Hooked on a Feeling: Using Sentiment Analysis on My Text Messages
I conducted an analysis on my text messages. I wondered what I could learn by leveraging artificial intelligence (AI) algorithms on my text messages. I was aware of sentiment analysis to look at text and try to make sense of the intent or emotion. Was it a positive or negative statement?
Would it really work? Do I send good vibes to others, or am I a negative Nelly? Who is the most negative person that texts me? Is my wife always so positive?
Introduction to Sentiment Analysis
Humans can interpret the meaning behind what someone else is saying. Is this person expressing anger? Are they sad?
As digital communication has increased, engineers have tried to teach computers to do the same. Business leaders have explored this technology to mine what people are saying about them online. Are they delighted? Or disappointed? Some common uses of sentiment analysis for business include:
customer service and customer satisfaction
social media analysis
reviews of company products
marketing performance evaluation
Here are some examples I pulled from my dataset of texts, classified as positive, neutral, or negative.
Sentiment Category Examples
Tapping Into a Cloud Service by Microsoft To Assign Sentiment to Text Messages
I decided to leverage Microsoft’s cloud service for my text message analysis. It was simple to get started with a few clicks in the Azure platform. The rest was more challenging and involved writing software to call the service and capture the results. The nerds in your company or a consultant can handle it, as it is standard API familiar to developers. The key takeaway is a technical resource can access the service within minutes and begin getting results. There are many other providers of sentiment analysis, such as Google and Amazon.
I Receive More Negative Texts Than I Send
See—I am a positive person! The proof is below. I send more positive messages than negative.
Sentiment Analysis Summary - Sent Vs. Received
My Friends Are a Mixed Bag, but Family is More Neutral
I guess there aren’t a lot of bland conversations between my friends. They are either positive or negative, not nearly as many gray, based on the data visualization below. On the flip side, my interactions with my immediate family are much more neutral (75% of sent and 71% of received). This makes sense, as there are a lot more transactional conversations with family, like On my way, Leaving, and Yes, for example.
Sentiment By Contact Group
COVID-19 Brings Out Negativity
An interesting trend I found was a significant increase in negative sentiment following COVID-19 discussions (March 2020 and later), increasing from 13% to 19% of messages received.
Sent Vs. Received Text Sentiment Before vs. After COVID-19
You can clearly see the spike by laying out the results each month as seen below. In August 2019, I spread the most cheer!
Sent Messages' Sentiments by Month
Three-Way Tie for Most Negative Texts Received
It didn’t surprise me too much to see my father-in-law and friends at the top of the negative texts I received. But the kids’ school? I dug a little deeper. It was likely keying off words like cancel and delay, as most of the texts from the school were about school closings and delays.
Sentiment by Contact Type
Extended Family Tops in Positive Message Percentage
Many times, I only hear from my extended family on events like birthdays, anniversaries, etc. So it makes sense that when they do reach out, their texts carry a positive message to me.
Most Positive Response Percentages
Spouse Head-To-Head: She Spreads Slightly More Cheer
The messages between my wife and I were pretty well matched—and most were neutral sentiment. She has a slight edge in messages sent with positive sentiment.
Spouse Sentiment Head-To-Head
Don’t Expect Perfection
It can be hard enough for a human to detect someone’s intentions. So no wonder the machine is going to get it wrong at times. Each sentiment comes with a score for how confident it is in the sentiment it determined. The lower the score, the more questionable the results.
I had to make some adjustments based on the output. The key is to review the results and adjust your output accordingly. The service returns a score for positive, neutral, and negative sentiment. This allows the user to adjust and possibly add cut-off scores or other logic to handle mixed sentiment, like the example shown below. This article gives good tips on the limitations. As always, the services will continue to improve with added investments from cloud providers.
Example of Mixed Sentiment
Should You Get Sentimental?
Sentiment analysis is a powerful technology that can be a game changer for getting closer to your customers and being in tune with what others are saying about you. You can now measure this critical component (that was previously very subjective) with hard numbers. With cloud-based providers (Azure, Google, AWS), your developers can append this data to your company data at minimal cost. I would recommend running a small sample of your data points through before investing in software development to run a large set of data through. Kick the tires and see if it adds value to your business.
If you are looking to track marketing sentiment and more common use cases, there are a host of vendors that already offer this service, including Salesforce. Explore these first to tap into your social media channels without building something custom.
Are you tired of losing valuable time sifting through mountains of data or trying to make sense of your number? Are time-consuming tasks eating into your ability to grow and nurture your company? Are you losing clients because you’re behind the eight ball when it comes to delivering information? We hear you. It doesn’t have to be that way. We’ll help you navigate your toughest data challenges like a pro with user-friendly data visualizations.
Perhaps you’re looking to save time on mundane tasks so you can concentrate on more important aspects of your business. Or maybe you’re just trying to save money. (We find that most of the time, those two go hand in hand.) Or perhaps you’re striving to become more efficient or make more confident business decisions.
Whatever the case, we can leverage software, programs, and platforms such as Tableau, Power BI, and Microsoft SQL Server Reporting Services (SSRS) to bring you a customized solution that most accurately solves your biggest challenges. We’ll get you set up to access your most important data with the click of a button. Contact us today to schedule a consultation.