Fundamentals of Text Analytics: Suggested Sequence

The following list represents a suggested sequence for the text analytics teaching tools. The sequence is designed to ensure that students build upon their previous learning as they progress through the topics.

Topic Classroom Tools

I. Text Analysis: Basics

Introduction to Text Analysis

An overview of natural language processing (NLP), concentrating on techniques used to prepare text data for analysis.

II. Sentiment Analysis

Introduction to Sentiment Analysis

Learn basics of sentiment analysis, including how text can be classified as positive, negative, or neutral.

Sentiment Analysis Lexicons

Introduces different types of sentiment lexicons, including a domain-specific sentiment lexicon used to analyze financial statements.

Challenges of Sentiment Analysis

Examines common challenges to sentiment analysis, and includes an introduction to the VADER model for performing a sentiment analysis.

III. Named-Entity Recognition

Named-Entity Recognition

Understand the practice of named-entity recognition (NER) and evaluate three different approaches to NER.

IV. Machine Learning

Machine Learning: Text Classification

An overview of supervised machine learning, and a step-by-step explanation of how a naive Bayes classifier works for text classification.

Unsupervised Machine Learning: Clustering

Learn about clustering as an unsupervised machine learning task and become familiar with how the k-means algorithm works for text classification.

Introduction to Topic Modeling

An introduction to the benefits and challenges of using topic modeling, as well as an overview of the latent Dirichlet allocation (LDA) method..

Topic Modeling: NMF

Begins with a short review of topic modeling and moves on to an overview of a technique for topic modeling known as non-negative matrix factorization (NMF).