A carregar...
Publicação
An Activity-Centric Intelligent Information System for Context-Aware Recommendation in Exploratory Journalistic Research
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.18 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
Journalists navigating large digital archives face a tension between speed and thoroughness. Keyword search often returns unmanageable volumes of results, while topic-only recommendation may fail to identify contextually appropriate content. This paper presents magknet, a recommendation system that surfaces archival content for journalists by combining topic classification with hierarchical context modelling, with an explicit focus on transparency and explainability. The system integrates topic-based classification using Vector Space Models over predefined fundamental topics with context-based filtering through a four-dimensional ontological model representing where, when, who, and what. Recommendations are generated primarily from interpretable topic and context similarity, while the architecture allows later reinforcement with observed user attachment patterns. The system was validated at TRL 7 through exploratory testing with professional journalists. All assessed recommendations met the predefined relevance threshold and were judged contextually appropriate within the tested scenarios. Perceived value was strong: all participants recognized value in incorporating the system into professional work, while 84.6% valued the system as an information aggregator and anticipated productivity gains. The system’s value as a memory record was lower (38.5%), suggesting that active recommendation is the stronger use case. Qualitative feedback showed appreciation for contextual relevance and transparency, alongside challenges related to workflow integration and real-time information needs. The paper contributes: (i) an activity-centric formulation of recommendation for professional knowledge work; (ii) a hybrid topic-context ranking model combining vector-space topic representation with ontology-based contextual similarity; and (iii) an exploratory validation showing perceived usefulness, contextual adequacy, and adoption constraints. The results support interpretable, context-aware recommendation for archival journalistic research, while indicating that future systems should be embedded in existing professional tools.
Descrição
Publisher Copyright: © 2026 by the authors.
Palavras-chave
Activity-centric retrieval AI-assisted journalism Context-aware recommendation Explainable AI Intelligent information systems Ontology-based similarity General Materials Science Instrumentation General Engineering Process Chemistry and Technology Computer Science Applications Fluid Flow and Transfer Processes