A survey on predictions of cyber-attacks utilizing real-time twitter tracing recognition

In recent years, the number of cyber-attacks increased affecting different application types and targets. Many studies tried to focus on proposing solutions to detect imminent and current attacks. Besides that, they tried to extract useful information expecting these attacks in different ways. This study considered surveying recognizing the popular social online network Twitter data to detect and predict security attacks possibility. In this paper, we review and compare the relevant existing works that make use of Twitter streaming data to extract knowledge about current and imminent security cyber-attacks. The survey comparison is based on different effectiveness factors that are essential in the cyber domain for obtaining useful results. The work considered prediction factors investigating the detection scope, feature extraction technique, algorithm complexity, information summarization level, scalability over time, and performance measurements, all analysed to gain its prediction contribution. The comparison results are utilized for arranging previous work by a suggested unified (figure of merit) degree of achieving the factors. Thus, many improvements are proposed to enhance the top two models, SYNAPSE and DataFreq, to take a further step toward accurate predictions. This survey work is focussing on linking unrelated viewed studies aiming common prediction of cyber-security attacks in an attractive way, opening the door for more precise predictions of cyber-attacks research to come.