Sentiment analysis for Twitter in Python

By jacksparrow August 30, 2024

Sentiment Analysis for Twitter in Python

Sentiment analysis is the process of computationally determining the emotional tone behind a piece of text. In this article, we will explore how to perform sentiment analysis on Twitter data using Python.

1. Setting up the Environment

1.1 Installing Required Libraries

We’ll need the following libraries:

tweepy: for interacting with the Twitter API
textblob: for sentiment analysis

Install them using pip:

pip install tweepy textblob

1.2 Importing Libraries

Import the necessary libraries into your Python script:

import tweepy
from textblob import TextBlob

2. Connecting to Twitter API

2.1 Obtaining API Credentials

You’ll need to create a Twitter developer account and obtain API keys.

Visit https://developer.twitter.com/en/portal/dashboard to create an account.
Create a new app and note down the API keys (Consumer Key, Consumer Secret, Access Token, Access Token Secret).

2.2 Authenticating with tweepy

Set up your Twitter API credentials and authenticate with tweepy:

consumer_key = 'YOUR_CONSUMER_KEY'
consumer_secret = 'YOUR_CONSUMER_SECRET'
access_token = 'YOUR_ACCESS_TOKEN'
access_token_secret = 'YOUR_ACCESS_TOKEN_SECRET'

auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth)

3. Fetching Tweets

3.1 Searching for Tweets

Use the api.search_tweets method to retrieve tweets based on keywords.

search_query = '#Python'  # Replace with your desired search term
tweets = api.search_tweets(q=search_query, lang='en', count=100)  # Fetch 100 tweets in English

4. Performing Sentiment Analysis

4.1 Analyzing Sentiment with TextBlob

Iterate through the retrieved tweets and use TextBlob to analyze the sentiment of each tweet. TextBlob provides a sentiment attribute which returns a tuple containing the polarity and subjectivity scores. Polarity ranges from -1 (negative) to 1 (positive), while subjectivity ranges from 0 (objective) to 1 (subjective).

for tweet in tweets:
    analysis = TextBlob(tweet.text)
    print(f"Tweet: {tweet.text}")
    print(f"Polarity: {analysis.sentiment.polarity}")
    print(f"Subjectivity: {analysis.sentiment.subjectivity}\n")

4.2 Categorizing Sentiment

You can categorize sentiment based on the polarity score:

for tweet in tweets:
    analysis = TextBlob(tweet.text)
    if analysis.sentiment.polarity >= 0.5:
        sentiment = 'Positive'
    elif analysis.sentiment.polarity <= -0.5:
        sentiment = 'Negative'
    else:
        sentiment = 'Neutral'
    print(f"Tweet: {tweet.text}")
    print(f"Sentiment: {sentiment}\n")

5. Visualizing Results

5.1 Creating a Sentiment Distribution Chart

You can use a library like matplotlib to visualize the distribution of sentiment scores.

import matplotlib.pyplot as plt
sentiments = []
for tweet in tweets:
    analysis = TextBlob(tweet.text)
    sentiments.append(analysis.sentiment.polarity)

plt.hist(sentiments, bins=10)
plt.xlabel('Polarity Score')
plt.ylabel('Frequency')
plt.title('Sentiment Distribution of Tweets')
plt.show()

Conclusion

In this article, we've covered the fundamental steps for performing sentiment analysis on Twitter data using Python. You can adapt this code to analyze different search terms, adjust the number of tweets fetched, and explore more advanced sentiment analysis techniques.

Post Views: 10

Sentiment analysis for Twitter in Python