Using python, beautiful soup and topic modeling to understand the main themes underlying customer reviews

Photo by Christina @ wocintechchat.com on Unsplash

A key skill required in data science jobs is the ability connect data insights to business outcomes. For DTC brands, one of the biggest opportunities to do this is through customer reviews.

As an interviewee, you don’t have access to Google analytics or internal data storage systems, but you can find out what customers think about brands from their online reviews. And let’s face it, what better way to highlight your skills to a company than to come prepared to an interview with insights on their own customer reviews?

For this specific analysis, we are going to be using the…


Using Python, API’s and NLP keyword analysis to understand skills listed in data science job descriptions

whiteboard with circle and 3 arrows of various skills pointing at the data science circle
whiteboard with circle and 3 arrows of various skills pointing at the data science circle
Image by author

We have all heard that data is the new oil. But, with so many definitions of what a data scientist is, how can you prepare yourself for a career in data science?

One approach is to understand the skills needed from data science job descriptions. That’s exactly what I did. Using the Google jobs API available through SerpAPI, I pulled the job descriptions of over 100 data science roles. Then, I used a combination of Spacy, NLTK and Gensim to clean the data and extract keywords to identify the top hard and soft skills listed in job description.

Getting job…


\

Tips for those of us that aren’t Adobe masterminds

Person looking at computer with dashboard
Person looking at computer with dashboard
Photo by Mark Cruz on Unsplash

Full disclosure: I’m a huge Webflow fan. Huge. When I started using Webflow last year to design sites, I was like

“This is the best, I feel like I’m coding!”

The best bit, you get to download the code! Yes, thanks to Webflow, I actually learnt front-end code, and now, if I want to make a web application in Flask with a pretty front-end, I just whip something up in Webflow, download the code, add to my project and Voila!


And why that should change

Photo by Volodymyr Hryshchenko on Unsplash

I’m sure everyone here has read the Lean Startup. 1 of the signature mantras reads:

“Talk to your customers”

In fact, almost every product/entrepreneurial book you will ever read will insist that talking to customers is at least half the company, if you don’t talk to your customers you won’t build a product customers want.

This would imply that user research is critical to product development right?

If that’s the case, why is user research not even featured in 1 of the top 4 backgrounds of product managers:


Applying behavioral science to fintech

Photo by Rashmi Shukla on Unsplash

I love companies, and I love problems. With those 2 things in mind, what better way to spend my time then trying to figure out the problems of a company and how I would solve them?

That’s exactly what this article is about. To exercise my product management chops I like to analyze companies I’m interested in and come up with product strategies. Bonus is sharing with the company itself and seeing whether or not:

  • a) I got it “right” (aka they are thinking about the same things) or
  • b) whether I did something different, they didn’t think of (wohoo…


How to build products that matter quickly and cheaply

“I need a dev team”

“I need to build an entire app in react in 1 month to test my product”

Photo by Tim Gouw on Unsplash

These are common quotes I hear from 1st time entrepreneurs. I felt the same. The first product I built I insisted on learning how to code, spending hours designing a loader in javascript (I am still immensely proud of the result, visible here) to make sure that nobody could fault me for not being an engineer. But whilst I’m proud of my loader, was that really the best use of my time? …


And how you can stop that happening

Shows a tablet with a screen showing a LinkedIn Analytics dashboard
Shows a tablet with a screen showing a LinkedIn Analytics dashboard
Photo by inlytics | LinkedIn Analytics Tool on Unsplash

If I asked you what a click-through-rate (CTR) for a LinkedIn sponsored message means, what would you say? If it’s “number of clicks to your destination, duh”, then you, like me have been misled by LinkedIn campaign manager.

So, how can you find your real CTR and determine if those sponsored messaging ads (and other LinkedIn ads) are worth it?

Understanding the LinkedIn Analytics interface — A confusing sport

LinkedIn is a fairly late bloomer in the ads game. Unlike Facebook or Google, it’s clear from using the LinkedIn ads platform that it’s slightly behind its tech siblings. …


UX is core to understanding whether you have problem solution fit, but asking questions that honestly tests your problem assumptions is difficult.

Our team attended the #Collisionfromhome summit earlier this year. One of the partners, PitchBook shared a report on the state of VC investing including the question below:

Us, not really, with the leading framing of this question, of course most VCs say things are they same. If they say yes, they risk losing out on that one billion-dollar company and their idea.

How about the number of meetings they booked this quarter vs. last quarter?

If we look…


Ask good questions that show you did the research

Photo by Hello I’m Nik 🎞 on Unsplash

Interview questions are my favorite part of the interview process. As an interviewer, they are the 1st chance to see how the candidate thinks about our company. As an interviewee, it’s your chance to show prospective employers why they should hire you.

In spite of every blog telling you to prepare interview questions, few candidates do this well. Missing what I see as a crucial opportunity for you to show your competitive advantage. Interview questions that candidates receive will be the same, but the questions you ask are your own. This…


A golden tip to save you on the worst of interviews

I talked in my last article about how I got my job at Facebook by showing people what I could do. This approach has also influenced our mission at LMNS, the company started this year to apply skill-based hiring to non-technical roles.

But skills-based hiring can do more. It helped me save a bad interview. In this article, I want to focus on some of the feedback I have heard about skill-based hiring, and how my own experience in getting a job invalidates that.

After 1 year in my first role at Facebook I was ready for a change. At…

Christina Stejskalova

My articles vary in topic but focus on how you can build products that create real impact with the power of psychology

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store