Categories : All, Case Study, Web & Desktop Application
About Client
Swear filters are the need of the modern businesses looking to protect their brand image from expletive content.
Brainvire has come up with an amazing solution called UNAGI for these businesses so that they can practice profanity check on their brand content effortlessly and efficiently.
Unagi is a web application which evaluates the content, finds the words that are offensive and assigns a grade to the content according to the density of profanity words in it. The process can either happen automatically or manually with the efforts of a supervisor and a moderator.
The application automates profanity check in a given text or website content through API and can also operate manually for profanity check of images, audio and videos. The application uses a dictionary for performing content moderation process.
Business Challenges
Whether it is a chat room, an online video game or a blog, businesses need to take care of the fact that no obscene content gets promoted through their brand or else it can harm their brand image. Therefore, a profanity check needs to be implemented on the brand content before publishing it online.Rather, implementing the profanity check methods manually for large-scale necessities can be a daunting, time consuming and costly affair to practice. Hence, an automated content moderating solution is very much required to save costs, efforts and time of the businesses in managing their brand content.
Solution
Brainvire’s Unagi is a comprehensive profanity control system for the businesses looking to keep their brand content free from any sort of obscenity. It is a complete content profanity verification solution which will perform right from fetching and moderating the content using a predefined dictionary and providing feedback for each and every word or content that is rejected. The customers can submit their website URL or access our product API to submit the content for profanity check. They can either opt for automation or manual content verification process depending on their requirements and type of the content to be verified like text, audio, image or a video.
Features
- Automates filtering of profane words from particular websites through API
- Manual verification of images, audio and video for any profanity words or content in them through a moderator and supervisor
- Moderation of content on regular basis with an automated trigger functionality
- Profanity check supported for multiple languages
- Content moderation with a customized dictionary for every project
- Word specific grading to moderate the content based on a different calculation for specific age group (like content moderation for websites or content meant for adult or aged people, or content moderation for kids websites etc.)
- SaaS model to handle multiple projects and multiple clients
- User-role wise defined unique dashboards quick access to current entry status
- API integration allowed for easy data communication with 3rd party tools
Result
- Easy profanity verification and moderating of business website content
- Content in any language can be easily moderated
- Content moderation based on the age group of its readers
- Unique dashboard meant for different users
- Easy data communication through APIs