A Study on Methods for Summarizing Information from YouTube Channels
Abstract
This study explored the possibility of summarizing information from YouTube channels. To achieve this, the research compared and analyzed speech-to-text (STT) data from top-viewed videos and comment data from recent videos. The keyword network analysis revealed that comment data could represent the main content of the videos, thereby validating the feasibility of information summarization using only comments.
To enhance the reliability of the study, text similarity analysis and statistical verification were conducted. The results of this research are expected to contribute to the utilization of influencer marketing by businesses and to help individual subscribers quickly grasp the main content of channels. Furthermore, it is anticipated that this study will make a practical contribution to the development of efficient processing and analysis methodologies for digital media data.
References
- Kim, J. Y. (2023). "Enhancing Abstract Summarization through Triplet loss." Master's Thesis, Graduate School of Computer and Information Technology, Korea University, Seoul.
- Lee, J. W., Kim, T. H., Shin, D. G., & Cho, W. S. (2022). Korean Information Summarization System for Summarizing National R&D Project Information. Journal of the Korea Institute of Information and Communication Engineering, Jeju.
- Jung, J. I. (2016). "Improved Tag Search System through Keyword Extraction and Similarity Evaluation." Master's Thesis, Soongsil University, Seoul.
- Baek, S. H., & Kim, E. J. (2021). Research Trends of Korean Elderly Exercise through Keyword Network Analysis (1995-2019). Journal of the Korea Convergence Society, 19(1).
- Nam, H. J., & Hong, D. S. (2023). A Study on Keyword Network Analysis for Exploring Research Trends Related to Sports Injuries. Korean Journal of Sports Science, 32(6), 755-766. https://doi.org/10.35159/kjss.2023.12.32.6.755
- Kim, G. Y. (2019). Analysis of Tourist Destination Network Characteristics through Two-Mode Network Analysis - Focusing on Japanese Tourists Visiting Korea. Journal of Tourism Research, 31(4), 23-46. https://doi.org/10.21581/jts.2019.11.31.4.23
- Yoo, J. Y., & Kim, M. K. (2019). Convergence of Korean Traditional Dance and K-pop Dance: Analysis of YouTube Comments on BTS's 'IDOL' at 2018 MMA. Journal of Korea Entertainment Industry Association, 13(8), 189-198. https://doi.org/10.21184/jkeia.2019.12.13.8.189
- Lavish Mangal, Dhruv Aggarwal, Gulshan Kumar, Jai Kumar, Meenakshi Aggarwal. (2022). YouTube Transcript Summarizer. 2022 International Mobile and Embedded Technology Conference (MECON)
- J. H. Shin, E. H. Kim, and M. J. Lim, “Improving the effectiveness of document extraction summary based on the amount of sentence information,” Smart media journal, Vol. 11, No. 3, pp. 31-38, Apr. 2022.
- Mohamed, Fatma, and Abdulhadi Shoufan. (2024). Users’ experience with health-related content on YouTube: an exploratory study. BMC Public Health, 24:86.
- Sulochana Devi, Rahul Nadar, Tejas Nichat, and Alfredprem Lucas. (2023). Abstractive Summarizer for YouTube Videos. In Proceedings of the International Conference on Applied Mathematics, Intelligent Systems and Computing Applications (ICAMIDA), vol. 105, pp. 431-438.
- Kaiyang Zhou, Yu Qiao, and Tao Xiang. (2018). Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).
Keywords
Details
| Section | Articles |
| Issue | Vol. 1 No. 1 (2024): Volume 1 Issue 1 (Inaugural Issue) |
| Published | 2024-11-15 |
| Pages | 5-13 |
EDUCATION
- Master of Engineering in AI Big Data
- Department of Advanced AI, Graduate School of AI
- aSSIST (Seoul School of Integrated Sciences & Technologies)
RESEARCH INTERESTS
- Artificial Intelligence
- Natural Language Processing
- Large Language Models (LLMs)
- And related fields
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.