VADER_SENTIMENT

Overview

This function performs sentiment analysis on text using the VADER (Valence Aware Dictionary and sEntiment Reasoner) lexicon, which is specifically attuned to sentiments expressed in social media.

Usage

Analyzes the sentiment of the input text and returns a compound score.

=VADER_SENTIMENT(text)

Arguments:

Returns:

Examples

1. Positive Product Review Analysis

Analyze the sentiment of a positive product review.

=VADER_SENTIMENT("I absolutely love this product! It exceeded all my expectations and I would highly recommend it to anyone.")

Output: 0.9042

The highly positive score (close to +1) indicates very positive sentiment in the review.

2. Negative Customer Feedback Analysis

Analyze the sentiment of negative customer feedback.

=VADER_SENTIMENT("The customer service was terrible. I waited for hours and my issue was never resolved properly.")

Output: -0.8481

The strongly negative score (close to -1) indicates very negative sentiment in the feedback.

3. Neutral Business Statement Analysis

Analyze the sentiment of a neutral business statement.

=VADER_SENTIMENT("Our company will be conducting the annual inventory count on June 15th. All departments will participate as scheduled.")

Output: 0.0

The neutral score (close to 0) indicates the statement is factual without emotional connotation.

4. Mixed Sentiment Analysis

Analyze text with mixed positive and negative elements.

=VADER_SENTIMENT("While the product quality is excellent, the shipping was delayed which was disappointing.")

Output: 0.1901

The slightly positive score indicates that the text contains both positive and negative elements, with the positive aspects slightly outweighing the negative ones.

Source Code

import nltk
from nltk.sentiment import SentimentIntensityAnalyzer
 
# Ensure you have downloaded the necessary NLTK data
nltk.download('vader_lexicon')
 
def vader_sentiment(text):
    """Analyzes sentiment of text using VADER.
    Args:
        text (str): Text to analyze
    Returns:
        float: Compound sentiment score (-1 to 1)
    """
    if not isinstance(text, str):
        return 0.0 # Return neutral for non-string input
    sia = SentimentIntensityAnalyzer()
    sentiment = sia.polarity_scores(text)
    return round(sentiment['compound'], 4) # Round for consistency