Mastering Social Media Mining with Python

✍ Scribed by Marco Bonzanini

• Publisher: Packt Publishing
• Year: 2016
• Tongue: English
• Leaves: 333
• Category: Library

✦ Synopsis

Key Features

• Make sense of highly unstructured social media data with the help of the insightful use cases provided in this guide
• Use this easy-to-follow, step-by-step guide to apply analytics to complicated and messy social data
• This is your one-stop solution to fetching, storing, analyzing, and visualizing social media data

Book Description

Your social media is filled with a wealth of hidden data – unlock it with the power of Python. Transform your understanding of your clients and customers when you use Python to solve the problems of understanding consumer behavior and turning raw data into actionable customer insights.

This book will help you acquire and analyze data from leading social media sites. It will show you how to employ scientific Python tools to mine popular social websites such as Facebook, Twitter, Quora, and more. Explore the Python libraries used for social media mining, and get the tips, tricks, and insider insight you need to make the most of them. Discover how to develop data mining tools that use a social media API, and how to create your own data analysis projects using Python for clear insight from your social data.

What you will learn

• Interact with a social media platform via their public API with Python
• Store social data in a convenient format for data analysis
• Slice and dice social data using Python tools for data science
• Apply text analytics techniques to understand what people are talking about on social media
• Apply advanced statistical and analytical techniques to produce useful insights from data
• Build beautiful visualizations with web technologies to explore data and present data products

About the Author

Marco Bonzanini is a data scientist based in London, United Kingdom. He holds a PhD in information retrieval from Queen Mary University of London. He specializes in text analytics and search applications, and over the years, he has enjoyed working on a variety of information management and data science problems.

He maintains a personal blog at http://marcobonzanini.com, where he discusses different technical topics, mainly around Python, text analytics, and data science.

When not working on Python projects, he likes to engage with the community at PyData conferences and meet-ups, and he also enjoys brewing homemade beer.

Table of Contents

1. Social Media, Social Data, and Python
2. MiningTwitter – Hashtags, Topics, and Time Series
3. Users, Followers, and Communities on Twitter
4. Posts, Pages, and User Interactions on Facebook
5. Topic Analysis on Google+
6. Questions and Answers on Stack Exchange
7. Blogs, RSS, Wikipedia, and Natural Language Processing
8. Mining All the Data!
9. Linked Data and the Semantic Web

✦ Table of Contents

Cover
Copyright
Credits
About the Author
About the Reviewer
www.PacktPub.com
Table of Contents
Preface
Chapter 1: Social Media, Social Data, and Python
Getting started
Social media – challenges and opportunities
Opportunities
Challenges
Social media mining techniques
Python tools for data science
Python development environment setup
pip and virtualenv
Conda, Anaconda, and Miniconda
Efficient data analysis
Machine learning
Natural language processing
Social network analysis
Data visualization
Processing data in Python
Building complex data pipelines
Summary
Chapter 2: #MiningTwitter – Hashtags, Topics, and Time Series
Getting started
The Twitter API
Rate limits
Search versus Stream
Collecting data from Twitter
Getting tweets from the timeline
The structure of a tweet
Using the Streaming API
Analyzing tweets – entity analysis
Analyzing tweets – text analysis
Analyzing tweets – time series analysis
Summary
Chapter 3: Users, Followers, and Communities on Twitter
Users, friends, and followers
Back to the Twitter API
The structure of a user profile
Downloading your friends' and followers' profiles
Analysing your network
Measuring influence and engagement
Mining your followers
Mining the conversation
Plotting tweets on a map
From tweets to GeoJSON
Easy maps with Folium
Summary
Chapter 4: Posts, Pages, and User Interactions on Facebook
The Facebook Graph API
Registering your app
Authentication and security
Accessing the Facebook Graph API with Python
Mining your posts
The structure of a post
Time frequency analysis
Mining Facebook Pages
Getting posts from a Page
Facebook Reactions and the Graph API 2.6
Measuring engagement
Visualizing posts as a word cloud
Summary
Chapter 5: Topic Analysis on Google+
Getting started with the Google+ API
Searching on Google+
Embedding the search results in a web GUI
Decorators in Python
Flask routes and templates
Notes and activities from a Google+ page
Text analysis and TF-IDF on notes
Capturing phrases with n-grams
Summary
Chapter 6: Questions and Answers on Stack Exchange
Questions and answers
Getting started with the Stack Exchange API
Searching for tagged questions
Searching for a user
Working with Stack Exchange data dumps
Text classification for question tags
Supervised learning and text classification
Classification algorithms
Naive Bayes
k-Nearest Neighbor
Support Vector Machines
Evaluation
Performing text classification on Stack Exchange data
Embedding the classifier in a real-time application
Summary
Chapter 7: Blogs, RSS, Wikipedia, and Natural Language Processing
Blogs and NLP
Getting data from blogs and websites
Using the WordPress.com API
Using the Blogger API
Parsing RSS and Atom feeds
Getting data from Wikipedia
A few words about web scraping
NLP Basics
Text preprocessing
Sentence boundary detection
Word tokenization
Part-of-speech tagging
Word normalization
Case normalization
Stemming
Lemmatization
Stop word removal
Synonym mapping
Information extraction
Summary
Chapter 8: Mining All the Data!
Many social APIs
Mining videos on YouTube
Mining open source software on GitHub
Mining local businesses on Yelp
Building a custom Python client
HTTP made simple
Summary
Chapter 9: Linked Data and the Semantic Web
A Web of Data
Semantic Web vocabulary
Microformats
Linked Data and Open Data
Resource Description Framework
JSON-LD
Schema.org
Mining relations from DBpedia
Mining geo coordinates
Extracting geodata from Wikipedia
Plotting geodata on Google Maps
Summary
Index

✦ Subjects

Computers, Databases, Data Mining, Programming Languages, Python, Data Modeling & Design