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

TL;DR

This paper introduces SexTok, a multi-modal dataset for classifying TikTok videos as sexually suggestive, sex-educational, or neutral, aiming to improve content moderation and understanding of such videos.

Contribution

The creation of SexTok, a labeled dataset with video URLs and transcriptions, and the evaluation of transformer models for distinguishing different types of TikTok videos.

Findings

Distinguishing suggestive from educational videos is feasible but challenging.

Transformer models show promise in classifying video content.

The dataset supports further research in content moderation and education.

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.