Trump: Sentimental Tweetist!

I recently saw this blog post which was shared on linked in by Ahmed Sharif from Convergence Consulting Group.  It is really a great tutorial about how to use Python for sentiment analysis.

I found the topic fascinating but as a “mere mortal” (aka Business User) there was no way I was going to be able to open up Python, Tweepy, or any of the other tools in that tutorial.  It is just not in my DNA.  For a data scientist or a technical person, Python is an extremely powerful tool.  What about for the average business person? Say, in marketing, customer service or even product development… could they access twitter data or other internet data to understand sentiment?

I used this social media analytics solution which aggregates, structures and classifies ALL of the data for me in one location.  The solution then applies a variety of analytical techniques against this now structured information to provide me recommended topics I should explore, share of voice and most importantly SENTIMENT.  Sentiment is how people feel about a given topic.  Whether you are PRO or ANTI Trump, there was a LOT of sentiment out there and each side is fighting for their share of voice.

So what did I find?   What is being said and how do people feel about it? I found a mix of sentiment.  Screen Shot 2017-10-25 at 3.54.35 PMSome people were extremely positive in their topics about the president while other were extremely negative.  There was even some ambivalence as indicated by the grey dot.  If I were doing some damage control or political campaigns, I could use this information to identify those topics people are most interested in without needing to manually group aggregate and classify the information myself.  This saves a ton of time and highlights topics I had not necessarily even thought about.

Who was talking about the President and more specifically the handle @realdonaldtrump?  I see a mix of genders, split right down the middle.  Screen Shot 2017-10-25 at 4.20.24 PM

Now, this gender data is self reported in Twitter and other internet sources..  I can only see what people are willing to share on their profile which about 60% or so chose to do.  If I were running a marketing campaign this would help me identify who to target.  I can further refine this information to determine the topics each gender is interested in.

This is just a bit of a taste of what you can do with social media analytics.  And here is the key:  I was able to do this analysis in 5 minutes without writing a single line of code!

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s