Social media spam as a case examine

Disclaimer: the examples on this put up are for illustrative functions and aren’t commentary on any particular content material coverage at any particular firm. All views expressed on this article are mine and don’t mirror my employer.

Why is there any spam on social media? Nobody other than the spammers themselves enjoys clickbait scams or phishing makes an attempt. We now have a long time of coaching knowledge to feed machine studying classifiers. So why does spam on each main tech platform really feel inevitable? In spite of everything these years, why do bot farms nonetheless exist?

The reply, in brief, is that it’s actually arduous to combat spam at scale, and exponentially more durable to take action with out harming real customers and advertisers. On this put up, we’ll use precision and recall as a framework for understanding the spam downside. We’ll see that eradicating 100% of spam is impractical, and that there’s some “equilibrium” spam prevalence primarily based on finance, rules, and consumer sentiment.

Think about we’re launching a competitor to TikTok and Instagram. (Overlook that they’ve 1.1 billion and 2 billion month-to-month energetic customers, respectively; we’re feeling bold!) Our key differentiator on this tight market is that we assure customers could have solely the best high quality of movies: completely no “get wealthy fast” schemes, blatant reposts of current content material, URLs that infect your laptop with malware, and many others.

Try 1: Human Overview

To attain this high quality assure, we’ve employed a staggering 1,000 reviewers to audit each add earlier than it’s allowed on the platform. Some issues simply want a human contact, we argue: video spam is simply too complicated and context-dependent to depend on automated logic. A video that urges customers to click on on a URL might be a malicious phishing try or a benign fundraiser for Alzheimer’s analysis, for instance — the stakes are too excessive to…