😊 BERT-Emotions Emotion Classifier

🎯 Overview

A lightweight, Emotions-powered emotion classification model fine-tuned for short text sentiment/emotion detection using BERT architecture.

Each input text is tagged with one of 13 rich emotional categories, mapped to expressive emotions 🎭. This model is ideal for chatbot understanding, social media sentiment, and mental health analysis based on short messages.

---

💫 Supported Emotions

Emotion	Emoji
Sadness	😢
Anger	😠
Love	❤️
Surprise	😲
Fear	😱
Happiness	😄
Neutral	😐
Disgust	🤢
Shame	🙈
Guilt	😔
Confusion	😕
Desire	🔥
Sarcasm	😏

---

🚀 Use Cases

• 🧠 Chatbot emotion understanding
• 🎭 Social media sentiment tagging
• 🔍 Mental health context detection
• 💬 Smart replies and reactions
• 📊 Emotional tone analysis in text

---

🛠️ Usage

🔍 Basic Inference Example

A minimal example to predict the emotion behind a simple sentence.

from transformers import pipeline

# Load the fine-tuned BERT Mini sentiment analysis model
sentiment_analysis = pipeline("text-classification", model="boltuix/bert-emotions")

# Analyze sentiment
result = sentiment_analysis("i love you")
print(result)

✅ Output

[{'label': 'love', 'score': 0.8442274928092957}]

This means the model predicts the emotion as Love ❤️ with 84.42% confidence.

---

🔍 Extended Example with Emoji Mapping

An enhanced version to map model output to human-readable emotion with emojis.

from transformers import pipeline

# Load the fine-tuned BERT-Emotions model
sentiment_analysis = pipeline("text-classification", model="boltuix/bert-emotion")

# Define label-to-emoji mapping
label_to_emoji = {
    "Sadness": "😢",
    "Anger": "😠",
    "Love": "❤️",
    "Surprise": "😲",
    "Fear": "😱",
    "Happiness": "😄",
    "Neutral": "😐",
    "Disgust": "🤢",
    "Shame": "🙈",
    "Guilt": "😔",
    "Confusion": "😕",
    "Desire": "🔥",
    "Sarcasm": "😏"
}

# Input text
text = "i love you"

# Analyze emotion
result = sentiment_analysis(text)[0]
label = result["label"].capitalize()
emoji = label_to_emoji.get(label, "❓")

# Output
print(f"Text: {text}")
print(f"Predicted Emotion: {label} {emoji}")
print(f"Confidence: {result['score']:.2%}")

✅ Output

Text: i love you
Predicted Emotion: Love ❤️
Confidence: 84.42%

This version enhances readability and gives an expressive emoji for the predicted emotion.

---

⚙️ Model Details

• 🧠 Base: BERT (uncased)
• 🔢 Classes: 13 emotions
• 🗣️ Language: English
• 🏷️ Output: Single-label classification
• 🧪 Evaluation: Accuracy, F1, Precision, Recall

---

📦 Model Card Info

• Name: BERT-Emotions
• Author: Boltuix
• License: Apache-2.0
• Version: v1.0
• Tags: emotion, emoji, emotions, text-classification
• Status: Public + Inference-ready

---

✍️ Contact

• 📬 [email protected]