Interpreting the structure and results of a data warehouse model using ontology and machine learning techniques.

This article presents an intelligent methodology designed to assist decision-makers in understanding, querying, and interpreting data warehouse models, particularly those analyzing social media data related to people with personality disorders (PD). The approach involves transforming a data warehouse model into an ontology to clarify domain terminology and semantic relationships, recommending SPARQL queries based on the ontology to guide decision-makers, and enriching analytical results using advanced machine learning techniques such as association rule mining and decision trees. The methodology was applied to an extended data warehouse model that integrates multiple social media platforms and focuses on behavioral and writing style analysis of individuals with PD, with evaluation conducted through both qualitative expert assessment and quantitative experiments on diverse corpora. The study emphasizes supporting non-computer-expert decision-makers by providing semantic clarity and multiple result visualizations to facilitate meaningful decisions in the sensitive context of mental health monitoring via social media data.