How to Integrate Google Cloud AI with Twitter

Automated Customer Support Using AI and Social Media

• Integrate the Twitter API with Google Cloud AI to automatically respond to customer inquiries and complaints posted on Twitter in real-time.

 

• Utilize Google Cloud Dialogflow to build intelligent chat agents that can understand natural language queries and provide automated responses.

 

• Use Google Cloud Language API to analyze the sentiment of tweets to prioritize responses or escalate to human agents for negative sentiments.

import os
from google.cloud import language_v1
from google.cloud import dialogflow_v2 as dialogflow
import tweepy

def twitter_auth():
    # Twitter API credentials
    consumer_key = 'YOUR_CONSUMER_KEY'
    consumer_secret = 'YOUR_CONSUMER_SECRET'
    access_token = 'YOUR_ACCESS_TOKEN'
    access_token_secret = 'YOUR_ACCESS_TOKEN_SECRET'

    # Authenticate with Twitter
    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
    auth.set_access_token(access_token, access_token_secret)
    return tweepy.API(auth)

def analyze_sentiment(text_content):
    # Initialize the Google Cloud Natural Language API client
    client = language_v1.LanguageServiceClient()

    # Document configuration
    type_ = language_v1.Document.Type.PLAIN_TEXT
    language = "en"
    document = {"content": text_content, "type_": type_, "language": language}

    # Sentiment analysis
    response = client.analyze_sentiment(request={"document": document})
    sentiment = response.document_sentiment
    return sentiment.score

def dialogflow_response(project_id, session_id, text_input):
    # Initializes the Dialogflow client
    session_client = dialogflow.SessionsClient()
    session = session_client.session_path(project_id, session_id)

    # Configuring the text input
    text_input = dialogflow.types.TextInput(text=text_input, language_code="en")
    query_input = dialogflow.types.QueryInput(text=text_input)

    # Get the response from Dialogflow
    response = session_client.detect_intent(request={"session": session, "query_input": query_input})
    return response.query_result.fulfillment_text

def respond_to_tweets():
    # Twitter API instance
    api = twitter_auth()

    # Fetch the latest tweets containing your company's handle
    tweets = api.search(q="@YOUR_COMPANY_HANDLE", count=50, lang="en", tweet_mode="extended")
    project_id = "YOUR_DIALOGFLOW_PROJECT_ID"
    session_id = "session_id"
    
    for tweet in tweets:
        user = tweet.user.screen_name
        tweet_text = tweet.full_text
        sentiment_score = analyze_sentiment(tweet_text)
        
        if sentiment_score < 0:
            # Escalate or prioritize for customer support
            print(f"Escalate to human agent: {tweet_text}")
        else:
            response_text = dialogflow_response(project_id, session_id, tweet_text)
            # Respond using Twitter API
            api.update_status(status=f"@{user} {response_text}", in_reply_to_status_id=tweet.id)

if __name__ == "__main__":
    respond_to_tweets()

Advantages and Outcomes

• Improve customer satisfaction by providing quick and accurate responses to inquiries directly through Twitter.

 

• Streamline workflow by automating common queries and letting human agents focus on more complex issues.

 

• Enhance brand presence on social media by actively interacting and resolving customer issues in real-time, fostering a positive brand image.