Thread by @jojobickley

Many know I design #ConversationModels #Chatbots & #ai powered #VUI. Using that expertise for good is my mission in life. While twitter continues to close #FakeAccounts of the most egregious, and obvious, offenders - here is a primer to help our community spot & report #bots.

It’s important not to be swayed by #FakeAccounts or waste your time arguing with them. Identifying #bots in a Twitter thread has become a strange version of the Turing test. Here is are the data points you need to ID a #bot.
#ai #vui #chatbots #conversationmodels

User profile
The most common way to tell if an account is fake is to check out the profile. The most rudimentary #bots lack a photo, a link, or any bio. More sophisticated ones might use a photo stolen from the web, or an automatically generated account name.
#ai #vui #chatbot

Tweet syntax
Using human language is still incredibly hard for machines. A bot’s tweets may reveal its algorithmic logic: they may be formulaic or repetitive, or use responses common in chatbot programs. Missing an obvious joke and rapidly changing the subject are telltale traits

Tweet semantics
Bots are usually created with a particular end in mind, so they may be overly obsessed with a particular topic, perhaps reposting the same link again and again or tweeting about little else.
#ai #vui #chatbots #conversationmodels

Temporal behavior
Looking at tweets over time can also be revealing. If an account tweets at an impossible rate, at unlikely times, or even too regularly, that can be a good sign that it’s fake. Fake accounts often betray an inconsistent attitude toward topics over time. #ai #vui

Network dynamics aren’t visible to most users, but they can reveal a lot about an account. #Bots may follow only a few accounts or be followed by other bots. The tone of a bot’s tweets may also be incongruous w/ its connections, suggesting a lack of real social interaction.
#ai

URL shorteners
Automated accounts often track traffic on a particular link by using URL shortening services, so the frequency with which these services are used can be an indicator of automation.
#ai #vui #chatbots #conversationmodels

Multiple languages
#Bots created for commercial ads have created to “advertise” political positions. If you see an account posting or retweeting content in English, Dutch, Arabic, Russian, and Mandarin, it’s possible you’ve encountered a human polyglot—it’s more likely it's a bot

Here are a few links to great resources
The DARPA Twitter Bot Challenge
ieeexplore.ieee.org/document/74903…

#ai #vui #chatbots #conversationmodels #bots #fakeaccounts

The five best ways to detect fake social-media accounts.
technologyreview.com/s/611655/how-t…

#ai #vui #chatbots #conversationmodels #bots #fakeaccounts

five ways to identify phony Twitter accounts and ditch them.
motherjones.com/media/2018/08/…

#ai #vui #chatbots #conversationmodels #bots #fakeaccounts

3 ways to spot fake Twitter accounts
blog.mozilla.org/internetcitize…

#ai #vui #chatbots #conversationmodels #bots #fakeaccounts

Everything You Need to Know About How to Spot a Bot
bbc.com/news/av/storie…
#ai #vui #chatbots #conversationmodels #bots #fakeaccounts