A Hybrid Approach to Analyze Cybersecurity News Articles by Utilizing Information Extraction & Sentiment Analysis Methods

Abstract

Cybersecurity is becoming indispensable for everyone and everything in the times of the Internet of Things (IoT) revolution. Every aspect of human society — be it political, financial, technological, or cultural — is affected by cyber-attacks or incidents in one way or another. Newspapers are an excellent source that perfectly captures this web of cybersecurity. By implementing various NLP techniques such as tf-idf, word embedding and sentiment analysis (SA) (machine learning method), this research will examine the cybersecurity-related articles from 18 major newspapers (English language online version) from six countries (three newspapers from each country) collected within one year from April 2018 till March 2019. The first objective is to extract the crucial events from each country, which we will achieve by our first step — ‘information extraction.’ The next objective is to find out what kind of sentiments those crucial issues garnered, which we will accomplish from our second step — ‘SA.’ SA of news articles would also help in understanding each ‘nation’s mood’ on critical cybersecurity issues, which can aid decision-makers in charting new policies.