Sentiment Analysis for Exploratory Data Analysis

In this lesson you will learn to conduct ‘sentiment analysis’ on texts and to interpret the results. This is a form of exploratory data analysis based on natural language processing. You will learn to install all appropriate software and to build a reusable program that can be applied to your own texts.

This lesson uses sentiment analysis as the basis for an exploratory data analysis of a large textual corpus. It is appropriate for readers with some basic prior experience programming with Python. If you have no experience with Python or computer programming, the author recommends working through the first few lessons in the Introduction to Python series. By the end of this lesson, you will be able to:

• Devise appropriate research questions that use Natural Language Processing (NLP) on a textual corpus.
• Use Python and the Natural Language Processing Toolkit (NLTK) to generate sentiment scores for a text.
• Critically evaluate the sentiment analysis scores and adjust parameters and methodology as appropriate.
• Identify next steps to continue learning about exploratory data analysis and programmatic approaches to qualitative data.