robust-sentiment-analysis

conglt-mylong/robust-sentiment-analysis

robust-sentiment-analysis is a text classification model from conglt-mylong. Use it when you need a label for a piece of text. The card lists the license as apache-2.0.

Downloads · 30 days

8% of all-time downloads

All-time downloads

Public

Parameters

67M

268 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors268 MB · 100%

At a glance

Task: Text Classification
License: apache-2.0
Model type: distilbert
Access: Public
Created: Sep 3, 2025
Updated: Sep 3, 2025
SHA: 96aa63a6

Try a prompt

Base models

distilbert/distilbert-base-uncased

Model card

From the Hugging Face model README

🚀 (distil)BERT-based Sentiment Classification Model: Unleashing the Power of Synthetic Data

NEWS!

2024/12: We uploaded an even better and more robust sentiment model! The error rate is reduced by 10%, and overall accuracy is improved!

Model Details

Model Name: tabularisai/robust-sentiment-analysis
Base Model: distilbert/distilbert-base-uncased
Task: Text Classification (Sentiment Analysis)
Language: English
Number of Classes: 5 (Very Negative, Negative, Neutral, Positive, Very Positive)
Usage:
- Social media analysis
- Customer feedback analysis
- Product reviews classification
- Brand monitoring
- Market research
- Customer service optimization
- Competitive intelligence

Model Description

This model is a fine-tuned version of distilbert/distilbert-base-uncased for sentiment analysis. Trained only on syntethic data.

Training Data

The model was fine-tuned on synthetic data, which allows for targeted training on a diverse range of sentiment expressions without the limitations often found in real-world datasets.

Training Procedure

The model was fine-tuned for 5 epochs.
Achieved a train_acc_off_by_one (accuracy allowing for predictions off by one class) of approximately 0.95 on the validation dataset.

Intended Use

This model is designed for sentiment analysis tasks, particularly useful for:

Social media monitoring
Customer feedback analysis
Product review sentiment classification
Brand sentiment tracking

How to Use

Here's a quick example of how to use the model:

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load model and tokenizer
model_name = "tabularisai/robust-sentiment-analysis"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Function to predict sentiment
def predict_sentiment(text):
    inputs = tokenizer(text.lower(), return_tensors="pt", truncation=True, padding=True, max_length=512)
    with torch.no_grad():
        outputs = model(**inputs)
    
    probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
    predicted_class = torch.argmax(probabilities, dim=-1).item()
    
    sentiment_map = {0: "Very Negative", 1: "Negative", 2: "Neutral", 3: "Positive", 4: "Very Positive"}
    return sentiment_map[predicted_class]

# Example usage
texts = [
    "I absolutely loved this movie! The acting was superb and the plot was engaging.",
    "The service at this restaurant was terrible. I'll never go back.",
    "The product works as expected. Nothing special, but it gets the job done.",
    "I'm somewhat disappointed with my purchase. It's not as good as I hoped.",
    "This book changed my life! I couldn't put it down and learned so much."
]

for text in texts:
    sentiment = predict_sentiment(text)
    print(f"Text: {text}")
    print(f"Sentiment: {sentiment}\n")

Model Performance

The model demonstrates strong performance across various sentiment categories. Here are some example predictions:

1. "I absolutely loved this movie! The acting was superb and the plot was engaging."
   Predicted Sentiment: Very Positive

2. "The service at this restaurant was terrible. I'll never go back."
   Predicted Sentiment: Very Negative

3. "The product works as expected. Nothing special, but it gets the job done."
   Predicted Sentiment: Neutral

4. "I'm somewhat disappointed with my purchase. It's not as good as I hoped."
   Predicted Sentiment: Negative

5. "This book changed my life! I couldn't put it down and learned so much."
   Predicted Sentiment: Very Positive

JS example

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Tabularis Sentiment Analysis</title>
</head>
<body>
    <div id="output"></div>

    <script type="module">
        import { AutoTokenizer, AutoModel, env } from 'https://cdn.jsdelivr.net/npm/@xenova/[email protected]';

        env.allowLocalModels = false;
        env.useCDN = true;

        const MODEL_NAME = 'tabularisai/robust-sentiment-analysis';

        function softmax(arr) {
            const max = Math.max(...arr);
            const exp = arr.map(x => Math.exp(x - max));
            const sum = exp.reduce((acc, val) => acc + val);
            return exp.map(x => x / sum);
        }

        async function analyzeSentiment() {
            try {
                const tokenizer = await AutoTokenizer.from_pretrained(MODEL_NAME);
                const model = await AutoModel.from_pretrained(MODEL_NAME);

                const texts = [
                    "I absolutely loved this movie! The acting was superb and the plot was engaging.",
                    "The service at this restaurant was terrible. I'll never go back.",
                    "The product works as expected. Nothing special, but it gets the job done.",
                    "I'm somewhat disappointed with my purchase. It's not as good as I hoped.",
                    "This book changed my life! I couldn't put it down and learned so much."
                ];

                const output = document.getElementById('output');

                for (const text of texts) {
                    const inputs = await tokenizer(text, { return_tensors: 'pt' });
                    const result = await model(inputs);
                    
                    console.log('Model output:', result);

                    if (result.output && result.output.data) {
                        const logitsArray = Array.from(result.output.data);
                        console.log('Logits array:', logitsArray);

                        const probabilities = softmax(logitsArray);
                        const predicted_class = probabilities.indexOf(Math.max(...probabilities));

                        const sentimentMap = {
                            0: "Very Negative",
                            1: "Negative",
                            2: "Neutral",
                            3: "Positive",
                            4: "Very Positive"
                        };

                        const sentiment = sentimentMap[predicted_class];
                        const score = probabilities[predicted_class];

                        output.innerHTML += `Text: "${text}"<br>`;
                        output.innerHTML += `Sentiment: ${sentiment}, Score: ${score.toFixed(4)}<br><br>`;
                    } else {
                        console.error('Unexpected model output structure:', result);
                        output.innerHTML += `Unable to process: "${text}"<br><br>`;
                    }
                }
            } catch (error) {
                console.error('Error:', error);
                document.getElementById('output').innerHTML = 'An error occurred. Please check the console for details.';
            }
        }

        analyzeSentiment();
    </script>
</body>
</html>

Training Procedure

The model was fine-tuned on synthetic data using the distilbert/distilbert-base-uncased architecture. The training process involved:

Dataset: Synthetic data designed to cover a wide range of sentiment expressions
Training framework: PyTorch Lightning
Number of epochs: 5
Performance metric: Achieved train_acc_off_by_one of approximately 0.95 on the validation dataset

Ethical Considerations

While efforts have been made to create a balanced and fair model through the use of synthetic data, users should be aware that the model may still exhibit biases. It's crucial to thoroughly test the model in your specific use case and monitor its performance over time.

Citation

Will be included

Contact

For questions or private and reliable API with out model please contact [email protected]

tabularis.ai

Task: Text Classification
Type: distilbert
License: apache-2.0
Languages: en
Created: Sep 3, 2025
Updated: Sep 3, 2025