Sentiment Analysis has become increasingly important as more opinions are expressed online, in unstructured form. This course covers rule-based and ML-based approaches to extracting sentiment from opinions, including VADER, Sentiwordnet, and more.
Online opinions are becoming ubiquitous - more people are expressing their views online than ever before. As a result, extracting sentiment information from these opinions is becoming very important. In this course, Building Sentiment Analysis Systems in Python, you will learn the fundamentals of building a system to do so in Python. First, you will learn the differences between ML- and rule-based approaches, and how to use VADER, Sentiwordnet, and Naive Bayes classifiers. Next, you will build three sentiment analyzers, and use them to classify a corpus of movie reviews made available by Cornell. Finally, you will gain a conceptual understanding of Support Vector Machines, and why Naive Bayes is usually a better choice. When you're finished with this course, you will have a clear understanding of how to extract sentiment from a body of opinions, and of the design choices and trade-offs involved.
An engineer and tinkerer, Vitthal has worked at Google, Credit Suisse, and Flipkart and
studied at Stanford and INSEAD. He has worn many hats, each of which has involved
writing code and building models. He is passionately devoted to his hobby of laughing at
his own jokes.
Course Overview Hi everyone! My name is Vitthal Srinivasan. Welcome to my course, Building Sentiment Analysis Systems in Python. I am a co-founder at a start-up named Loonycorn. In the past, I've worked at Google and studied at Stanford. A person runs past you on the street in the morning. How does your brain decide whether she is participating in a marathon or a police officer chasing down a suspect? See how Bayes' Theorem shapes our intuition and is also the foundation of one of the most powerful machine learning techniques out there today. Some of the major topics that we will cover include machine learning techniques, such as naive Bayes classification and support vector machines, rule-based techniques such as Vader and SentiWordNet, Nltk, which is Python's powerful natural language processing tool kit, and the intuition behind Bayes' Theorem. By the end of this course you'll know how to build robust, powerful sentiment analysis systems in Python with accuracy approaching 75% on a famous corpus of movie review data made available by Cornell university. You'll also understand the flaws underlying some other approaches that do not perform quite so well. Before beginning this course, you should be familiar with basic Python programming. I hope you'll join me on this journey to learn opinion mining using machine learning with the course, building sentiment analysis systems in Python at Pluralsight.