Home / TransparencIA
Private Sector
Stage 1, Stage 2

TransparencIA

AIR Institute (Fundación Instituto Internacional de Investigación en Inteligencia Artificial y Ciencias de la Computación)
‹ Back to Open Call Winners
TransparencIA is an explainable AI system that assesses the quality of news articles in near real time. From a URL, it scores each article on eight journalistic criteria (timeliness, style, ethics, accuracy, headline, depth, sources and impartiality), flags clickbait, estimates political orientation as a separate label and explains every score in plain language. Articles above a documented threshold receive a Quality Seal.

Background

Europe’s information space is flooded with low-quality, misleading and clickbait content. The Digital Services Act, the European Media Freedom Act and the AI Act now push platforms, media and regulators to assess content quality in a way that is transparent, auditable and sovereign. Manual assessment does not scale: an expert needs about an hour per article, so a team can review roughly eight a day. Existing tools tend to give opaque scores or check single claims, without explaining the overall quality of a piece. Newsrooms, fact-checkers and media monitors need explainable quality indicators they can defend in front of their audiences.

Proposed solution

TransparencIA receives an article as a URL, extracts its text and metadata, and runs it through an LLM-based pipeline that applies a journalistic quality rubric. It returns a composite quality score, a rationale for each of the eight criteria, a clickbait flag, a political-orientation label and a natural-language justification. Political orientation is kept out of the Quality Seal, so it never affects certification, and every assessment is stored with its evidence so any score can be audited and reproduced. The system is human-in-the-loop: it supports editors and fact-checkers and takes no editorial decisions on its own. Results are delivered through a web portal, a REST API with OpenAPI documentation and publishing on Telegram, X and Bluesky. A ten-month public deployment (October 2024 to August 2025) analysed more than 3 thousand real articles from different Spanish media outlets (TRL 7), and the system is now being extended to English-language press. The containerised stack is being split into five AI Builder modules (extraction, clickbait, quality, bias and sources) that other AIoD providers can reuse.

Objectives

  • Assess the journalistic quality of news articles automatically, with an explainable 8-criteria score and a written justification for each one.
  • Detect clickbait headlines and editorial bias, making them visible to readers and editors.
  • Issue a verifiable Quality Seal that strengthens readers’ trust in the media.
  • Provide media outlets, fact-checkers and compliance teams with auditable evidence for EU transparency obligations (DSA, EMFA).
  • Deliver an open, containerised solution integrated with the AIoD platform and European language models.

AIR Institute (Fundación Instituto Internacional de Investigación en Inteligencia Artificial y Ciencias de la Computación)

Spain
AIR Institute is a private non-profit research organisation founded in 2018 in Salamanca, Spain, and recognised as a National Technological Centre in Castilla y León. Its multidisciplinary team of over 100 specialists delivers applied research, technological innovation and knowledge transfer in artificial intelligence, natural language processing, cybersecurity, data spaces, IoT and quantum AI, through dedicated GenAI, XAILAB, FEDLAB and Q-Lab facilities. AIR Institute runs more than 50 active projects with over 100 partners and coordinates DIGIS3, the European Digital Innovation Hub of Castilla y León, supporting the digital transformation of European SMEs.
Stay informed on AI opportunities
Get updates on new solutions, market trends, and adoption strategies delivered to your inbox.
The DeployAI project has received funding from the Digital Europe Programme (DIGITAL) under grant agreement №. 101146490 - DIGITAL-2022-CLOUD-AI-B-03
Stay informed on AI opportunities
Get updates on new solutions, market trends, and adoption strategies delivered to your inbox.
The DeployAI project has received funding from the Digital Europe Programme (DIGITAL) under grant agreement №. 101146490 - DIGITAL-2022-CLOUD-AI-B-03