The paper presents the motivation, development, and evaluation of an AI-driven framework for media stream impact analysis at the consumption end, employing user reactions monitoring through attention tracking (i.e., eye and mouse tracking). The adopted methodology elaborates on software and system engineering processes, combining elements of rapid prototyping models with interdisciplinary participatory design and evaluation, leaning on the foundation of information systems design science research to enable continuous refinement through repeated cycles of stakeholder engagement, feedback, technical iteration, and validation. A dynamic Form Builder has been implemented to supplement these tools, allowing the construction and management of pre- and post-intervention questionnaires, thus helping associate collected data with the respective tracking maps. The present begins with the detailed presentation of the tools’ implementation, the respective technology, and the offered functionalities, emphasizing the perception of tampered visual content that is used as a pilot evaluation and validation case. The significance of the research lies in the practical applications of AI-assisted monitoring to effectively analyze and understand media dynamics and user reactions. The so-called iMedius framework introduces an integration of innovative multidisciplinary procedures that bring together research instruments from the social sciences and multimodal analysis tools from the digital world.
This study introduces MediaWatchers4Climate, a methodological framework that leverages machine learning to evaluate the accuracy and rhetorical framing of climate change narratives in Greek online media. The model is designed to analyze large-scale textual data from over 1500 certified digital outlets registered in the Greek Online Media Registry. Through keyword-based filtering, thematic clustering, and content comparison techniques, the framework aims to detect discursive shifts, trace the replication of news stories, and identify misinformation patterns. While the current phase focuses on model development and data structuring, preliminary observations suggest significant content repetition across sources and a lack of original reporting on climate issues. The project ultimately seeks to promote evidence-based reasoning and enhance public resilience to misinformation related to the climate crisis.