트윗 클러스터링을 통한 마약 조직 및 규모 식별 모델 개발
Development of a Model for Identifying Drug Organizations and Their Scale through Tweet Clustering
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문은 10대와 청년층에서 빈번하게 발생하는 마약 범죄를 수사하기 위해 소셜미디어 플랫폼 ‘X’에서마약 홍보 트윗을 수집하고, 이를 바탕으로 마약 유통 조직 및 규모를 식별하는 클러스터링 모델을 개발하는것을 목표로 한다. 최근 소셜미디어의 익명성을 악용한 마약, 불법 도박, 성범죄 등 다양한 사이버 범죄가증가하고 있으며, 특히 마약 유통 조직은 각 구성원이 자신의 역할에 대해서만 익명으로 지시를 받고, 다른 구성원들과 직접 연결되지 않은 점조직 형태로 운영되고 있다. 이러한 유형의 범죄를 추적하기위해 BERT(Bidirectional Encoder Representations from Transformers), GloVe(Global Vectors for Word Representation)와 같은 텍스트 임베딩 모델 및 K-means Clustering과 Spectral Clustering 등 다양한 클러스터링알고리즘을 활용하여 실험 시나리오를 설계하였다. 또한, 각 시나리오에서 도출된 클러스터링 결과를자카드 유사도(Jaccard Similarity) 및 전수조사 기반으로 검증하고, 모든 시나리오에서 동일한 마약 조직으로식별된 트윗 클러스터를 분석하여 사이버 수사 시, 추적 우선순위가 높은 계정을 식별한다.
Abstract
In this paper, we propose a model for identifying drug trafficking organizations and assessing their scale by collecting drug promotional tweets from the social media platform ‘X,’ with a focus on investigating drug crimes that frequently occur among teenagers and young adults. Recently, various cyber crimes, such as drug distribution, illegal gambling, and sex offense, have been on the rise, exploiting the anonymity provided by social media. Drug trafficking organizations, in particular, operate in a decentralized cell structure, where each member receives anonymous instructions regarding only their specific role and is not directly connected to other members. To track these types of crimes, we designed experimental scenarios using various clustering algorithms, such as K-means Clustering and Spectral Clustering, alongside text embedding models like BERT (Bidirectional Encoder Representations from Transformers) and GloVe (Global Vectors for Word Representation). Furthermore, the clustering results derived from each scenario are validated using Jaccard Similarity and a full-scale investigation. We then analyze tweet clusters identified as the same drug organization across all scenarios, prioritizing the identification of high-priority accounts for cyber investigations.
참고문헌 (32)
- "Digital 2024 Global Overview Report"[URL]
- [URL]
- "Drugs Smuggled Overseas, Sold via Cryptocurrency and SNS... Organization Arrested (Comprehensive)"[URL]
- "70 Arrested for Distributing Drugs Nationwide via Telegram"[URL]
- "Undercover Investigations in Drug Crimes Like in ‘New World"[URL]
- E. Choi, "A Study on the Comparison and Semantic Analysis between SNS Big Data, Search Portal Trends and Drug Case Statistics", Journal of Digital Convergence, 19(2), pp.231~238 (2021)[DOI]
- S. Degadwala, "Location-Based Modelling And Analysis Of Threats By Using Text Mining", 2021 Second International Conference on Electronics and Sustainable Communication Systems(ICESC), pp.1940~1944 (2021)
- D. Petrou, "Twitter Account Analysis for Drug Involvement Detection", 20233rd Intelligent Cybersecurity Conference(ICSC), pp.9~16 (2023)
- F. Zhao, "Computational Approaches to Detect Illicit Drug Ads and Find Vendor Communities Within Social Media Platforms", IEEE, 2022, pp.19(1), 180~191
- C. Hu, "Detection of Illicit Drug Trafficking Events on Instagram : A Deep Multimodal Multilabel Learning Approach", Proceedings of the 30th ACM International Conference on Information and Knowledge Management(CIKM '21), pp.3838~3846 (2021)
- "Unveiling the Potential of Knowledge-Prompted ChatGPT for Enhancing Drug Trafficking Detection on Social Media" (2023)[URL]
