What this book covers

Chapter 1, Social Media, Social Data, and Python, introduces the main concepts of data mining applied to social media using Python. By walking the reader through a brief overview on machine learning, NLP, social network analysis, and data visualization, this chapter discusses the main Python tools for data science and provides some help to set up the Python environment.

Chapter 2, #MiningTwitter – Hashtags, Topics, and Time Series, opens the practical discussion on data mining using the Twitter data. After setting up a Twitter app to interact with the Twitter API, the chapter explains how to get data through the streaming API and how to perform some frequentist analysis on hashtags and text. The chapter also discusses some time series analysis to understand the distribution of tweets over time.

Chapter 3, Users, Followers, and Communities on Twitter, continues the discussion on Twitter mining, focusing the attention on users and interactions between users. This chapter shows how to mine the connections and conversations between the users. Interesting applications explained in the chapter include user clustering (segmentation) and how to measure influence and user engagement.

Chapter 4, Posts, Pages, and User Interactions on Facebook, focuses on Facebook and the Facebook Graph API. After understanding how to interact with the Graph API, including aspects of security and privacy, examples of how to mine posts from a user's profile and Facebook pages are provided. The concepts of time series analysis and user engagement are applied to user interactions such as comments, Likes, and Reactions.

Chapter 5, Topic Analysis on Google+, covers the social network by Google. After understanding how to access the Google centralized platform, examples of how to search content and users on Google+ are discussed. This chapter also shows how to embed data coming from the Google API into a custom web application that is built using the Python microframework, Flask.

Chapter 6, Questions and Answers on Stack Exchange, explains the topic of question answering and uses the Stack Exchange network as paramount example. The reader has the opportunity to learn how to search for users and content on the different sites of this network, most notably Stack Overflow. By using their data dumps for online processing,  this chapter introduces supervised machine learning methods applied to text classification and shows how to embed machine learning model into a real-time application.

Chapter 7, Blogs, RSS, Wikipedia, and Natural Language Processing, teaches text analytics. The Web is full of opportunities in terms of text mining, and this chapter shows how to interact with several data sources such as the WordPress.com API, Blogger API, RSS feeds, and Wikipedia API. Using textual data, the basic notions of NLP briefly mentioned throughout the book are formalized and expanded. The reader is then walked through the process of information extraction with custom examples on how to extract references of entities from free text.

Chapter 8, Mining All the Data!, reminds us of the many opportunities, in terms of data mining, that are available out there beyond the most common social networks. Examples of how to mine data from YouTube, GitHub, and Yelp are provided, along with a discussion on how to build your own API client, in case a particular platform doesn't provide one.

Chapter 9, Linked Data and the Semantic Web, provides an overview on the Semantic Web and related technologies. This chapter discusses the topics of Linked Data, microformats, and RDF, and offers examples on how to mine semantic information from DBpedia and Wikipedia.