A Consensus Clustering-based Label Propagation Method for Classification of Science & Technology Resources

With the rapid expansion of the science & technology services industry, abundant science and technology resources were produced which caused great difficulties for the management of science and technology service platform. Due to the high specialization of science & technology resources, the classification task is not easy. This study aims to propose an efficient classification method for science & technology resources classification such as papers, patents, etc. A science & technology text classification framework based on Word2Vec and consensus clustering-based label propagation algorithm was proposed in this paper. To verify the effectiveness of the method, a dataset of science & technology resources from a Chinese science and technology service platform was used for the demonstration. The study provides a new perspective on science & technology resource classification and the method can also serve many different business scenarios.