Hybrid Autoencoder and NiaARM Framework for Flash Viral Detection on YouTube Shorts

Erlin Windia Ambarsari(1*), Mercy Hermawati(2), Dedin Fathudin(3),

(1) Universitas Indraprasta PGRI, DKI Jakarta
(2) Universitas Indraprasta PGRI, DKI Jakarta
(3) Universitas Pamulang, South Tangerang
(*) Corresponding Author

Abstract


YouTube Shorts has rapidly emerged as a dominant short-form video platform, yet small creator channels often experience an unusual viral phenomenon best described as flash viral—a sudden surge of views that peaks within 24 to 48 hours and then collapses almost as quickly. Detecting and explaining this pattern is challenging because traditional statistical detectors miss multivariate signatures, while classical Association Rule Mining (ARM) such as Apriori loses information through mandatory discretization. This study proposes a hybrid framework that combines a semi-supervised Deep Learning Autoencoder with Nature-Inspired Numerical Association Rule Mining (NiaARM) using Differential Evolution and Particle Swarm Optimization. The framework is validated on six temporal snapshots of the Indonesian Boburu YouTube Shorts channel, comprising 63 unique videos (42 active) collected between February 22 and March 19, 2026. Experimental results show that the Autoencoder achieves an F1-score of 0.667 with 100% recall, matching the best classical baseline (Z-Score) while providing learnable representational capacity for future scaling. NiaARM-PSO discovered 3,115 high-quality numerical association rules with a maximum lift of 63.00, compared to only 43 rules and a maximum lift of 2.52 obtained by Apriori, an improvement of approximately 25 times. Traffic source decomposition further revealed that 99.9% of viral views originated from external platforms rather than YouTube's recommendation system, indicating that flash viral on micro-channels is externally driven. This research contributes a methodological framework that simultaneously detects and explains flash viral phenomena in short-form video analytics

Keywords


Flash Viral Detection; YouTube Shorts; Deep Learning Autoencoder; Numerical Association Rule Mining; Nature-Inspired Optimization

Full Text:

PDF

References


C. Violot, T. Elmas, I. Bilogrevic, and M. Humbert, “Shorts vs. Regular Videos on YouTube: A Comparative Analysis of User Engagement and Content Creation Trends,” in Proceedings of the 16th ACM Web Science Conference, 2024, pp. 213–223. doi: 10.1145/3614419.3644023.

J. Q. Wang, “Investigating the Effectiveness of Short Form Media Advertisements Compared to Long Form Media Advertisements,” Advances in Economics, Management and Political Sciences, vol. 89, no. 1, pp. 98–103, Jun. 2024, doi: 10.54254/2754-1169/89/20231451.

R. Ramzan and S. Hashmat, “Short-Form Video Platforms and Their Impact on News Consumption & Civic Engagement: a Review,” International Journal of Social Sciences Bulletin, vol. 4, no. 2, pp. 474–491, Feb. 2026, doi: 10.5281/zenodo.18630606.

Boburu, "Boburu Official," YouTube. [Online]. Available: https://youtube.com/@boburuofficial. [Accessed: April 20, 2026].

A. S. Yaro, F. Maly, and P. Prazak, “Outlier Detection in Time-Series Receive Signal Strength Observation Using Z-Score Method with Sn Scale Estimator for Indoor Localization,” Applied Sciences, vol. 13, no. 6, p. 3900, Mar. 2023, doi: 10.3390/app13063900.

M. Hubert and E. Vandervieren, “An adjusted boxplot for skewed distributions,” Comput Stat Data Anal, vol. 52, no. 12, pp. 5186–5201, Aug. 2008, doi: 10.1016/j.csda.2007.11.008.

D. Alcan, K. Ozdemir, B. Ozkan, A. Y. Mucan, and T. Ozcan, “A Comparative Analysis of Apriori and FP-Growth Algorithms for Market Basket Analysis Using Multi-level Association Rule Mining,” in Industrial Engineering in the Covid-19 Era, F. Calisir and M. Durucu, Eds., Cham: Springer Nature Switzerland, 2023, pp. 128–137.

