| Popis: |
Expert recommendation plays an important role in academic peer evaluation activities, because their gradual evaluation will influence the final decision. In this paper, we propose a review expert recommendation (RER) method based on comprehensive evaluation in multi-source data. First, we use network extraction technology to collect network information and build expert profile. And then an expert field classification model is built in conjunction with the text similarity method. Finally, we establish a domain expert evaluation model to recommend experts based on the needs of the review work. Subsequently, an experiment is conducted using from real data, and the results show that our proposed scheme is effective. |
