Paper visualization method for assisting literature review based on citation analysis and topic modeling

The invention relates to a thesis visualization method based on citation analysis and topic modeling assisted literature review, which comprises the following steps: acquiring an original thesis data set, and creating a coupling similarity matrix and a co-citated similarity matrix according to a citation relationship between theses; extracting themes of the papers and probability distribution of the themes of the papers; inputting the probability distribution of the themes of the papers into t-sne to obtain a scatter diagram of the papers on a two-dimensional plane, and performing calculation by using a Kruskal algorithm to obtain a t-sne quotation network diagram for visual display; calculating the similarity between the probability distributions of the theses topic to create a content similarity matrix; calculating a comprehensive similarity matrix according to the coupling similarity matrix, the co-citated similarity matrix and the content similarity; and generating a corresponding coupled citation network