The Smart Book Recommender (SBR) is an ontology-based system developed to assist Springer Nature’s Computer Science editorial team in selecting appropriate editorial products—such as books, journals, and conference proceedings—to market at specific scientific venues. By leveraging the Computer Science Ontology, a comprehensive taxonomy of research areas, SBR semantically analyzes and matches approximately 27,000 editorial products with the thematic focus of various conferences. This approach aims to streamline the traditionally manual and increasingly inefficient process of product selection in the face of a rapidly expanding body of scientific literature.
Benefits & outcomes
- Enhanced efficiency in matching editorial products to relevant conferences.
- Reduction in manual effort required by editors for product selection.
- Improved transparency through interactive graph views explaining recommendations.
- Positive evaluation results from both Springer Nature editors and Open University researchers, confirming the system’s effectiveness.
Notes & quotes
“We have addressed this issue by creating Smart Book Recommender (SBR), an ontology-based recommender system developed by The Open University (OU) in collaboration with Springer Nature.”
“SBR recommends books, journals, and conference proceedings relevant to a conference by taking advantage of a semantically enhanced representation of about 27K editorial products.”
“SBR also allows users to investigate why a certain publication was suggested by the system.”
The system’s interactive graph view displays the topic taxonomy of the recommended editorial product and compares it with the topic-centric characterization of the input conference, providing a visual rationale for recommendations
Publisher / company: The Open University in collaboration with Springer Nature
Date of case study: 24/03/2021
Source: https://arxiv.org/abs/2103.13526