# News Bias Detector News articles often suffer from bias and manipulation, making it hard to find objective reporting. This service is designed to detect bias in news articles and ensure that you can rely on more credible information. **Service Description:** Each submitted news article is analyzed and given a bias score from 0 (extremely biased) to 1 (non-biased). Our 2nd version is currently online, which we have converted to the LLM from OpenAI. The advantage of LLM over NLP models in this case is that subliminal biases in particular are better recognised. With this update, in addition to the bias score, there is also an explanation of how the score is determined. The following reference scores can be used to interpret the output values: * 0.0 - 0.6 = highly biased * 0.7 - 0.8 = moderately biased * 0.9 - 1.0 = not biased **How to use it:** This service is published and available on SingularityNET's AI marketplace. To use this service, you need to create an account and connect your MetaMask Wallet with the portal. Everyone has the opportunity to request 3 free demo analyses. After that they only cost 0.1 AGIX per call (currently around 0.05 USD) **Link to the services:** **Github Documentation:** {% embed url="" %} *If you are interested in using this services directly via our API, please contact us via * --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://trustlevel.gitbook.io/knowledge-base/tools-and-apps/news-bias-detector.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.