Keywords Extraction Method for Technological Demands of Small and Medium-Sized Enterprises Based on LDA
Xingbing Liu, Zhen Zhang, Baoxia Li, Fei Zhang · 2019
Keywords extraction technology is used in the technological demands of SMEs. It can match the demands to the scientific research team quickly and accurately. This is an effective method to promote industry-university-research linkage. But how to extract effective information from a wide range of technological demands information is a challenging task. For this issue, the paper is based on the text of the technological demands of SMEs, and proposes a keywords extraction method based on LDA. Firstly, natural language processing technology is used to preprocess text. Then, multi-feature weighting and Latent Dirichlet Allocation (LDA) theme model are fused to extract keywords. Thirdly, the method chooses the best keywords through post-processing. Finally, the method is verified by experiments, and the feasibility of the method is demonstrated by actual cases. The method was tested on Chinese ScientistIn dataset. The experimental results show that the F-value is higher than that of Term Frequency - Inverse Document Frequency (TF - IDF) and LDA. It also shows that the method can improve the intelligence of the scientific and technological collaboration platform. The algorithm works best when the F-value is 0.79 at K=3.