Enhancing Academic Paper Recommendations Using Fine-Grained Knowledge Entities and Multifaceted Document Embeddings
This addresses the specific literature needs of scholars during research, though it appears incremental as it builds on existing recommendation approaches with enhanced features.
The paper tackles the problem of academic paper recommendation systems being too coarse-grained by proposing a method that integrates fine-grained knowledge entities, document text, and citation data to generate more specific recommendations. The method achieved an average precision of 27.3% in top-50 recommendations, improving by 6.7% over baselines on the STM-KG dataset.
In the era of explosive growth in academic literature, the burden of literature review on scholars are increasing. Proactively recommending academic papers that align with scholars' literature needs in the research process has become one of the crucial pathways to enhance research efficiency and stimulate innovative thinking. Current academic paper recommendation systems primarily focus on broad and coarse-grained suggestions based on general topic or field similarities. While these systems effectively identify related literature, they fall short in addressing scholars' more specific and fine-grained needs, such as locating papers that utilize particular research methods, or tackle distinct research tasks within the same topic. To meet the diverse and specific literature needs of scholars in the research process, this paper proposes a novel academic paper recommendation method. This approach embeds multidimensional information by integrating new types of fine-grained knowledge entities, title and abstract of document, and citation data. Recommendations are then generated by calculating the similarity between combined paper vectors. The proposed recommendation method was evaluated using the STM-KG dataset, a knowledge graph that incorporates scientific concepts derived from papers across ten distinct domains. The experimental results indicate that our method outperforms baseline models, achieving an average precision of 27.3% among the top 50 recommendations. This represents an improvement of 6.7% over existing approaches.