Header menu link for other important links
Exploiting Aspect-Classified Sentiments for Cyber-Crime Analysis and Hack Prediction
S. Mandal, , R. Nag
Published in Springer Science and Business Media Deutschland GmbH
Volume: 1358
Pages: 200 - 212
In today’s world both cybercrimes and the huge data on social media have been a subject of study and recent research has shown that there is a strong correlation between the two. The occurrence of cyber threats is hard to predict because of the sporadic nature of such events. Generally the hackers and other cyber criminals tend to conceal their activities. But it is often seen that majority of such activities occur as a response to a social incident involving phenomenal discussions on the social media. Accurate study of the available data can allow us to predict such crimes and thus can be used to generate an alert in appropriate time. This paper has been aimed at considering the different aspects of social events, responses and their relations to further improve the classification of the social sentiment. The proposed method covers not only the response due to major social events but also predicting and generating alert for situations of significant social importance. The approach has made use of Twitter datasets and performed aspect-based sentiment analysis on the obtained text data. It is shown to outperform the state of the art methods. © 2020, Springer Nature Switzerland AG.
About the journal
JournalData powered by TypesetCommunications in Computer and Information Science
PublisherData powered by TypesetSpringer Science and Business Media Deutschland GmbH