Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Demo
Search
Greg Starek
February 15, 2016
44
1
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Demo
Bot or Not: Detecting Fraudulent Social Media Accounts
Greg Starek
February 15, 2016
Featured
See All Featured
Facilitating Awesome Meetings
lara
57
7.2k
Scaling GitHub
holman
464
140k
Thoughts on Productivity
jonyablonski
76
5.4k
Intergalactic Javascript Robots from Outer Space
tanoku
273
28k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.6k
Tips & Tricks on How to Get Your First Job In Tech
honzajavorek
1
800
Side Projects
sachag
456
43k
Lightning talk: Run Django tests with GitHub Actions
sabderemane
0
300
The AI Search Optimization Roadmap by Aleyda Solis
aleyda
2
6.3k
RailsConf 2023
tenderlove
30
1.6k
Optimizing for Happiness
mojombo
378
71k
Six Lessons from altMBA
skipperchong
29
4.5k
Transcript
Greg Starek Insight Data Science Bot or Not: Detecting Fraudulent
Social Media Accounts
None
Bot Followers Human Followers Bot Followers Human Followers Bots are
under-followed Bots are spammy Number of Followers Follower Max Post Rate Proportion of Followers Proportion of Followers
Bot Followers Human Followers Bot Followers Human Followers Bots are
under-followed Bots are spammy Number of Followers Follower Max Post Rate Proportion of Followers Proportion of Followers
Instagram API: Data Bottleneck Complete sampling of both features requires
> 6 hours
Instagram API: Data Bottleneck Bootstrapping a random subsample takes <
5 minutes! Complete sampling of both features requires > 6 hours
Bot or Not delivers: 1. Improved fraud detection 2. Classifier
to build predictive model 3. Sampling method within constraints of Instagram API 4. Scalable solution
Greg Starek
None