Learn about traditional sequential neural network architectures and how transformers revolutionised NLP. — In my two previous articles (here and here), despite quickly introducing word embeddings that are created using neural networks, I mainly focused on traditional machine-learning models that take one-hot encoded vectors as input. However, these one-hot encoded vectors are a very naive method of representing text and linear classifiers cannot…

“Lisa, you should study computer science”, said my mother, an ex-programmer, to me many years ago. “Ew no — I don’t want to become like M.” (M. was the geek in my high school class). And this is how I fell into the trap many girls fall into when deciding…

Fuelled by big data and AI, demand for data analytics and data science skills is growing exponentially, according to job sites. As companies are searching for approaches to harness the power of Big Data, technology professionals who are experts in data analytics and data science are in high demand. …

Disclaimer: This article is the second out of a three-part series that I am writing for shecancode. Compared to my other articles, it goes into more theory and does not contain any code (for those, check out my other articles). In this blog post, I want to give you a…

This is a translation of an article by Benjamin Bidder from SPIEGEL. I am from Belarus and given that the majority of people I meet in the West can’t even find Belarus on the map, or believe it is a region of Russia, I cannot expect people to know anything…

An introduction to machine learning on textual data — This article builds upon my previous two articles where I share some tips on how to get started with data analysis in Python (or R) and explain some basic concepts on text analysis in Python. …

A pragmatic step-by-step tutorial for data analysts who are stuck with Excel for text analysis — So, apparently using MS Excel for text data is a thing, because there are add-ons you can install that create word counts and word clouds and can apparently even perform sentiment analysis. …

A pragmatic approach to learning Python or R for data analysts with no coding background — Often people get frustrated when using a software for data analysis which is not particularly suitable for a given task but nevertheless continue using it because they are familiar with that software. For example, using MS Excel for data which consists of mainly text. Using Python or R would make…