, , , ,
TikTok has become a popular platform, especially among younger audiences, due to its viral trends and social challenges. However, concerns have been raised about the potential for harmful and dangerous content to spread on the platform. A study utilizing the TikTok Research API collected a dataset of 1.5 million videos shared in the US over three years to analyze the presence of conspiracy theories. The study found that approximately 0.1% of all videos contained conspiracy content. The research also evaluated the impact of TikTok's Creator Program on the supply of conspiratorial content. State-of-the-art Large Language Models were used to identify harmful content in audio transcriptions with high precision, although overall performance was comparable to traditional language models like RoBERTa. The findings have significant implications for researchers and social media platforms, providing insights into developing more effective moderation strategies and policies to combat malicious content. The study also sheds light on how platform policies influence content creation trends. Limitations include potential biases in data returned by the TikTok Research API and uncertainties associated with using Large Language Models. Future research aims to address these limitations by integrating multi-modal data in classification pipelines and exploring other online media platforms. Ethical considerations were taken into account throughout the study, with measures implemented to protect user privacy and ensure data security aligns with best practices. While the dataset is not publicly available, readers can contact the authors for access to code for replication purposes. In conclusion, this study highlights the importance of understanding and mitigating harmful content on social media platforms like TikTok through advanced technologies and strategic moderation approaches.
Summary- TikTok is a popular app that many young people like because of fun challenges and trends.
- Some people worry that there might be bad or unsafe things on TikTok.
- A study looked at lots of videos on TikTok and found only a very small number had conspiracy content.
- Smart computer programs were used to find bad content on TikTok, but they weren't much better than older methods.
- The study shows we need better ways to keep social media safe from harmful content.
Definitions
- Popular: Liked by many people
- Challenges: Fun activities or tasks
- Worry: Feel concerned or anxious about something
- Conspiracy: Believing in secret plans made by powerful groups
- Content: Information or material shared online
TikTok Research Paper: Analyzing the Presence of Conspiracy Theories on the Popular Social Media Platform
TikTok has taken the world by storm, with its short-form videos and viral trends capturing the attention of millions of users, especially among younger audiences. However, as with any social media platform, concerns have been raised about the potential for harmful and dangerous content to spread on TikTok. In response to these concerns, a recent research paper utilized the TikTok Research API to collect a dataset of 1.5 million videos shared in the US over three years to analyze the presence of conspiracy theories.
The Study
The study found that approximately 0.1% of all videos on TikTok contained conspiracy content. While this may seem like a small percentage, it still represents a significant number given the vast amount of content shared on the platform daily. Additionally, researchers evaluated how TikTok's Creator Program impacted the supply of conspiratorial content.
To identify harmful content in audio transcriptions accurately, state-of-the-art Large Language Models were used in this study. These models showed high precision in identifying malicious content; however, overall performance was comparable to traditional language models like RoBERTa.
Implications for Researchers and Social Media Platforms
The findings from this study have significant implications for both researchers and social media platforms alike. For researchers studying online behavior and trends, this research provides valuable insights into understanding how conspiracy theories are present on popular platforms like TikTok.
For social media platforms themselves, these findings highlight the importance of developing more effective moderation strategies and policies to combat malicious content effectively. By understanding how conspiratorial content is created and shared on their platform through advanced technologies like Large Language Models, platforms can take proactive steps towards mitigating harm caused by such content.
Limitations and Future Directions
As with any research study, there are limitations that must be taken into consideration. One potential limitation is the biases in data returned by the TikTok Research API. Additionally, uncertainties may arise from using Large Language Models for content classification.
To address these limitations, future research aims to integrate multi-modal data in classification pipelines and explore other online media platforms beyond TikTok. By incorporating different types of data and expanding the scope of research, a more comprehensive understanding of harmful content on social media can be achieved.
Ethical Considerations
Throughout this study, ethical considerations were taken into account to protect user privacy and ensure data security aligns with best practices. While the dataset used in this study is not publicly available, readers can contact the authors for access to code for replication purposes.
Conclusion
In conclusion, this research paper sheds light on the presence of conspiracy theories on TikTok and how platform policies influence content creation trends. It highlights the importance of understanding and mitigating harmful content on social media platforms through advanced technologies like Large Language Models and strategic moderation approaches. As technology continues to evolve, it is crucial for researchers and social media platforms to work together towards creating a safer online environment for all users.
TikTok has skyrocketed in popularity over recent years, especially among younger audiences, thanks to its viral trends and social challenges. However, concerns have been raised about the potential of this platform to promote and amplify online harmful and dangerous content. Leveraging the official TikTok Research API and collecting a longitudinal dataset of 1.5M videos shared in the US over a period of 3 years, our study analyzes the presence of videos promoting conspiracy theories, providing a lower-bound estimate of their prevalence (approximately 0.1% of all videos) and assessing the effects of the new Creator Program, which provides new ways for creators to monetize, on the supply of conspiratorial content. We evaluate the capabilities of state-of-the-art open Large Language Models to identify conspiracy theories after extracting audio transcriptions of videos, finding that they can detect harmful content with high precision but with overall performance comparable to fine-tuned traditional language models such as RoBERTa. Our findings are instrumental for content moderation strategies that aim to understand and mitigate the spread of harmful content on rapidly evolving social media platforms like TikTok.
