You can deploy this model and start earning money today!

prakosoee/
indobert-ABSA-FnB

Name: indobert-ABSA-FnB
Rating: 2.5 (7 reviews)

safetensors

bert

indobert

aspect-based-sentiment-analysis

sentiment-analysis

multilabel-classification

text-classification

indobenchmark/indobert-base-p2

finetune

mit

Views

No views yet

ABSA Model - F&B Best (Multilabel)

This directory contains a fine-tuned BERT model for Aspect-Based Sentiment Analysis (ABSA) that simultaneously analyzes all three aspects in the Food and Beverage (F&B) industry using multilabel classification.

Model Details

Model Architecture: BERT for Sequence Classification
Base Model: indobenchmark/indobert-base-p2
Aspects: Food Quality, Service, Price (simultaneous detection)
Language: Indonesian
Task: Multilabel Sentiment Classification

Label Mapping

The model classifies text into three sentiment categories for each aspect:

Label ID	Sentiment	Description
0	Negative	Poor quality, bad service, expensive, or complaints.
1	Neutral	General mentions without specific positive or negative sentiment.
2	Positive	Good quality, excellent service, affordable, or praise.

Multilabel Output: The model can detect multiple aspects in a single text and assign sentiment to each aspect independently.

Evaluation Metrics

Based on the fine-tuning results, the model achieves the following performance:

Overall Performance (Epoch 4)

Validation Loss: 0.9696
Overall Accuracy: 90.55%
Macro F1-Score: 90.25%

F1 Score per Aspect

Aspect	F1-Score
Food Quality	88.43%
Service	87.10%
Price	94.75%

Usage

This model is loaded and used by the ABSA API service. It provides simultaneous sentiment analysis for all three aspects.

python

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_path = "./absa-fnb-model/model_absa_fnb_best"
model = AutoModelForSequenceClassification.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained("indobenchmark/indobert-base-p2")

Multilabel Output Example

The model can detect multiple aspects in a single review:

json

{
    "Food Quality": "Positive",
    "Service": "Positive", 
    "Price": "Negative"
}

Example Input: "Makanannya enak dan pelayanannya ramah, tapi harganya agak mahal."

This demonstrates the model's ability to:

Detect Food Quality aspect with Positive sentiment
Detect Service aspect with Positive sentiment
Detect Price aspect with Negative sentiment
All in a single inference pass

prakosoee/indobert-ABSA-FnB