You’re cute, you want to use an API and you’re not a developer.
Oh no… said Mr.Koolaid. “You can’t use an API. Unless you’re a developer.”
Sure, you can fire a URL off to an API but in return, are you able to make sense of the XML data or JSON data formats?
I found a user-friendly API that will help you understand more about API’s.
Today, I was building a workflow to use an API.
I’m calling it a “word spider.”
I’m using a user-friendly API called Sentic, in Alteryx Designer.
I use the Download Tool to easily use an API.
If you’re not a developer, API stands for the hard part you don’t touch, the weird programmer thing…
That thing your friend Cody does but you know… he’s really good, and can’t teach you anything important.
Well, paying for Cody is all great and good but eventually, you’re going to want to change the custom coded solution. None of these wizards want to train a muggle.
Eventually, you’re going to want to support it, fix it, updated it, and that’s just to keep it working.
You’re throwing money down the drain.
Starting with an easy API will help you understand API’s
I found an API that allows me to input words in a URL, just one word, or two words, a phrase, and it will output synonyms.
The full set of conceptual features associated with the concept meet friend in English, for example, can be retrieved with the command http://sentic.net/api/en/concept/meet_friend
Click if you want to see the screenshot above. It takes a little time to load. Most API’s are must faster but this particular API is easy to explain!
Sentiment Scoring – The output comes with a few other ways to see if the words are more negative or positive.
Sentiment Scoring used to be an advanced purchase, now I’m building the entire data solution, in a few hours.
If you have words, write words, read words,… You’re impacted by sentiment analysis.
Government agencies, media companies, and just about every company you can think of has paid for some sort of sentiment analysis of their data.
It has been so complex to do sentiment scoring, people have paid millions for years.
I’m now doing it in minutes and it’s my own custom solution.
A gathering of peoples intelligent works.
So, the API takes words or phrases…
It returns similar words. Word, words, phrases… The API is hungry for your URL input.
What we know.
- Synonyms are words…
- It gives us synonyms in response.
- 1 word = 5 responses.
- Our word spider merely needs to eat more words.
- Loop the output into the input.
So, what if I could loop the data spider output into the input? A loop at Hotel Irvine.
Why not send the words back to the API?
It was easy to exponentially grow the API requests. 2 turned into 600+…
A little slow though.
The API connection we just built is not fast.
They offer the data in XML.
XML is a kind of file format, slash programming language, slash advanced if you aren’t a developer or a bit of a technology nerd.
It has code in the file and it’s a data table but not what you’re used to seeing in excel or a CSV.
I will offer the data in a few formats soon and credit the authors.
Because you can score and of the words, you’re using in your emails or text messages before sending…
How cool would that be?
The goal, of course, is to to make sure you don’t sound dumb.
www.Sentic.net/API offers an easy API for everyone.
Essentially the Sentic API lets you send it a URL and it outputs XML code, you can transform the XML code into a relational database table, and output it to a report, dashboard, visualization tool, etc…
What’s also interesting is I’ve been ripping apart sentences with “Regular Expression,” and transposing the words vertically.
Alteryx Designers join speeds are so fast I’m able to do string=string matches, with split-second speeds.
It opens a massive door for deeper insights and less work/cost to get there.
I wonder what people use to build applications with the voice to text capability…
That’s the next step to start another idea.
It would be nice to have mini sentiment scoring capabilities and generate a type of sentiment dashboard for words, emails, or copy on a website.
– Tyler 4/24
Kicking back off, 4/27. I was able to generate the above quote. Before I start explaining everything, let me start with one thing.
Smart people don’t care about data prep.
It’s cool to finally be able to understand Ph.D. presentations. I found some Harvard data, lots of different sentiment related data, one sentiment analysis data set that was generated by hand, and also a data set that I’ve transposed into a bar chart scoring tool to capture the overall style, mood, and feelings being portrayed.
Some of the sources offer different styles of models. Modal is like, am I coming across as absolute and definitive? Or am I coming off as off I’m more moderate and general? One source offers a ‘weak score’ too.
All together I’ve curated my own sentiment analysis analytics application.
I’m taking comments from a meeting and transposing each word down one column. Lowercase to assume the ETL position and boom – off to the join, peel out any similar values.
Now we have several different scoring devices. It works really well.
Yes, now you and I have several different sentiment scoring devices.
Here are my 2 cents about sentiment scoring.
What’s interesting is everyone is recreating the wheel. People are building new sentiment dictionaries every day.
Scanning 5 or 10 years ago offers gigs of sentiment analysis data and very little thought leadership around the topic.
Everyone stores their work, output, etc… on outdated websites, with usually very little insights into what they found, the data is generally extremely dirty and shaped in a way that would make excel flustered with building a data visualization.
My next step is to take emails from sales reps who are winning the most deals and see if we can find any interesting outliers.
Looking for things straying from the pack can be easy if you know how to look.
But it’s a lot easier if you know SQL or have Alteryx.