SENTIMENT EVOLUTION CODE FINAL

from pymongo import MongoClient
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
import statistics
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import string
from deep_translator import GoogleTranslator
import re






# Initialize MongoDB client and collection
mongo_uri = "mongodb://localhost:27017/"
database_name = "twitter_database"
collection_name = "tweet_cleaned"
client = MongoClient(mongo_uri, serverSelectionTimeoutMS=5000)
db = client[database_name]
collection = db[collection_name]


# Initialize sentiment analyzer
analyzer = SentimentIntensityAnalyzer()


# Initialize WordNet Lemmatizer
lemmatizer = WordNetLemmatizer()


# Function to clean text by lemmatizing
def clean_text(text):
    # Lemmatize the entire text
    lemmatized_text = lemmatizer.lemmatize(text)
    return lemmatized_text.strip()


# Function to translate text to English
def translate_to_english(text, lang):
    if lang != 'en':
        translated_text = GoogleTranslator(source='auto', target='en').translate(text)
    else:
        translated_text = text
    return translated_text


# Function to analyze sentiment
def analyze_sentiment(text):
    sentiment = analyzer.polarity_scores(text)
    compound_score = sentiment['compound']
    return compound_score


# Initialize counters
positive_count = 0
negative_count = 0
compound_scores = []


# Iterate through tweets in MongoDB collection
cursor = collection.find().limit(100)


for doc in cursor:
    lang = doc.get("json_data.lang")
    tweet_text = doc.get('json_data.text')



    if lang != 'en':
        translated_text = translate_to_english(tweet_text, lang)
    else:
        translated_text = tweet_text
   
    # Clean and lemmatize text
    cleaned_text = clean_text(translated_text)
   
    # Perform sentiment analysis
    sentiment = analyze_sentiment(cleaned_text)
    compound_scores.append(sentiment)
   
    # Update sentiment counts
    if sentiment > 0 :
        positive_count += 1
    else :
        negative_count += 1
    


# Calculate mean compound score
mean_score = statistics.mean(compound_scores)


# Print results
print("Positive:", positive_count)
print("Negative:", negative_count)
print("Mean compound score:", mean_score)


# Close MongoDB client
client.close()