Sentiment Analysis in a Forensic Timeline With Deep Learning

Abstract

A forensic investigator creates a timeline from a forensic disk image after an occurrence of a security incident. This procedure aims to acquire the time for all events identified from the investigated artifacts. An investigator usually looks for events of interest by manually searching the timeline. One of the sources from which to build a timeline is log files, and these events are often found in log messages. In this paper, we propose a sentiment analysis technique to automatically extract events of interest from log messages in the forensic timeline. We use a deep learning technique with a context and content attention model to identify aspect terms and the corresponding sentiments in the forensic timeline. Terms with negative sentiments indicate events of interest and are highlighted in the timeline. Therefore, the investigator can quickly examine the events and other activities recorded within the surrounding time frame. Experimental results on four public forensic case studies show that the proposed method achieves 98.43% and 99.64% for the F1 score and accuracy, respectively.

Sentiment Analysis in Social Media Data for Depression Detection Using Artificial Intelligence: A Review

“…GloVe: GloVe [11,14,[41][42][43]53], a unsupervised learning algorithm by mapping words into a meaningful space for obtaining words vector representations where the semantic similarity is related to the distance between words.…”

Sentiment Analysis based Error Detection for Large-Scale Systems

“…Yadwad et al [38] applied machine learning and time series models (e.g., PCA, Naïve Bayes, logistic regression, and CNN) on combined data of the social tweets, mails and logs for service outage detection and predication. Based on the context and content attention model, Studiawan et al [39] employed a deep learning technique to identify aspect terms and the corresponding sentiments to extract events of interest from log files in the forensic timeline. By comparison, our work is the first attempt in the domain of a large-scale system.…”

SentiLog

“…SentiLog focuses on single log entry and builds sentimental model to analyze it. Some recent studies [46,47] also apply sentiment analysis in log-based anomaly detection. However, they perform both training and testing directly on the runtime logs which needs extensive efforts to label the logs.…”