• YASHDEEP SINGH
• VISHWAJEET RAI
• FARAZ CHISHTI

According to a report by CNBC about 40 million accounts on Twitter are bots and it has been estimated that up to 50% of the activity on Twitter is from these bots. Their motive is to advertise a product, distribute spam, or alter public opinion. Then it becomes extremely necessary to detect bots to protect genuine users from misinformation and malicious intents. Several types of research have been carried out in past years, but current algorithms still lag in performance and are not much efficient in determining whether the account is genuine or not. The idea behind this project is to build a Binary Classifier that identifies a given user as "bot" or "Human". This application is a web browser-based plug-in that would give a score to a given account based on 12 features that are verification status, followers, friends to follower’s ratio, frequency of tweets, re-tweet count per tweet Tweets variance, etc. Based on that score the end-user application would identify the account. It is our opinion that an application like this is sorely needed for a Twitter user for his own safety and for better confidentiality of data. The approach is to identify bots, of any type based on features that are acquired from user profile metadata and accumulated statics based on timeline data (tweet history).

twitter,bot,classifier,spam detection,twitter bot

"TWITTER BOT DETECTOR", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.514-517, May-2019, Available :http://www.jetir.org/papers/JETIR1905969.pdf

"TWITTER BOT DETECTOR", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp514-517, May-2019, Available at : http://www.jetir.org/papers/JETIR1905969.pdf