Get Practical Natural Language Processing now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
Get Practical Natural Language Processing now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
Get Mark Richards’s Software Architecture Patterns ebook to better understand how to design components—and how they should interact.
Dive in for free with a 10-day trial of the O’Reilly learning platform—then explore all the other resources our members count on to build skills and solve problems every day.
Start your free trial Become a member now
Chapter 8. Social Media
Social media platforms (Twitter, Facebook, Instagram, WhatsApp, etc.) have revolutionized the way we communicate with individuals, groups, communities, corporations, government agencies, media houses, etc. This, in turn, has changed established norms and etiquette and the day-to-day practices of how businesses and government agencies carry out things like sales, marketing, public relations, and customer support. Given the huge volume and variety of data generated daily on social media platforms, there’s a huge body of work focused on building intelligent systems to understand communication and interaction on these platforms. Since a large part of this communication happens in text, NLP has a fundamental role to play in building such systems. In this chapter, we’ll focus on how NLP is useful for analyzing social media data and how to build such systems.
To give an idea of the volume of data that’s generated on these platforms [1, 2, 3], consider the following numbers:
Volume: 152 million monthly active users on Twitter; for Facebook, it’s 2.5 billion
Velocity: 6,000 tweets/second; 57,000 Facebook posts/second
Variety: Topic, language, style, script
The infographic shown in Figure 8-1 presents how much data is generated per minute across different platforms [4].
Figure ...