Attitudes Towards Log4j : A Sentiment Analysis Study on Twitter Data

Abstract: A major security risk with the use of a Java logging library called Log4j was discovered in November 2021. The vulnerability meant that all Java applications using Log4j could be exploited by hackers through remote code execution. The Log4j vulnerability came to the general public's knowledge and became a hot topic on various social media platforms the 9th of December 2021. This is what will be referred to as the Log4j incident in this paper. The aim of the study is to investigate what attitudes users on Twitter have towards Log4j and how these attitudes have evolved over time in relation to the incident in question. Twitter data regarding Log4j was collected using Twitter API and sentiment analysis was performed on the data set using VADER. The gathered tweets were classified as either positive, negative or neutral. The data was collected, sorted and analyzed based on the CRISP-DM methodology. Tweets from two different time periods were studied. The two periods were 1) five months prior to the incident and 2) five months after the incident. The results showed that tweets posted before the incident were mostly positive, while tweets posted after the incident were mostly negative. An interesting discovery was found when comparing the sentiments exhibited within the five-month period directly following the incident. During the first month the results exhibited a predominance of negative sentiment regarding Log4j, while April 2022 on the contrary, was predominantly positive. In conclusion this study has presented the results of the attitudes a large group of Twitter users have expressed towards Log4j and how these attitudes have evolved over time. A gap in related research of how the discussions on social media circulate when a security threat with great impact appears has been identified and this study aims to provide new insights within this area.