The code below analyzes twitter sentiment: whether it is positive, negative or neutral. However, it is fairly inaccurate for many tweets such as if it includes "someone gave him a middle fingered saulte", I want to train the program to recognize that middle fingered implies disrepect, even though it includes the word salute in the sentence.
Any suggestions would be appreciated.
import re import tweepy from tweepy import OAuthHandler from textblob import TextBlob
class TwitterClient(object):
'''
Generic Twitter Class for sentiment analysis.
'''
def __init__(self):
'''
Class constructor or initialization method.
'''
# keys and tokens from the Twitter Dev Console
consumer_key = 'WHexAxkRn6uEJkzS2CKpeQejI'
consumer_secret = 'fSxjGVM247YS6Y6BpkWXaIfr6ThXdoSUg2y0aR259vNXVPPfob'
access_token = '915324744140025862-jnGvcTPkJHOObkeydiVburK8SdAngEk'
access_token_secret = 'JGgkWI9Lq0rJU1K0C8JLplRnSrEuw8pj3anOlIsn3YdiO'
# attempt authentication
try:
# create OAuthHandler object
self.auth = OAuthHandler(consumer_key, consumer_secret)
# set access token and secret
self.auth.set_access_token(access_token, access_token_secret)
# create tweepy API object to fetch tweets
self.api = tweepy.API(self.auth)
except:
print("Error: Authentication Failed")
def clean_tweet(self, tweet):
'''
Utility function to clean tweet text by removing links, special characters
using simple regex statements.
'''
return ' '.join(re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t])|(\w+:\/\/\S+)", " ", tweet).split())
def get_tweet_sentiment(self, tweet):
'''
Utility function to classify sentiment of passed tweet
using textblob's sentiment method
'''
# create TextBlob object of passed tweet text
analysis = TextBlob(self.clean_tweet(tweet))
# set sentiment
if analysis.sentiment.polarity > 0:
return 'positive'
elif analysis.sentiment.polarity == 0:
return 'neutral'
else:
return 'negative'
def get_tweets(self, query, count = 30):
'''
Main function to fetch tweets and parse them.
'''
# empty list to store parsed tweets
tweets = []
try:
# call twitter api to fetch tweets
fetched_tweets = self.api.search(q = query, count = count)
# parsing tweets one by one
for tweet in fetched_tweets:
# empty dictionary to store required params of a tweet
parsed_tweet = {}
# saving text of tweet
parsed_tweet['text'] = tweet.text
# saving sentiment of tweet
parsed_tweet['sentiment'] = self.get_tweet_sentiment(tweet.text)
# appending parsed tweet to tweets list
if tweet.retweet_count > 0:
# if tweet has retweets, ensure that it is appended only once
if parsed_tweet not in tweets:
tweets.append(parsed_tweet)
else:
tweets.append(parsed_tweet)
# return parsed tweets
return tweets
except tweepy.TweepError as e:
# print error (if any)
print("Error : " + str(e))
def main():
# creating object of TwitterClient Class
api = TwitterClient()
# calling function to get tweets
tweets = api.get_tweets(query = 'Donald Trump', count = 200)
# picking positive tweets from tweets
ptweets = [tweet for tweet in tweets if tweet['sentiment'] == 'positive']
# percentage of positive tweets
print("Positive tweets percentage: {} %".format(100*len(ptweets)/len(tweets)))
# picking negative tweets from tweets
ntweets = [tweet for tweet in tweets if tweet['sentiment'] == 'negative']
# percentage of negative tweets
print("Negative tweets percentage: {} %".format(100*len(ntweets)/len(tweets)))
# percentage of neutral tweets
print("Neutral tweets percentage:{}%".format(100*(len(tweets) - len(ntweets) - len(ptweets))/len(tweets)))
# printing first 5 positive tweets
print("\n\nPositive tweets:")
for tweet in ptweets[:20]:
print(tweet['text'])
# printing first 5 negative tweets
print("\n\nNegative tweets:")
for tweet in ntweets[:20]:
print(tweet['text'])
if __name__ == "__main__":
# calling main function
main()
This algorithm does not follow any classification procedure used in Machine Learning , therefore it has nothing to train . It is an algorithm based on a very rudimentary statistical procedure, and to execute it it is required to have bags of words previously classified by feeling (a bag of positive words and another with negative words).
By following such a rudimentary statistical procedure, classifying words as neutral is extremely complicated. That is why your algorithm does not work well.
Also, enter a rate of retweets greater than 0
if tweet.retweet_count> 0 :
but that doesn't make any sense if there is no measure of the proportion of retweets in a period of time.
So as it is your algorithm is hardly going to work well. I recommend doing more research on employee word bag word ranking and tokenization .
You can check this link for some details: https://www.pluralsight.com/guides/building-a-twitter-sentiment-analysis-in-python
Successes and greetings.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.