O Impacto de Estratégias de Embeddings de Grafos na Explicabilidade de Sistemas de Recomendação

• DOI: 10.5753/webmedia.2024.241857
• Publication Date: 2024-10-14T17:36:19Z
• Authors: André Levi Zanon; Leonardo Rocha; Marcelo Garcia Ma...

Explanations in recommender systems are essential improving trust, transparency, and persuasion. Recently, using Knowledge Graphs (KG) to generate explanations gained attention due the semantic representation of information which items their attributes represented as nodes, connected by edges, representing connections among them. Model-agnostic KG explainable algorithms can be based on syntactic approaches or graph embeddings. The impact embedding strategies generating meaningful still needs studied literature. To fill this gap, work, we evaluate quality provided different embeddings compare them with traditional strategies. was assessed three metrics from literature: diversity, popularity recency. Results indicate that algorithm chosen impacts generates more balanced results regarding explanation diversity compared approaches.