LISE: A Logic-Based Interactive Similarity Explainer for Clusters of RDF Data

Clustering methods are instrumental in the preliminary analysis of unstructured data, yet interpreting the resulting groups—-especially in the context of RDF (Resource Description Framework) data—-poses significant challenges. This paper introduces LISE (Logic-based Interactive Similarity Explainer), an integrated and model-agnostic framework designed to generate explainable, human-readable insights into clusters of RDF resources. LISE combines four core components: (i) a machine learning module leveraging vector embeddings and k-means clustering; (ii) a logic-based reasoning component that computes the common semantic features of clustered items via an optimized Least Common Subsumer (LCS); (iii) a Natural Language Generation (NLG) module that verbalizes these features into structured and human-readable explanations; and (iv) an interactive user feedback loop that captures user perception of explanation relevance to iteratively enhance embedding quality and cluster interpretability. An extensive use case on the DrugBank dataset demonstrates LISE’s ability to generate meaningful, context-aware cluster explanations and adapt to user preferences, advancing the state of explainable AI for semantic web technologies and knowledge graph analytics. The paper investigates also the integration in LISE of an LLM-based NLG approach, both in the DrugBank use case and through an extended experiment in a general-purpose dataset: YAGO3-10.