Advanced risk assessment using machine learning and sentiment analysis on log data

Aug 5, 2026

Advanced risk assessment is addressed by combining sentiment analysis with machine learning on log data to reduce subjectivity and processing effort. The method automates data collection and improves the effectiveness, precision, and coverage of risk insights by detecting feelings expressed in logs. Multiple ML classifiers are evaluated, and a pre-trained deep learning model is applied to handle multilinguistic logs. Results highlight adaptability and scalability in multilingual settings, enabling real-time processing and actionable organizational risk management compared with traditional approaches.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Role of log data in auditing and security

Conventional cybersecurity risk assessment approaches

NLP and sentiment analysis for log-based risk evaluation

Related work

Advanced risk assessment using machine learning and sentiment analysis on log data Nidal Turab1, Abdelrahman Abushattal1, Jamal Al-Nabulsi2, Hamza Abu Owida2 1Department of Networks and Cyber Security, Faculty of Information Technology, Al-Ahliyya Amman University, Amman, Jordan 2Department of Medical Engineering, Faculty of Engineering, Al-Ahliyya Amman University, Amman, Jordan Article history: Received Sep 8, 2024 Revised Jul 5, 2025 Accepted Aug 6, 2025 Keywords: K-nearest neighbors Natural language processing Sentiment analysis Risk assessment Support machines Corresponding Author: Standard risk assessment approaches are sometimes time-consuming and subjective. In order to overcome these challenges an innovative method will be presented in this article by mixing sentiment analysis and machine learning (ML) . The suggested technique improves the effectiveness, precision, and scope of risk insights when it comes to the detection of feelings in logs via the use of automated data collection. The research examines several different ML classifiers and makes use of a deep learning model that has been pre-trained to evaluate risks in logs that are multilinguistic. This proves the adaptability and scalability of our technique when used in a multilanguage setting. This combination of sentiment analysis and ML are a significant advancement in comparison to traditional approaches since it enables real-time processing and delivers important insights into the management of organizational risks. This is an open access article under the CC BY-SA license. Nidal Turab Department of Networks and Cyber Security, Faculty of Information Technology Al-Ahliyya Amman University Amman 19328, Jordan [Email: n.turab@ammanu.edu.jo](Email: n.turab@ammanu.edu.jo) Article Info ABSTRACT 1. INTRODUCTION Data logs are essential documentation of computer systems or network events that provide an audit trail for assessing and addressing problems. Logs play a vital role in various functions such as audit and compliance to ensure compliance with regulations. They also aid in troubleshooting by providing detailed information to find the root causes of failures [1] . In addition, logs are used for security monitoring to detect suspicious activities and potential breaches [2] . Furthermore, logs are valuable for performance analysis, helping to understand system performance and find areas that need improvement. Logs are essential instruments for preserving integrity and perfecting the performance of technological infrastructures due to their diverse nature [3] . Within the landscape of cyber security, risk assessment is quite an important piece to ensure crucial information is secured and the IT information systems are fully functional and available [4] . Several conventional risk techniques are related to cybersecurity. Expert-based risk assessment (EBRA) uses experts’knowledge to evaluate, prioritize, and define the risks that the system has. However, it is susceptible to biases and contradictions [5] . Compliance-based risk assessment (CBRA) defines the risks by guaranteeing compliance with regulations like the health insurance portability and accountability act (HIPAA) but lacks flexibility for dynamic threats [6] . Red team/blue team exercises (RTBTE) decide risk in cases with attackers (red team) versus defenders (blue team) [7]; however, it is time-consuming for data collection and pre-and post-participation status characterization [7] . Artificial intelligence (AI) has proven to be a valuable tool in evaluating the cybersecurity risks ranging from AI-based attacks to deepfake videos [8] . The speech’s most potential application is use of natural language processing (NLP), which allows one to retrieve important data from written documents. NLP can help to increase the efficiency of cybersecurity risk assessment by transforming unstructured data into structured and useful information [9] . Event log data is often rich i

FAQs

Why combine sentiment analysis with machine learning for risk assessment on log data?

Standard risk assessment can be time-consuming and subjective, so the approach automates processing and extracts sentiment signals from logs to improve risk insight quality and timeliness.

How is sentiment analysis applied in this work?

Sentiment analysis evaluates attitudes expressed in words, phrases, or longer text passages to determine whether the sentiment is good, negative, or neutral, supporting automated risk evaluation.

What models and evaluation strategy are used for the proposed technique?

Several machine learning classifiers are examined, and a deep learning model pre-trained to process multilinguistic logs is employed to assess risks in multilingual log settings.

Aug 5, 2026

Upload by Clementine