M. Kaushik, R. Sharma, S. A. Peious, M. Shahin, S. ben Yahia, and D. Draheim, “A Systematic Assessment of Numerical Association Rule Mining Methods,” SN Comput Sci, vol. 2, no. 5, p. 348, 2021, doi: 10.1007/s42979-021-00725-2.

G. Pang, C. Shen, L. Cao, and A. van den Hengel, “Deep Learning for Anomaly Detection,” ACM Comput Surv, vol. 54, no. 2, pp. 1–38, Mar. 2022, doi: 10.1145/3439950.

S. Givnan, C. Chalmers, P. Fergus, S. Ortega-Martorell, and T. Whalley, “Anomaly Detection Using Autoencoder Reconstruction upon Industrial Motors,” Sensors, vol. 22, no. 9, p. 3166, Apr. 2022, doi: 10.3390/s22093166.

B. X. Yong and A. Brintrup, “Do Autoencoders Need a Bottleneck for Anomaly Detection?,” IEEE Access, vol. 10, pp. 78455–78471, 2022, doi: 10.1109/ACCESS.2022.3192134.

Ž. Stupan and I. F. Jr., “NiaARM: A minimalistic framework for Numerical Association Rule Mining,” J Open Source Softw, vol. 7, no. 77, p. 4448, Sep. 2022, doi: 10.21105/joss.04448.

I. Fister, D. Fister, I. Fister, V. Podgorelec, and S. Salcedo-Sanz, “Time series numerical association rule mining variants in smart agriculture,” J Ambient Intell Humaniz Comput, vol. 14, no. 12, pp. 16853–16866, 2023, doi: 10.1007/s12652-023-04694-7.

S. Han, X. Hu, H. Huang, M. Jiang, and Y. Zhao, “ADBench: anomaly detection benchmark,” in Proceedings of the 36th International Conference on Neural Information Processing Systems, in NIPS ’22. Red Hook, NY, USA: Curran Associates Inc., 2022.

S. Zannettou et al., “Analyzing User Engagement with TikTok’s Short Format Video Recommendations using Data Donations,” in Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, in CHI ’24. New York, NY, USA: Association for Computing Machinery, 2024. doi: 10.1145/3613904.3642433.

S. Shajari and N. Agarwal, “Developing a network-centric approach for anomalous behavior detection on youtube,” Soc Netw Anal Min, vol. 15, no. 3, pp. 1–16, Mar. 2025, doi: 10.1007/s13278-025-01417-y.

S. Darrab et al., “Anomaly Detection Algorithms: Comparative Analysis and Explainability Perspectives,” in Data Science and Machine Learning, D. Benavides-Prado, S. Erfani, P. Fournier-Viger, Y. L. Boo, and Y. S. Koh, Eds., Singapore: Springer Nature Singapore, 2024, pp. 90–104.

Y. Kim and M. Vasarhelyi, “Anomaly detection with the density based spatial clustering of applications with noise (DBSCAN) to detect potentially fraudulent wire transfers,” The International Journal of Digital Accounting Research, vol. 24, pp. 57–91, 2024, doi: 10.4192/1577-8517-v24_3.

J. A. Diaz-Garcia, M. D. Ruiz, and M. J. Martin-Bautista, “A survey on the use of association rules mining techniques in textual social media,” Artif Intell Rev, vol. 56, pp. 1175–1200, 2023, doi: 10.1007/s10462-022-10196-3.

H. Xu, Q. Deng, Z. Zhang, and S. Lin, “A hybrid differential evolution particle swarm optimization algorithm based on dynamic strategies,” Sci Rep, vol. 15, 2025, doi: 10.1038/s41598-024-82648-5.

