Sentiment Analysis for Customer Experience With Python and Streamlit

The Vonage Messaging API allows businesses to leverage customer service by collating review feedback from social media platforms such as Facebook. Sentiment analysis mines insights from customers' feedback using natural language processing techniques to determine whether feedback data is positive, negative or neutral. The tutorial covers initializing the Messages API Sandbox on Vonage, collecting data from customers through Facebook, creating a bot to handle feedback from customers, and analyzing customer key pain points with visualization. To create a bot, businesses need a Vonage API account, a business account with each provider, and a Facebook account. The bot stores customer feedback in a database or text file, returns relevant responses to the customer, creates a dashboard through Streamlit to understand sentiments in real-time, measures customer sentiments with a positive, negative, neutral scale, and analyzes customer key pain points with visualization. The tutorial also covers creating a function called `sendMessage` which sends messages to Facebook in response to customers' queries, feedback, or reviews. Additionally, the application listens for incoming messages from the Messages API and stores data in a database file named `messages.db`. To analyze user's feedback, the data is visualized through the python Streamlit framework with libraries such as TextBlob, WordCloud, Matplotlib, and Pandas, which generates a word cloud to visualize the frequency of words provided in the feedback by users. The overall sentiment analysis shows that most of the feedback is not in support of the products and services of the firm.