Book Image

Machine Learning for Emotion Analysis in Python

By : Allan Ramsay, Tariq Ahmad
5 (1)
Book Image

Machine Learning for Emotion Analysis in Python

5 (1)
By: Allan Ramsay, Tariq Ahmad

Overview of this book

Artificial intelligence and machine learning are the technologies of the future, and this is the perfect time to tap into their potential and add value to your business. Machine Learning for Emotion Analysis in Python helps you employ these cutting-edge technologies in your customer feedback system and in turn grow your business exponentially. With this book, you’ll take your foundational data science skills and grow them in the exciting realm of emotion analysis. By following a practical approach, you’ll turn customer feedback into meaningful insights assisting you in making smart and data-driven business decisions. The book will help you understand how to preprocess data, build a serviceable dataset, and ensure top-notch data quality. Once you’re set up for success, you’ll explore complex ML techniques, uncovering the concepts of deep neural networks, support vector machines, conditional probabilities, and more. Finally, you’ll acquire practical knowledge using in-depth use cases showing how the experimental results can be transformed into real-life examples and how emotion mining can help track short- and long-term changes in public opinion. By the end of this book, you’ll be well-equipped to use emotion mining and analysis to drive business decisions.
Table of Contents (18 chapters)
1
Part 1:Essentials
3
Part 2:Building and Using a Dataset
7
Part 3:Approaches
14
Part 4:Case Study

Using SVMs for sentiment mining

We have now seen how SVMs provide classifiers by finding hyperplanes that separate the data into classes and have seen a graphical explanation of how such hyperplanes can be found, even when the data is not linearly separable. Now, we’ll look at how SVMs can be applied to our datasets to find the boundaries between sentiments, with an analysis of their behavior on single-label and multi-label datasets and a preliminary investigation into how their performance on multi-label datasets might be improved.

Applying our SVMs

As with the previous classifiers, we can define the SVMCLASSIFIERs class as a subclass of SKLEARNCLASSIFIER by using the following initialization code (useDF is a flag to decide whether to use the TF-IDF algorithm from Chapter 5, Sentiment Lexicons and Vector Space Models when building the training set; max_iter sets an upper bound on the number of iterations the SVM algorithm should carry out – for our examples, the...