G. Vrbančič, L. Brezočnik, U. Mlakar, D. Fister, and I. Fister Jr., “NiaPy: Python microframework for building nature-inspired algorithms,” J Open Source Softw, vol. 3, no. 23, p. 613, Mar. 2018, doi: 10.21105/joss.00613.

M. Owusu-Adjei, J. ben Hayfron-Acquah, T. Frimpong, and G. Abdul-Salaam, “Imbalanced class distribution and performance evaluation metrics: A systematic review of prediction accuracy for determining model performance in healthcare systems,” PLOS Digital Health, vol. 2, no. 11, p. e0000290, Nov. 2023, doi: 10.1371/journal.pdig.0000290.

H. Xu, G. Pang, Y. Wang, and Y. Wang, “Deep Isolation Forest for Anomaly Detection,” IEEE Trans Knowl Data Eng, vol. 35, no. 12, pp. 12591–12604, 2023, doi: 10.1109/TKDE.2023.3270293.

Z. Zamanzadeh Darban, G. I. Webb, S. Pan, C. Aggarwal, and M. Salehi, “Deep Learning for Time Series Anomaly Detection: A Survey,” ACM Comput Surv, vol. 57, no. 1, pp. 1–42, Jan. 2025, doi: 10.1145/3691338.

S. Maleki, S. Maleki, and N. R. Jennings, “Unsupervised anomaly detection with LSTM autoencoders using statistical data-filtering,” Appl Soft Comput, vol. 108, p. 107443, 2021, doi: https://doi.org/10.1016/j.asoc.2021.107443.

A. Telikani, A. H. Gandomi, and A. Shahbahrami, “A survey of evolutionary computation for association rule mining,” Inf Sci (N Y), vol. 524, pp. 318–352, 2020, doi: https://doi.org/10.1016/j.ins.2020.02.073.

G. Li, T. Wang, Q. Chen, P. Shao, N. Xiong, and A. Vasilakos, “A Survey on Particle Swarm Optimization for Association Rule Mining,” Electronics (Basel), vol. 11, no. 19, p. 3044, Sep. 2022, doi: 10.3390/electronics11193044.

U. Mlakar, I. Fister, and I. Fister, “Variable-Length Differential Evolution for Numerical and Discrete Association Rule Mining,” IEEE Access, vol. 12, pp. 4239–4254, 2024, doi: 10.1109/ACCESS.2023.3348408.

U. Mlakar, I. Fister, and I. Fister, “NiaAutoARM: Automated Framework for Constructing and Evaluating Association Rule Mining Pipelines,” Mathematics, vol. 13, no. 12, p. 1957, Jun. 2025, doi: 10.3390/math13121957.

M. Kaushik, R. Sharma, I. Fister Jr., and D. Draheim, "Numerical Association Rule Mining: A Systematic Literature Review," arXiv preprint, arXiv:2307.00662, Jul. 2023, doi: 10.48550/arXiv.2307.00662.

S. Shajari, M. Alassad, and N. Agarwal, "Commenter Behavior Characterization on YouTube Channels," arXiv preprint, arXiv:2304.07681, Apr. 2023, doi: 10.48550/arXiv.2304.07681.

B. Kirdemir, O. Adeliyi, and N. Agarwal, "Towards Characterizing Coordinated Inauthentic Behaviors on YouTube," in Proc. 2nd Workshop on Reducing Online Misinformation through Credible Information Retrieval (ROMCIR 2022), co-located with ECIR 2022, CEUR Workshop Proceedings, vol. 3138, pp. 100–116, Apr. 2022.




DOI: http://dx.doi.org/10.61944/bids.v5i1.162

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Erlin Windia Ambarsari, Mercy Hermawati, Dedin Fathudin

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Bulletin of Informatics and Data Science
Asosiasi Peneliti Data Science Indonesia
Email: pdsi.bids@gmail.com
This work is licensed under a Creative Commons Attribution 4.0 International License.