Deep Talk is a great platform to analyze the content on Twitter.
We often need to know what a person or celebrity talks about or what is being said about a company or brand. Twitter is a huge data source, but it is unstructured data, millions of words that would take years to process by hand.
Here is an easy example of how to analyze someone’s tweets; in this case, we will use Barack Obama’s account, @BarackObama.
- We need a database with Barack Obama’s tweets; for this, there are several services. One that we like is PhantomBuster.com. There you must create an account and use one of the “Phantoms,” in this case, use “Twitter export tweets” and follow these four steps
1.- Connect to Twitter using a PhantomBuster extension
2.- Specify the user you want to extract tweets from
3.- Configure the Phantom
4.- Download tweets to a .CSV file
Once you have exported the tweets of a specific account to a .CSV file, create an account in Deep Talk. You can log in with your GMAIL account or register your account.
Upload the .CSV file and choose the Deep Learning model option “General Text Data.” You will have to follow a series of steps as follows
Specify the columns that have the data you want to analyze. Indicate which column has the tweets and which one has the dates of the tweets. In this case, they are the columns “Text” and “Tweet Date.”
The system will validate the file, and then you will have to start training the deep learning model to process the tweets.
Now you have to wait a few minutes for the system to process the files, and you will be able to see the results of the analysis of Barack Obama’s tweets. Click on the magnifying glass, and you will access the results.
Did you see how easy it is to sort, cluster and process text files into useful data with Deep Talk?