Personalized Scholar Recommendation Based on Multi-Dimensional Features

The rapid development of social networking platforms in recent years has made it possible for scholars to find partners who share similar research interests. Nevertheless, this task become increasingly challenging with the dramatic increase number scholar users over networks. Scholar recommendation recently a hot topic. Thus, we propose personalized approach, Mul-RSR (Multi-dimensional features based Research Recommendation), which improves accuracy and interpretability. In work, aims provide academic platforms. uses Doc2Vec text model random walk algorithm calculate textual similarity relevance measure correlation between scholars. It is able recommend Top-N each on multi-layer perception attention mechanism. To evaluate proposed conduct series experiments public self-collected ResearchGate datasets. results demonstrate that our approach hit rate, rate reaches 59.31% when N value 30. Through these evaluations, show can more solid scientific decision-making basis achieve better effect.