社交网站数据如同深埋地下的“金矿”，如何利用这些数据来发现哪些人正通过社交媒介进行联系？他们正在谈论什么？或者他们在哪儿？本书第2版对上一版内容进行了全面更新和修订，它将揭示回答这些问题的方法与技巧。你将学到如何获取、分析和汇总散落于社交网站（包括Facebook、Twitter、LinkedIn、Google+、 GitHub、邮件、网站和博客等）的数据，以及如何通过可视化找到你一直在社交世界中寻找的内容和你闻所未闻的有用信息。

Preface
Part I. A Guided Tour of the Social Web
Prelude
1. Mining Twitter: Exploring Trending Topics, Discovering What People Are Talking
About, and More
1.1 Overview
1.2 Why Is Twitter All the Rage?
1.3 Exploring Twitter's API
1.3.1 Fundamental Twitter Terminology
1.3.2 Creating a Twitter API Connection
1.3.3 Exploring Trending Topics
1.3.4 Searching for Tweets
1.4 Analyzing the 140 (or More) Characters
1.4.1 Extracting Tweet Entities
1.4.2 Analyzing Tweets and Tweet Entities with Frequency Analysis
1.4.3 Computing the Lexical Diversity of Tweets
1.4.4 Examining Patterns in Retweets
1.4.5 Visualizing Frequency Data with Histograms
1.5 Closing Remarks
1.6 Recommended Exercises
1.7 Online Resources
2. Mining Facebook: Analyzing Fan Pages, Examining Friendships, and More
2.1 Overview
2.2 Exploring Facebook's Graph API
2.2.1 Understanding the Graph API
2.2.2 Understanding the Open Graph Protocol
2.3 Analyzing Social Graph Connections
2.3.1 Analyzing Facebook Pages
2.3.2 Manipulating Data Using pandas
2.4 Closing Remarks
2.5 Recommended Exercises
2.6 Online Resources
3. Mining Instagram: Computer Vision, Neural Networks, Object Recognition,
and Face Detection
3.1 Overview
3.2 Exploring the Instagram API
3.2.1 Making Instagram API Requests
3.2.2 Retrieving Your Own Instagram Feed
3.2.3 Retrieving Media by Hashtag
3.3 Anatomy of an Instagram Post
3.4 Crash Course on Artificial Neural Networks
3.4.1 Training a Neural Network to "Look" at Pictures
3.4.2 Recognizing Handwritten Digits
3.4.3 Object Recognition Within Photos Using Pretrained Neural
Networks
3.5 Applying Neural Networks to Instagram Posts
3.5.1 Tagging the Contents of an Image
3.5.2 Detecting Faces in Images
3.6 Closing Remarks
3.7 Recommended Exercises
3.8 Online Resources
4. Mining Linkeflln: Faceting Job Titles, Clustering Colleagues, and More
4.1 Overview
4.2 Exploring the LinkedIn API
4.2.1 Making LinkedIn API Requests
4.2.2 Downloading LinkedIn Connections as a CSV File
4.3 Crash Course on Clustering Data
4.3.1 Normalizing Data to Enable Analysis
4.3.2 Measuring Similarity
4.3.3 Clustering Algorithms
4.4 Closing Remarks /
4.5 Recommended Exercises
4.6 Online Resources
5. Mining Text Files: Computing Document Similarity, Extracting Collocations, and More.
5.1 Overview
5.2 Text Files
5.3 A Whiz-Bang Introduction to TF-IDF
5.3.1 Term Frequency
5.3.2 Inverse Document Frequency
5.3.3 TF-IDF
5.4 Querying Human Language Data with TF-IDF
5.4.1 Introducing the Natural Language Toolkit
5.4.2 Applying TF-IDF to Human Language
5.4.3 Finding Similar Documents
5.4.4 Analyzing Bigrams in Human Language
5.4.5 Reflections on Analyzing Human Language Data
5.5 Closing Remarks
5.6 Recommended Exercises
5.7 Online Resources
6. Mining Web Pages: Using Natural Language Processing to Understand Human
Language, Summarize Blog Posts, and More
6.1 Overview
6.2 Scraping, Parsing, and Crawling the Web
6.2.1 Breadth-First Search in Web Crawling
6.3 Discovering Semantics by Decoding Syntax
6.3.1 Natural Language Processing Illustrated Step-by-Step
6.3.2 Sentence Detection in Human Language Data
6.3.3 Document Summarization
6.4 Entity-Centric Analysis: A Paradigm Shift
6.4.1 Gisting Human Language Data
6.5 Quality of Analytics for Processing Human Language Data
6.6 Closing Remarks
6.7 Recommended Exercises
6.8 Online Resources
7. Mining Mailboxes: Analyzing Who's Talking to Whom About What,
How Often, and More
7.1 Overview
7.2 Obtaining and Processing a Mail