Threat Detection in Tweets with Trigger Patterns and Contextual Cues

Abstract

Abstract-Many threats in the real world can be related to activities in open sources on the internet. Early detection of threats based on internet information could assist in the prevention of incidents. However, the amount of data in social media, blogs and forums rapidly increases and it is time consuming for security services to monitor all these open sources. Therefore, it is important to have a system that automatically ranks messages based on their threat potential and thereby allows security operators to check these messages more efficiently. In this paper, we present a novel method for detecting threatening messages on Twitter based on trigger keywords and contextual cues. The system was tested on multiple large collections of Dutch tweets. Our experimental results show that our system can successfully analyze messages and recognize threatening content.

Harnessing Artificial Intelligence Capabilities to Improve Cybersecurity

“…Their work classified fake news with 77.2 percent accuracy using Stochastic Gradient Descent, an iterative optimization algorithm. The authors of [109] proposed correlation-based classifiers, analyzed more than 150,000 tweets, and showed that the proposed classifiers performed with 47 times greater precision than when the system was not employed in classifying messages. The authors of [110] analyzed 4.4 million Facebook messages and classified them into fake and legitimate ones.…”

“…Furthermore, detecting false information borrows knowledge from linguistics [112] to classify texts. Here, the text classification approaches [108], [109], [113], [114] expand observations and features required in cybersecurity to implement automatic detection methods. The features such as grammatical mistakes and choice of words are adopted from linguistic cues, which are then mapped into machine learning features.…”

Cyber Security Model Based on Open Source Intelligence via Twitter Tweets

“…Filtreleme için birbiri ile alakalı kelime gruplarının kullanılması tweetin siber saldırı veya güvenlik ile ilgili olma olasılığını arttıracaktır [14]. Buradaki asıl amaç, saldırı ile ilgili maksimum alakaya sahip tweetlerin analiz edilmesini sağlamaktır.…”

“…Kullanılan yapı tweetlerin sınıflandırılmasında %70 oranında başarı sağlanmıştır. Spitters ise çalışmasında[14] tek kelime yerine kelime kalıplarını kullanarak tweetlerin tehdit içerip içermediğini tespit etmeye çalışmıştır. Kullanılan filtrelerde makine öğrenmesi metotları kullanarak sistemin tehdit içeren kelime ve kelime gruplarını öğrenmesi sağlanmıştır.…”

Improved lexicon-based sentiment analysis for social media analytics

“…A work related to predicting popularity of forum threads related to public events was undertaken in [14]. In [15] a method based on trigger keywords and contextual cues was proposed for detecting threatening messages on social media. A Violence Detection Model was proposed in [16] for identification of violence related topics being discussed on a micro blog.…”