Open AccessDetecting spam campaign in twitter with semantic similarity
Author(s) -
Mohamed Saber Mostafa,
Amira Abdelwahab,
Hanan M El Sayed
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1447/1/012044
Subject(s) - spamming , computer science , social media , similarity (geometry) , key (lock) , precision and recall , information retrieval , spambot , world wide web , artificial intelligence , internet privacy , computer security , the internet , image (mathematics)
Twitter is a widespread supply for real-time news distribution between individuals. Furthermore, spammers could post any kinds of spam content to users, and a variant of incidents are committed on Twitter against users. These threats aren’t restricted to the social media platforms however they threaten the safety of Twitter users. Most of the researches use deep learning techniques to detect Twitter spammer activities. The traditional solutions check the behavior of each account or campaign of similar purpose accounts. The number of solutions concentrate on detecting spam campaign based on URL only and ignoring text in a tweet. In this paper, the lightweight framework is proposed to take tweet text into consideration for optimizing spam campaign detection methods based on deep learning techniques. The main contribution of this work summarized in two key points. First one is to summarize text of the tweets to cluster them. The second one is to find similar tweets based on Siamese Recurrent Network. Experimental results show the ability of the proposed technique to extract the right candidate campaign and classify them as spam or not with high recall and precision.