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

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