Learn the basics of Natural Language Processing in Python and build your own Deep Learning Sentiment Analysis!
Do You Want to Analyse Product Reviews or Social Media Posts to see whether they are positive or negative?
What you’ll learn
- Students will be able to install Jupyter Notebook and manage Python Modules.
- Definition of Natural Language and its Applications.
- Get to know Basics of Natural Language Processing.
- Learn Basics of Text Processing with NLTK and spaCy.
- Get to know Traditional Feature Engineering Models.
- Implement a working Sentiment Analysis Model.
- Learn to Code all these points in Python.
Course Content
- Introduction to the Course: Jupyter Notebook and Python Modules –> 2 lectures • 7min.
- Natural Language Basics –> 2 lectures • 8min.
- Processing Text –> 9 lectures • 30min.
- Traditional Feature Engineering Models –> 7 lectures • 33min.
- Recap: Machine Learning –> 1 lecture • 5min.
- Text Classification using TensorFlow –> 7 lectures • 26min.
Requirements
- Prior Experience in Python.
- Prior Implementation of Machine Learning Models will be beneficial.
- Should have an Interest in Learning Practical Text Mining and Natural Language Processing (NLP).
Do You Want to Analyse Product Reviews or Social Media Posts to see whether they are positive or negative?
Do you want to be able to make Computers understand Natural Language?
Then this course is just right for you! We will go over the basic, theoretical foundations of Natural Language Processing (NLP) and directly apply them in Python.
It becomes ever more important for companies and organizations to keep track of large amounts of social media posts concerning their brand or product reviews. In NLP there is a whole field called sentiment analysis, that tries to automate this process. In the end, a Deep Learning model can then process a text and predict whether it’s a positive or negative review. If you are curious about how to build such a model, then this course is just right for you!
Get to know the Basics of NLP & Text Mining and learn how to implement it in Python:
My course will help you implement the learned methods directly in Python modules like spaCy or NLTK. Besides learning the ground rules of NLP and common methods, you will even deal with so-called Transformer models, which are state-of-the-art in Natural Language Processing. In the end, you will combine your gained knowledge to build up a functioning Deep Learning Model that can take text as input and predict a sentiment. With this powerful course, you’ll know it all: applying different steps of text preprocessing, combining it in datasets, and building a Deep Learning Model in TensorFlow.
Learn from an experienced Machine Learning Engineer and University Teacher:
My name is Niklas Lang and I am a Machine Learning Engineer, currently working for a German IT System House. I have experience in working with kinds of textual data arising from our e-commerce website, product descriptions, or online reviews which we turn into powerful and working Machine Learning models. Besides that, I already taught courses at University level for Data Science as well as Business Intelligence.
Here is what you will get:
- Introduction to Jupyter Notebooks and Python Module Management
- Introduction to Natural Languages and NLP Applications
- In-Detail Text Preprocessing Techniques in Python
- Overview of Feature Engineering Approaches like Word2Vec, Bag of Words, or BERT Embeddings
- In-Depth Explanation on Convolutional Neural Networks for Classification Tasks
- Implementing Machine Learning Model for Sentiment Analysis Task in TensorFlow
- Getting to know the Process of Building, Compiling and Training a Deep Learning Model in Python
Join the course now!