Mining the Social Web

Mine the rich data tucked away in popular social websites such as Twitter, Facebook, LinkedIn, and Instagram. With the third edition of this popular guide, data scientists, analysts, and programmers will learn how to glean insights from social media―including who’s connecting with whom, what they’re talking about, and where they’re located―using Python code examples, Jupyter notebooks, or Docker containers.

In part one, each standalone chapter focuses on one aspect of the social landscape, including each of the major social sites, as well as web pages, blogs and feeds, mailboxes, GitHub, and a newly added chapter covering Instagram. Part two provides a cookbook with two dozen bite-size recipes for solving particular issues with Twitter.

• Get a straightforward synopsis of the social web landscape
• Use Docker to easily run each chapter’s example code, packaged as a Jupyter notebook
• Adapt and contribute to the code’s open source GitHub repository
• Learn how to employ best-in-class Python 3 tools to slice and dice the data you collect
• Apply advanced mining techniques such as TFIDF, cosine similarity, collocation analysis, clique detection, and image recognition
• Build beautiful data visualizations with Python and JavaScript toolkits

Table of Contents

Part I. A Guided Tour of the Social Web

1. Mining Twitter: Exploring Trending Topics, Discovering What People Are Talking About, and More

2. Mining Facebook: Analyzing Fan Pages, Examining Friendships, and More

3. Mining Instagram: Computer Vision, Neural Networks, Object Recognition, and Face Detection

4. Mining LinkedIn: Faceting Job Titles, Clustering Colleagues, and More

5. Mining Text Files: Computing Document Similarity, Extracting Collocations, and More

6. Mining Web Pages: Using Natural Language Processing to Understand Human Language, Summarize Blog Posts, and More

7. Mining Mailboxes: Analyzing Who’s Talking to Whom About What, How Often, and More

8. Mining GitHub: Inspecting Software Collaboration Habits, Building Interest Graphs, and More

Part II. Twitter Cookbook

9. Twitter Cookbook

Part III. Appendixes

A. Information About This Book’s Virtual Machine Experience

B. OAuth Primer

C. Python and Jupyter Notebook Tips and Tricks

About the Authors

Matthew Russell (@ptwobrussell) is Chief Technology Officer at Built Technologies, where he leads a team of leaders on a mission to improve the way the world is built. Outside of work, he contemplates ultimate reality, practices rugged individualism, and trains for the possibilities of a zombie or robot apocalypse.

Mikhail Klassen is Chief Data Scientist at Paladin AI, a startup creating adaptive training technologies. He has a PhD in computational astrophysics from McMaster University and a BS in applied physics from Columbia University. Mikhail is passionate about artificial intelligence and how the tools of data science can be used for good. When not working at a startup, he’s usually reading or traveling.