Bibliographic Details
| Title: |
СИСТЕМА АВТОМАТИЗОВАНОГО АНАЛІЗУ ЦИФРОВОГО СЛІДУ КОРИСТУВАЧА В СОЦІАЛЬНИХ МЕДІА З ВИКОРИСТАННЯМ OSINT |
| Alternate Title: |
SYSTEM FOR AUTOMATED ANALYSIS OF USER DIGITAL FOOTPRINT IN SOCIAL MEDIA USING OSINT. |
| Authors: |
Власова, А. В.1, Назаров, В. О.1, Ярова, І. А.1, Кушніренко, Н. І.1 kushnirenko@op.edu.ua |
| Source: |
Informatics & Mathematical Methods in Simulation / Informatika ta Matematičnì Metodi v Modelûvannì. 2025, Vol. 15 Issue 4, p536-544. 9p. |
| Subjects: |
Digital footprint, Open source intelligence, Computer user identification, Acquisition of data, Ukrainian language, Information retrieval, Algorithms, Social media |
| Geographic Terms: |
Ukraine |
| Abstract: |
The article presents a system for automated analysis of user digital footprint in social media using Open Source Intelligence (OSINT) approaches adapted for the Ukrainian language. Growing user activity on social networks creates privacy risks through accumulation of personal information. The aim of the work is to create a specialized system for comprehensive analysis of user digital presence in Telegram and YouTube considering morphological features of Ukrainian language and cultural context. Analysis of existing social platform research methods revealed limitations when processing Ukrainian content, particularly insufficient recognition accuracy and absence of specialized linguistic models. The proposed system consists of three sequential algorithms: a data collection algorithm through Telegram and YouTube APIs, a comprehensive text content analysis algorithm using TF-IDF method for key term extraction and langdetect library for automatic language detection, and an integrated profile construction algorithm with heterogeneous data normalization based on textual, social, temporal, and behavioral components. Experimental validation on a sample of 100 users across different age categories demonstrated system accuracy of 73% for Ukrainian content with average processing time of 85-95 seconds per user. The highest accuracy was achieved in determining temporal activity patterns (87%) and social activity level (77%). Scientific novelty lies in creating a specialized system for Ukrainian language considering its morphological features, including integration of TF-IDF frequency analysis methods adapted for word forms specificity, development of Ukrainian internet slang dictionary with over 800 entries, and construction of a comprehensive digital profile model based on four components. [ABSTRACT FROM AUTHOR] |
|
Copyright of Informatics & Mathematical Methods in Simulation / Informatika ta Matematičnì Metodi v Modelûvannì is the property of Odessa Polytechnic University and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |
