tencent cloud

Challenges in Content Moderation

With the rapid development of the internet, smart devices, and various emerging businesses, internet data has been growing explosively and is subject to diverse uncontrollable risks, such as pornographic text, terrorism content, and spam ads.

With ever heightened regulation, content involving violence, blood, porn, gambling, and drug use has become an area of focus, which makes content moderation an urgent need of short video, news, and live streaming platforms.

As common violent, ironic, and suggestive content in text are difficult and costly to recognize and moderate through traditional means, enterprises face new technical challenges in content operations.

TMS Overview

Tencent Cloud Text Moderation System (TMS) is a smart text recognition service for moderating the text uploaded by users. It delivers a high recognition accuracy and recall rate, meets the needs for content moderation in multiple dimensions, and has been constantly improved in its recognition standards and capabilities in response to the changing regulatory requirements.

• It can detect various scenes in text and accurately recognize content that may be offensive, unsafe, or inappropriate, which effectively reduces the risks of non-compliant content and moderation costs.
• It can accurately recognize content that involves porn, terrorism, and violence and allows you to configure dictionaries to filter custom non-compliant text. It can also determine the risk level of content. Specifically, it directly filters non-compliant content and submits suspicious content for human review, so as to reduce the labor costs and business risks.
• It provides services in the form of open APIs. You can call them to get moderation results and efficiently create a smart business system to increase the efficiency of business operations.