Public
sector
Media
Judiciary

Perspective API

Media Country or Region United States of America
Sourced From
Partnership on AI: AI Tools for Local Newsrooms Database International Media Support (2021) 'The next wave of disruption: Emerging market media use of artificial intelligence and machine learning'. Available at: https://www.mediasupport.org/wp-content/uploads/2021/07/AI-ML-in-Emerging-Markets-vFinal4.pdf (Accessed March 2025).
Perspective API employs machine learning algorithms to evaluate and flag harmful or toxic language in online conversations. By assessing various attributes, such as offensive language, personal attacks, and explicit content, it generates a score that reflects the potential negative impact of a comment. This tool is primarily used to automate and streamline the moderation process, helping platforms ensure healthier, more respectful discussions.
Distribution and Audience Engagement

AI-powered content personalization (e.g. personalized trailers, thumbnails, hyper-personalized content) Optimized distribution and scheduling, such as automated A/B testing Audience analytics and audience sentiment analysis Interaction with audiences, such as comment moderation on media’s online platforms, generating standard replies, processing feedback AI-powered tools that enable user/audience empowerment (for instance to understand why they see such content, to decide on the algo, to enable flagging of problematic content).

#automate Automate the moderation process to quickly detect and filter harmful or abusive content. Streamline online interactions by automatically identifying and blocking inappropriate language in real time.
#detect Detect toxic or harmful content by analyzing text for offensive words and phrases. Use machine learning to recognize and flag harmful comments with high accuracy, reducing manual review efforts.
#monitor Monitor conversations and comments across digital platforms to ensure a safe environment. Track discussions for potentially harmful language and take necessary actions based on the severity of content.
Developed by
Private Sector
Deployment Type
Cloud-Based AI Service & API
Community Moderation
Requires community manager
Difficulty Level
Requires developer
License
Proprietary
Back to all
With the support of

User Guide

© IRCAI and UNESCO

The designations used and the presentation of materials throughout this repository do not imply the expression of any opinion on the part of UNESCO and IRCAI concerning the legal status of any country, territory, city or area, or of its authorities, or concerning the delimitation of its frontiers or boundaries. The ideas, opinions, and content presented in this repository are those of the authors; they do not necessarily represent the views of UNESCO and IRCAI and do not commit the Organizations.