Evaluation of literature frontier based on latent semantic analysis

摘要

In this paper, a literature frontier evaluation method based on latent semantic analysis was proposed in terms of collection of front keywords and the surface information of literature. Firstly, to build the collection of front keywords, the frontier metric of keyword was studied for evaluating the frontier of keyword. Secondly, the collection of front literatures was achieved according to the built collection of front keywords and the latent semantic space of front literatures was built in terms of the front literatures' surface information such as title, keywords and abstract. Finally, the frontier of new literature was evaluated in terms of the frontier of each front literature, the semantic relevance with each front literature, and the impact factor of the journal which the new literature belonged to. The experimental results show that the collection of front keywords built by proposed frontier metric outperforms the academic hotspots achieved by the existing research platform of academic hotspots, and the proposed method is proved to be reasonable with the positive correlation between the frontier score of new literature and each of the impact factor of journal and the published year of literature.