Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Bulletin of Computer Science and Electrical Engineering (BCSEE)
Agus Pamuji
Department of Islamic Counseling Guidance, Islamic State Religion Institute Sheikh Nurjati Cirebon, Indonesia
Computer Science & IT Electrical & Electronics Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Investigation of the Dark Web Illegal Activities using Data Mining Approach Agus Pamuji
Bulletin of Computer Science and Electrical Engineering Vol. 4 No. 1 (2023): June 2023 - Bulletin of Computer Science and Electrical Engineering
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25008/bcsee.v4i1.1179

Abstract

The rapid advancements in internet technology have opened up various avenues for illicit activities targeting users. These nefarious activities are carried out by anonymous individuals or groups, making identification and tracking a challenging task. Periodical updates to the content of the dark web are common, with alterations to concealed data often escaping detection. Consequently, the primary arduous tasks concerned the data mining framework and its impact on the classification accuracy with regards to illegal activities. In contemporary times, the constraint of dealing with considerations pertaining to the academia and the business environment has emerged as a crucial phenomenon. This paper encompasses an analysis of a web crawler designed for the dark web. The crawler is proficient not only in data collection and cleansing but also in storage, making use of a data-driven approach. Data mining is a potent technique that enables thorough investigation through exhaustive exploration of data, often revealing evidence of illicit activity. Consequently, the crawler has emerged as a focal point for enforcing automated classification of the amassed web pages into five distinct categories. The classification process involved the utilization of classifiers, specifically the Linear Support Vector Classifier (SVC) and Naïve Bayes (NB) for the categorization of pages. Furthermore, as per the probationary findings, the Support Vector Classifier (SVC) and the Naive Bayes (NB) algorithm demonstrated precision rates of 91% and 84%, respectively, in the presented sequence.
Co-Authors