndoBERT model REST API for University Sentiment Analysis using FAST API

This repository contains the final project (skripsi) for sentiment classification on Indonesian Twitter data using the hashtag #KaburAjaDulu. It explores the performance comparison between a fine-tuned IndoBERT model and traditional machine learning models (such as SVM with IndoBERT embeddings). Built with 🤗 Hugging Face Transformers.

NusaBERT: Teaching IndoBERT to be multilingual and multicultural!

Model analisis sentimen berbasis IndoBERT yang dapat memprediksi sentimen dalam teks berbahasa Jawa Ngoko Lugu

Sentiment analysis of GoPay Indonesian tweets using IndoBERT fine-tuning, LLM-assisted labeling (Groq API), and paraphrase augmentation | Accuracy: 87.6% | Macro F1: ~85%

IndoBERT is used for sentiment analysis of product reviews, helping businesses understand customer opinions. With fine-tuning, the model improves sentiment classification accuracy, enabling more effective marketing strategies such as ad personalisation, quick response, and service improvement based on customer feedback.

The system is designed to compare and utilize multiple state-of-the-art multilingual language models to produce more accurate and context-aware translations between Indonesian and Manado language.

🥈🏆 SEPAKAT - Modul Integrasi is a winning project in Regsosek Hackathon 2022 organized by The Ministry of National Development Planning/Bappenas Indonesia. This module provides a single individual identification model by integrating Regsosek data as basic information which is then linked with related data using the idea of entity resolution.

dataset came from scraping in play store livin by mandiri app

Indonesian financial sentiment dashboard built with Python. Features live IDX market data via yfinance, multi-ticker comparison, and dual-engine sentiment analysis (Lexicon & IndoBERT). Open-source, no API keys required.