M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, et al. Tensorflow: a system for large-scale machine learning. In OSDI, 2016.
 S. Agarwal and A. Sureka. A focused crawler for mining hate and extremism promoting videos on youtube. In ACM Hypertext, 2014. [OpenAIRE]
 N. Aggarwal, S. Agrawal, and A. Sureka. Mining youtube metadata for detecting privacy invading harassment and misdemeanor videos. In IEEE PST, 2014. [OpenAIRE]
 T. C. Alberto, J. V. Lochter, and T. A. Almeida. Tubespam: Comment spam filtering on youtube. In IEEE ICMLA, 2015. [OpenAIRE]
 C. S. Arau´ jo, G. Magno, W. Meira, V. Almeida, P. Hartung, and D. Doneda. Characterizing videos, audience and advertising in youtube channels for kids. In SocInfo, 2017.
 F. Benevenuto, T. Rodrigues, A. Veloso, J. Almeida, M. Gonc¸alves, and V. Almeida. Practical detection of spammers and content promoters in online video sharing systems. IEEE Cybernetics, 2012.
 R. Brandom. Inside elsagate, the conspiracyfueled war on creepy youtube kids videos. https://www.theverge.com/2017/12/8/16751206/elsagateyoutube-kids-creepy-conspiracy-theory, 2017.
 V. Bulakh, C. W. Dunn, and M. Gupta. Identifying fraudulently promoted online videos. In WWW, 2014. [OpenAIRE]
 M. Buzzi. Children and youtube: access to safe content. In ACM SIGCHI, 2011.
 V. Chaudhary and A. Sureka. Contextual feature based oneclass classifier approach for detecting video response spam on youtube. In IEEE PST, 2013.
A large number of the most-subscribed YouTube channels target children of a very young age. Hundreds of toddler-oriented channels on YouTube feature inoffensive, well-produced, and educational videos. Unfortunately, inappropriate content that targets this demographic is also common. YouTube's algorithmic recommendation system regrettably suggests inappropriate content because some of it mimics or is derived from otherwise appropriate content. Considering the risk for early childhood development, and an increasing trend in toddler's consumption of YouTube media, this is a worrisome problem. In this work, we build a classifier able to discern inappropriate content that targets toddlers on YouTube with 84.3% accuracy, and leverage it to perform a first-of-its-kind, large-scale, quantitative characterization that reveals some of the risks of YouTube media consumption by young children. Our analysis reveals that YouTube is still plagued by such disturbing videos and its currently deployed counter-measures are ineffective in terms of detecting them in a timely manner. Alarmingly, using our classifier we show that young children are not only able, but likely to encounter disturbing videos when they randomly browse the platform starting from benign videos.
Published at the 14th International Conference on Web and Social Media (ICWSM 2020). Please cite the ICWSM version