In this repository we include a package with the latest version of the deep learning model implemented in this work which can be used by anyone who wants to detect inappropriate videos for kids on YouTube. (see https://ojs.aaai.org/index.php/ICWSM/article/view/7320/7174 for the detailed description on the results). Codebase also available on Github. Please appropriately cite the "Disturbed YouTube For Kids: Characterizing And Detecting Inappropriate Videos Targeting Young Children" paper in any publication, of any form and kind, using this software: @inproceedings{papadamou2020disturbedyoutube, title= {{Disturbed YouTube for Kids: Characterizing and Detecting Inappropriate Videos Targeting Young Children}}, author={Papadamou, Kostantinos and Papasavva, Antonis and Zannettou, Savvas and Blackburn, Jeremy and Kourtellis, Nicolas and Leontiadis, Ilias and Stringhini, Gianluca and Sirivianos, Michael}, booktitle={14th International AAAI Conference on Web and Social Media}, year={2020}, organization={AAAI} }

Acknowledgments: This project has received funding from the European Union's Horizon 2020 Research and Innovation program under the Marie Skłodowska-Curie ENCASE project (Grant Agreement No. 691025) and from the National Science Foundation under grant CNS-1942610.