Sentiment analysis and Alteryx #AYXAdvocacyAmplified

-
Sentiment analysis in Alteryx
Alteryx is a great platform to run some analytics, in a graphical and easy-to-explain format. One thing I've been experimenting with lately is natural language processing.

In the above workflow I'm leveraging the built-in #rstats environment to scrape data from a financial analyst's report.

Using Alteryx's built-in data cleansing and reporting tools, I then re-shaped and pivoted the data for further processing.

Sometimes people ask, #rstats (aka the "R programming language") or #Python? The answer is: "Why choose, when you can have both?" In the example above, I'm then processing the data with a Python script which leverages the open source VADER library. Although more appropriate with social media inputs, I'm experimenting with this sentiment analysis library before moving on to other libraries.

I then take the data back out into a scatterplot provided by #rstats



The box plot above is basically saying that overall, this document had a positive sentiment. Lo and behold ... drilling in to the actual paragraphs fed in to the analyser I can see that phrases that included the words "net loss on investments" and "IRR of the Company was a sham" caused the paragraphs to be identified as negative (the < 0 VADER_score and a predicted_sentiment = 1.0).

My analysis still needs some more work, but with the above, I hope that I can demonstrate two of the unique selling propositions with Alteryx: (1) interacting with code that is written in both R and Python in a visual workflow that can be explained to non-technical audience (2) developing workflows in a rapid and iterative method. This trivial example above was pulled together in <15 minutes by building on reusable components.

In the fast-paced world we live in, minimising "time taken to solve" a particular analytical challenge is key, especially when we need to move on to the next challenge!

I'm now going to explore other NLP technologies and sentiment analysis tools other than VADER! Good luck with yours, and feel free to reach out to me at @izamryan!

Comments

Post a Comment

Popular posts from this blog

Define: artificial intelligence

-
Image
Alas, that term "artificial intelligence" gets bandied about a lot in business and non-business circles. So what exactly do we mean by "AI"? And to make things more complicated - what do people mean when they say "machine learning"?  A no-nonsense guide to AI Quite simply: AI is a general label for all of the computerised systems that perform tasks in an approximation of human intelligence. You know that magic rice cooker? It might have a heuristic (fancy way of saying "a rule of thumb") on "how long to keep the water on the boil". It's not quite as sexy as "machine learning", but this approximation of how grandma used to cook the rice is as simple as saying, "use two cups of water for every one cup of rice".  The next level down is "machine learning", and I actually prefer to split this down into supervised learning, unsupervised learning and reinforcement learning. These are statistical methods where ...
Read more

Inductive vs Deductive approaches #statisticalThinking @muralCo #imagine2020

-
In this past month I've had a bunch of interesting interactions with strategists, consultants and statisticians. Quite tongue-in-cheek, but I thought I'd share this insight on #inductive vs. #deductive approaches to statistics : Settling the debate between induction vs deduction once and for all. #StatsTikTok pic.twitter.com/U7xSuBFrTL — Daniël Lakens (@lakens) May 17, 2020 Inductive vs Deductive But more seriously, what does it mean to be inductive or deductive? I'm sharing my notes here, because it was a chance for me to experiment with the Mural service, having attended some of Mural #Imagine2020 . I'm planning to use #Mural on my next data science project and I can quickly see how this can be a great facilitation tool to work with problem owners and business leaders to bring design thinking and a clear analytical thought process to their ill-defined business problems. Figure 1: Inductive thinking Let's have a hypothetical situation of a manufacturer of unique p...
Read more

The importance of being data-driven

-
Competing in today's VUCA world calls for new skills in strategy, finance and analytics I posit to you that: this volatile, uncertain, complex and ambiguous market we find ourselves in calls for both, a new set of skills and a not-so-new set of skills. What do I mean by "not-so-new"? Robust strategic problem-solving skills and the ability to lead diverse teams in managing change in an unpredictable environment. Financial nous and being able to read a report and being able to articulate managerial decisions in financial terms: efficiency, effectiveness ... position (sufficiency) and performance (sometimes, the lack of it!). These core skills of strategy and finance are well understood by our business and leadership community ... But at the same time, the 21st century has seen an exponential increase in the volumes of data generated and its availability. We've seen this growth in the ability of systems to process that information, but at the same time, there ...
Read more