- T. Ma, "Hypergraph Contrastive Learning for Drug Trafficking Community Detection", 2023 IEEE International Conference on Data Mining (ICDM), pp.1205~1210 (2023)
- N. Shah, "Crime forecasting : a machine learning and computer vision approach to crime prediction and prevention", Visual Computing for Industry, Biomedicine, and Art, 4(9), pp.1~14 (2021)[DOI]
- Y. Wang, "The Relationship Between Social Media Data and Crime Rates in the United States", Social Media + Society, 5(1) (2019)[DOI]
- F. -C. Tsai, "Exploring drug-related crimes with social network analysis", Procedia Computer Science, 159, pp.1907~1917 (2019)[DOI]
- P. Siriaraya, "Witnessing Crime through Tweets : A Crime Investigation Tool based on Social Media", Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems(SIGSPATIAL '19), pp.568~571 (2019)
- E. -Y. Park, "A Tracking Method of Same Drug Sales Accounts through Similarity Analysis of Instagram Profiles and Posts", Journal of The Korea Society of Computer and Information, 29(2), pp.109~118 (2024)[DOI]
- H. J. Park, "A Study on Drug trading countermeasures via internet and sns", Journal of the Korea Information Assurance Society, 18(1), pp.93~102 (2018)
- H. -j. Song, "An Analysis of the Progress of Youth Drug Crimes Using Cryptocurrency", Korean Journal of Convergence Science, 12(11), pp.133~145 (2023)[DOI]
- F. M. Bianchi, "Spectral Clustering with Graph Neural Networks for Graph Pooling", Proceedings of the 37th International Conference on Machine Learning, 119, pp.874~883 (2020)
- Lee, Seul-ki, "Analysis of Question Types by Student Writers Using Clustering in Writing Using Generative Artificial Intelligence", The Journal of Korean Language and Literature Education, 84, pp.69~105 (2024)
- S. -Y. Ihm, "A Study on Clustering-based Color Extraction Method for Pill Classification", Journal of Big Data Service, 1(1), pp.79~84 (2023)[DOI]
- Inmook Lee, "Generating Travel Patterns of Public Transportation Users Using a k-means Clustering Based on Smart Card Data", Journal of the Korean Society for Railway, 23(3), pp.204~215 (2020)[DOI]
- D. -T. Vu, "Collision Risk Assessment by using Hierarchical Clustering Method and Real-time Data", Journal of the Korean Society of Marine Environment and Safety, 27(4), pp.483~491 (2021)[DOI]
- J. -H. Tak, "A Study on Road Link Vulnerability Assessment Based on Clustering Analysis for Disaster Situations", Journal of Korean ITS Society, 22(2), pp.29~43 (2023)[DOI]
- G. Hajela, "A Clustering Based Hotspot Identification Approach For Crime Prediction", Procedia Computer Science, 167, pp.1462~1470 (2020)[DOI]
- D. Y. Kim, "A Preliminary Study on the Application of Spatial Clustering Techniques for Crime Prediction", Proceedings of the Korean Society of Spatial Information Science Conference, 2020(6), pp.111~114 (2020)
- A. A. Alkhaibari, "Cluster analysis for reducing city crime rates", 2017 IEEE Long Island Systems, Applications and Technology Conference(LISAT), pp.1~6 (2017)
- "Community detection using spectral clustering on sparse geosocial data" (2012)[URL]
- K. Joseph, "Who Says What with Whom using Bi-Spectral Clustering to Organize and Analyze Social Media Protest Networks", DOI: 10.5117, 2020
- K-Means Clustering and Related Algorithms, "R. Tibshirani", Stanford University, ~ (2004)
- A Tutorial on Spectral Clustering, "U. von Luxburg", Max Planck Institute for Biological Cybernetics, ~, pp.Technical Report No. MPIK-TR-149 (2007)