Facebook、Twitter和Linkedln产生了大量的宝贵的社交数据，但是你怎样才能找出谁通过社交媒介进行联系？他们在讨论些什么？或者他们在哪儿？《挖掘社交网络(影印版)》这本简洁而且具有操作性的书将为你展示如何回答这些甚至更多的问题。你将学到如何组合社交网络数据、分析技术，如何通过可视化帮助你找到你一直在社交世界中寻找的内容，以及那些你都不知道存在的有用信息。

每个独立章节介绍了在社交网络的不同领域挖掘数据的技术，这些领域包括博客和电子邮件。你所需要具备的就是一定的编程经验和学习基本的python工具的意愿。

Preface

1. Introduction: Hacking on Twitter Data

 Installing Python Development Tools

 Collecting and Manipulating Twitter Data

 Tinkering with Twitter's API

 Frequency Analysis and Lexical Diversity

 Visualizing Tweet Graphs

 Synthesis: Visualizing Retweets with Protovis

 Closing Remarks

2. Microformats: Semantic Markup and Common Sense Collide

 XFN and Friends

 Exploring Social Connections with XFN

 A Breadth-First Crawl of XFN Data

 Geocoordinates: A Common Thread for Just About Anything

 Wikipedia Articles + Google Maps = Road Trip?

 Slicing and Dicing Recipes (for the Health of It)

 Collecting Restaurant Reviews

 Summary

3. Mailboxes: Oldies but Goodies

 mbox: The Quick and Dirty on Unix Mailboxes

 mbox + CouchDB = Relaxed Email Analysis

 Bulk Loading Documents into CouchDB

 Sensible Sorting

 Map/Reduce-Inspired Frequency Analysis

 Sorting Documents by Value

 cotichdb-lucene: Full-Text Indexing and More

 Threading Together Conversations

 Look Who's Talking

 Visualizing Mail "Events" with SIMILE Timeline

 Analyzing Your Own Mail Data

 The Graph Your (Gmail) Inbox Chrome Extension

 Closing Remarks

4. Twitter: Friends, Followers, and Setwise Operations

 RESTful and OAuth-Cladded APIs

 No, You Can't Have My Password

 A Lean, Mean Data-Collecting Machine

 A Very Brief Refactor Interlude

 Redis: A Data Structures Server

 Elementary Set Operations

 Souping Up the Machine with Basic Friend/Follower Metrics

 Calculating Similarity by Computing Common Friends and Followers

 Measuring Influence

 Constructing Friendship Graphs

 Clique Detection and Analysis

 The Infochimps "Strong Links" API

 Interactive 3D.Graph Visualization

 Summary

5. Twitter: The Tweet, the Whole Tweet, and Nothing but the Tweet

 Pen : Sword :: Tweet : Machine Gun (?!?)

 Analyzing Tweets (One Entity at a Time)

 Tapping (Tim's) Tweets

 Who Does Tim Retweet Most Often?

 What's Tim's Influence?

 How Many of Tim's Tweets Contain Hashtags?

 Juxtaposing Latent Social Networks (or #JustinBieber Versus #TeaParty)

 What Entities Co-Occur Most Often with #JustinBieber and #TeaParty

 Tweets?

 On Average, Do #JustinBieber or #TeaParty Tweets Have More

 Hashtags?

 Which Gets Retweeted More Often: #JustinBieber or #TeaParty?

 How Much Overlap Exists Between the Entities of #TeaParty and

 #JustinBieber Tweets?

 Visualizing Tons of Tweets

 Visualizing Tweets with Tricked-Out Tag Clouds

 Visualizing Community Structures in Twitter Search Results

 Closing Remarks

6. Linkedln: Clustering Your Professional Network for Fun (and Profit?)

 Motivation for Clustering

 Clustering Contacts by Job Title

 Standardizing and Counting Job Titles

 Common Similarity Metrics for Clustering

 A Greedy Approach to Clustering

 Hierarchical and k-Means Clustering

 Fetching Extended Profile Information

 Geographically Clustering Your Network

 Mapping Your Professional Network with Google Earth

 Mapping Your Professional Network with Dorling Cartograms

 Closing Remarks

7. Google Buzz: TF-IDF, Cosine Similarity, and Collocations

 Buzz = Twitter + Blogs (???)

 Data Hacking with NLTK

 Text Mining Fundamentals

 A Whiz-Bang Introduction tO TF-IDF

 Querying Buzz Data with TF-IDF

 Finding Similar Documents

 The Theory Behind Vector Space Models and Cosine Similarity

 Clustering Posts with Cosine Similarity

 Visualizing Similarity with Graph Visualizations

 Buzzing on Bigrams

 How the Collocation Sausage Is Made: Contingency Tables and Scoring

 Functions

 Tapping into Your Gmail

 Accessing Gmail with OAuth

 Fetching and Parsing Email Messages

 Before You Go Off and Try to Build a Search Engine...

 Closing Remarks

8. Blogs et al.: Natural Language Processing (and Beyond)

 NLP: A Pareto-Like Introduction

 Syntax and Semantics

 A Brief Thought Exercise

 A Typical NLP Pipeline with NLTK

 Sentence Detection in Blogs with NLTK

 Summarizing Documents

 Analysis of Luhn's Summarization Algorithm

 Entity-Centric Analysis: A Deeper Understanding of the Data

 Quality of Analytics

 Closing Remarks

9. Facebook:TheAll-in-OneWonder

 Tapping into Your Social Network Data

 From Zero to Access Token in Under 10 Minutes

 Facebook's Query APIs

 Visualizing Facebook Data

 Visualizing Your Entire Social Network

 Visualizing Mutual Friendships Within Groups

 Where Have My Friends All Gone? (A Data-Driven Game)

 Visualizing Wall Data As a (Rotating) Tag Cloud

 Closing Remarks

10. The Semantic Web: A Cocktail Discussion

 An Evolutionary Revolution?

 Man Cannot Live on Facts Alone

 Open-World Versus Closed-World Assumptions

 Inferencing About an Open World with FuXi

 Hope

Index