Combining Machine Learning and Semantic Web: A Systematic Mapping Study

In line with the general trend in artificial intelligence research to create intelligent systems that combine learning and symbolic components, a new sub-area has emerged focuses on combining machine (ML) components techniques developed by Semantic Web (SW) community – Machine Learning (SWeML for short). Due its rapid growth impact several communities last two decades, there is need better understand space of these SWeML Systems, their characteristics, trends. Yet, surveys adopt principled unbiased approaches are missing. To fill this gap, we performed systematic study analyzed nearly 500 papers published decade area, where focused evaluating architectural, application-specific features. Our analysis identified rapidly growing interest high application domains tasks. Catalysts increased deep knowledge graph technologies. By leveraging in-depth understanding area acquired through study, further key contribution paper classification system Systems which publish as ontology.