• Darla Vandana
• V.Sesha Bhargavi

Twitter, a popular micro-blogging service, is traditionally used to share messages and updates with a maximum of 280 characters. It is very open in nature and has a large user base which is often exploited by spammers to commit cybercrimes, like phishing, cyber bullying, harassment and spreading rumors. The proposed approach is to discriminate users depending on their activities with their corresponding followers where the user can bypass the features related to his/her activities, but avoiding those which are based on the followers is challenging. In this paper, a technique to detect automated spammers by combining metadata based features, content based features and interaction based features is proposed. Nine different features are identified for learning the dataset that includes both the legitimate users and spammers. The distinction between the feature categories is analyzed; interaction-based and content-based features are decided to be more effective for the detection of spammers, while metadata-based features are less effective.

Automated spammers, Social Network, Social Network Security, Spambot Detection

"A Mixed Technique to Detect Automated Spam Senders in a Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 8, page no.982-987, August-2020, Available :http://www.jetir.org/papers/JETIR2008127.pdf

"A Mixed Technique to Detect Automated Spam Senders in a Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 8, page no. pp982-987, August-2020, Available at : http://www.jetir.org/papers/JETIR2008127.pdf