Sanjeev2501/nyxar-logistic-sentiment

NYXAR Logistic Sentiment Model

Model Description

A sentiment classification model developed for the NYXAR AI Intelligence & Observability Platform.

The model predicts sentiment across three classes:

• —Positive
• —Neutral
• —Negative

Framework:

• —Scikit-Learn
• —TF-IDF Vectorization
• —Logistic Regression

Language:

• —English

License:

• —MIT

Training Data

Dataset:

• —SetFit/amazonreviewsmulti_en

The dataset contains English Amazon product reviews used for sentiment classification.

Intended Use

This model is designed for:

• —Customer feedback analysis
• —Product review monitoring
• —Support ticket intelligence
• —Sentiment trend analysis

Limitations

The model may struggle with:

• —Sarcasm
• —Irony
• —Domain-specific terminology
• —Very long texts

Predictions should be used as supporting signals rather than business-critical decisions.

Performance

Metrics obtained during evaluation:

• —Accuracy: 69.28%
• —Precision: 65.75%
• —Recall: 69.28%
• —F1 Score: 65.89%

Usage

import joblib

model = joblib.load("logistic_model_v1.pkl")
vectorizer = joblib.load("tfidf_vectorizer_v1.pkl")

text = ["The product exceeded expectations."]
X = vectorizer.transform(text)

prediction = model.predict(X)