Python Program to Extract the Meaning of a Paragraph Using NLP

---

This program utilizes spaCy and TextBlob to extract the meaning of a paragraph by performing text summarization and keyword extraction.

---

1. Install Required Libraries

Run the following command to install necessary libraries if not installed:

pip install spacy textblob nltk
python -m spacy download en_core_web_sm

---

2. Python Program

import spacy
from textblob import TextBlob
import nltk
from collections import Counter
from nltk.corpus import stopwords
import string

# Download stopwords
nltk.download('stopwords')

# Load spaCy English model
nlp = spacy.load("en_core_web_sm")

def extract_meaning(paragraph):
    """
    Function to extract the meaning of a paragraph using NLP techniques
    - Summarization using TextBlob
    - Keyword extraction using spaCy and NLTK
    """
    # Step 1: Text Summarization
    blob = TextBlob(paragraph)
    sentences = blob.sentences
    summary = " ".join(str(sentence) for sentence in sentences[:2])  # Extract first 2 sentences as summary

    # Step 2: Keyword Extraction
    doc = nlp(paragraph)
    words = [token.text.lower() for token in doc if token.is_alpha]  # Extract words, ignore punctuation
    stop_words = set(stopwords.words('english'))
    keywords = [word for word in words if word not in stop_words]  # Remove stopwords
    most_common_keywords = [word for word, freq in Counter(keywords).most_common(5)]  # Top 5 keywords

    # Step 3: Extract Sentiment
    sentiment = blob.sentiment.polarity
    if sentiment > 0:
        sentiment_analysis = "Positive"
    elif sentiment < 0:
        sentiment_analysis = "Negative"
    else:
        sentiment_analysis = "Neutral"

    # Print results
    print("\n--- Extracted Meaning ---")
    print(f"Summary: {summary}")
    print(f"Top Keywords: {', '.join(most_common_keywords)}")
    print(f"Sentiment: {sentiment_analysis}")

# Example Usage
if __name__ == "__main__":
    paragraph = input("Enter a paragraph: ")
    extract_meaning(paragraph)

---

3. Explanation of the Code

• Text Summarization: Extracts the first two sentences from the paragraph as a summary.
• Keyword Extraction:
  • Uses spaCy to tokenize words.
  • Removes stopwords using NLTK.
  • Finds the top 5 most common keywords.
• Sentiment Analysis:
  • Uses TextBlob to determine sentiment polarity.
  • Classifies sentiment as positive, negative, or neutral.

---

4. Example Output

Input:

Enter a paragraph: Artificial Intelligence is transforming industries. It enables automation, improves efficiency, and enhances decision-making. AI-driven systems can analyze vast amounts of data quickly. However, ethical concerns regarding AI remain a challenge.

Output:

--- Extracted Meaning ---
Summary: Artificial Intelligence is transforming industries. It enables automation, improves efficiency, and enhances decision-making.
Top Keywords: artificial, intelligence, transforming, automation, efficiency
Sentiment: Positive

---

5. Where to Use This Program?

• Summarizing long documents for quick insights.
• Keyword extraction for SEO and content optimization.
• Sentiment analysis for understanding opinions in customer reviews or social media posts.
• Chatbots and AI Assistants to comprehend text input.

Would you like any enhancements, such as topic classification or concept extraction? 😊