@article{ART003212303},
author={Byuong-Chan Park and Lee, Jae Chung and Seok-Yoon Kim and Youngmo Kim},
title={An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model},
journal={Journal of Software Assessment and Valuation},
issn={2092-8114},
year={2025},
volume={21},
number={2},
pages={33-42}
TY - JOUR
AU - Byuong-Chan Park
AU - Lee, Jae Chung
AU - Seok-Yoon Kim
AU - Youngmo Kim
TI - An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model
JO - Journal of Software Assessment and Valuation
PY - 2025
VL - 21
IS - 2
PB - Korea Software Assessment and Valuation Society
SP - 33
EP - 42
SN - 2092-8114
AB - This paper proposes an automated method for detecting and collecting evidence of illegal OTT content distribution using a Large Language Model (LLM) and a Large Action Model (LAM). Traditional manual web crawling methods are limited in their ability to adapt to structural changes in websites and incur high maintenance costs. To address these issues, we design a fully automated system architecture encompassing web structure analysis, code generation, similarity-based judgment, and evidence preservation.
In the proposed method, the LLM analyzes the HTML structure of a website and generates code for information extraction, while the LAM executes the code to collect data. Additionally, the system incorporates Retrieval-Augmented Generation (RAG) to enhance semantic similarity comparison and includes a feedback loop that iteratively improves the results when confidence is low. This approach allows the system to flexibly adapt to various web structures and enhances the reliability and efficiency of evidence collection.
KW - Large Language Model(LLM);Large Action Model(LAM);Illegal Content Distribution;Web Structure Analysis;Automated Evidence Collection
DO -
UR -
ER -
Byuong-Chan Park, Lee, Jae Chung, Seok-Yoon Kim and Youngmo Kim. (2025). An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model. Journal of Software Assessment and Valuation, 21(2), 33-42.
Byuong-Chan Park, Lee, Jae Chung, Seok-Yoon Kim and Youngmo Kim. 2025, "An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model", Journal of Software Assessment and Valuation, vol.21, no.2 pp.33-42.
Byuong-Chan Park, Lee, Jae Chung, Seok-Yoon Kim, Youngmo Kim "An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model" Journal of Software Assessment and Valuation 21.2 pp.33-42 (2025) : 33.
Byuong-Chan Park, Lee, Jae Chung, Seok-Yoon Kim, Youngmo Kim. An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model. 2025; 21(2), 33-42.
Byuong-Chan Park, Lee, Jae Chung, Seok-Yoon Kim and Youngmo Kim. "An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model" Journal of Software Assessment and Valuation 21, no.2 (2025) : 33-42.
Byuong-Chan Park; Lee, Jae Chung; Seok-Yoon Kim; Youngmo Kim. An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model. Journal of Software Assessment and Valuation, 21(2), 33-42.
Byuong-Chan Park; Lee, Jae Chung; Seok-Yoon Kim; Youngmo Kim. An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model. Journal of Software Assessment and Valuation. 2025; 21(2) 33-42.
Byuong-Chan Park, Lee, Jae Chung, Seok-Yoon Kim, Youngmo Kim. An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model. 2025; 21(2), 33-42.
Byuong-Chan Park, Lee, Jae Chung, Seok-Yoon Kim and Youngmo Kim. "An Automated Method for Detecting and Collecting Evidence of Illegal OTT Content Distribution Using Large Language Model" Journal of Software Assessment and Valuation 21, no.2 (2025) : 33-42.
