A study on Humans and Bots in Internet Chat

ast week I was contacted by Steven Gianvecchio, one of the co authors who did a case study on the topic Measurement and Classification of Humans and Bots in Internet Chat. As a summary this case study documented how the abuse of chat services by automated programs, known as chat bots, poses a serious threat to Internet users. Chat bots target popular chat networks to distribute spam and malware.

Here is a direct quote from their case study

In this paper, we first conduct a series of measurements on a large commercial chat network. Our measurements capture a total of 14 different types of chat bots ranging from simple to advanced. Moreover, we observe that human behavior is more complex than bot behavior. Based on the measurement study, we propose a classification system to accurately distinguish chat bots from human users.

Even we on TS had posted about this many a times. Some posts which really took these guys attention where

  • Yahoo! chat adds CAPTCHA check to remove bots ( Read More )
  • Bots are back in Yahoo! chat rooms. ( Read More )
  • Infact we also did made an open announcement to Yahoo on what they are doing with chat rooms. Users have pointed out their problems in all these posts.

We feel great that our effort for this was included in their case study along with. Thanks Guys.

If you  be interested go ahead and read their article on Measurement and Classification of Humans and Bots in Internet Chat. Just a note that its little complex as it has lot more details with calculations, diagrams and lot more.

As a conclusion we are not sure what yahoo chat is doing about it but their captcha check is serious failure and it has done nothing but added problems because of which even regular users don’t get access to chat rooms, Pity. We hope they do something about it with time.


Please enter your comment!
Please enter your name here