Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

It is not Sexually Suggestive, It is Educative. Separating Sex Education from Suggestive Content on TikTok Videos (2307.03274v1)

Published 6 Jul 2023 in cs.CV, cs.AI, and cs.CL

Abstract: We introduce SexTok, a multi-modal dataset composed of TikTok videos labeled as sexually suggestive (from the annotator's point of view), sex-educational content, or neither. Such a dataset is necessary to address the challenge of distinguishing between sexually suggestive content and virtual sex education videos on TikTok. Children's exposure to sexually suggestive videos has been shown to have adversarial effects on their development. Meanwhile, virtual sex education, especially on subjects that are more relevant to the LGBTQIA+ community, is very valuable. The platform's current system removes or penalizes some of both types of videos, even though they serve different purposes. Our dataset contains video URLs, and it is also audio transcribed. To validate its importance, we explore two transformer-based models for classifying the videos. Our preliminary results suggest that the task of distinguishing between these types of videos is learnable but challenging. These experiments suggest that this dataset is meaningful and invites further study on the subject.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (27)
  1. American Psychological Association. 2015. Guidelines for psychological practice with transgender and gender nonconforming people. American psychologist, 70(9):832–864.
  2. A survey of artificial intelligence strategies for automatic detection of sexually explicit videos. Multimedia Tools and Applications, 81(3):3205–3222.
  3. Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement, 20(1):37–46.
  4. Sexual media and childhood well-being and health. Pediatrics, 140(Supplement_2):S162–S166.
  5. Bag-of-visual-words models for adult image classification and filtering. In 2008 19th International Conference on Pattern Recognition, pages 1–4. IEEE.
  6. BERT: pre-training of deep bidirectional transformers for language understanding. CoRR, abs/1810.04805.
  7. Finding naked people. In Computer Vision—ECCV’96: 4th European Conference on Computer Vision Cambridge, UK, April 15–18, 1996 Proceedings Volume II 4, pages 593–602. Springer.
  8. Let’s tok about sex. Journal of Adolescent Health, 69(5):687–688.
  9. Sex education on tiktok: a content analysis of themes. Health promotion practice, 23(5):739–742.
  10. Detecting sexually provocative images. In 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 660–668. IEEE.
  11. A pornographic image and video filtering application using optimized nudity recognition and detection algorithm. In 2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), pages 1–5. IEEE.
  12. Implementation of high performance objectionable video classification system. In 2006 8th International Conference Advanced Communication Technology, volume 2, pages 4–pp. IEEE.
  13. A bag-of-features approach based on hue-sift descriptor for nude detection. In 2009 17th European Signal Processing Conference, pages 1552–1556. IEEE.
  14. Gender artifacts in visual datasets. arXiv preprint arXiv:2206.09191.
  15. Accessing sexual health information online: use, motivations and consequences for youth with different sexual orientations. Health education research, 29(1):147–157.
  16. Jonathan Peters. 2020. Sexual content and social media moderation. Washburn LJ, 59:469.
  17. Charles Pierse. 2021. Transformers Interpret.
  18. Skin sheriff: a machine learning solution for detecting explicit images. In Proceedings of the 2nd international workshop on Security and forensics in communication systems, pages 45–56.
  19. Robust speech recognition via large-scale weak supervision. arXiv preprint arXiv:2212.04356.
  20. Multimodal periodicity analysis for illicit content detection in videos. In The 3rd European Conference on Visual Media Production (CVMP 2006) - Part of the 2nd Multimedia Conference 2006, pages 106–114.
  21. Randal W Summers. 2016. Social Psychology: How Other People Influence Our Thoughts and Actions [2 volumes]. ABC-CLIO.
  22. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. arXiv preprint arXiv:2203.12602.
  23. Adrian Ulges and Armin Stahl. 2011. Automatic detection of child pornography using color visual words. In 2011 IEEE international conference on multimedia and expo, pages 1–6. IEEE.
  24. Identification and annotation of erotic film based on content analysis. In Electronic Imaging and Multimedia Technology IV, volume 5637, pages 88–94. SPIE.
  25. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38–45, Online. Association for Computational Linguistics.
  26. An approach of bag-of-words based on visual attention model for pornographic images recognition in compressed domain. Neurocomputing, 110:145–152.
  27. Recognition of blue movies by fusion of audio and video. In 2008 IEEE International Conference on Multimedia and Expo, pages 37–40. IEEE.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now