News text analysis method based on graph analysis technology

The invention provides a news text analysis method based on a graph analysis technology, and the method comprises the steps: collecting massive news text data, calculating multi-level mixed similarity based on a plurality of natural language processing methods, quantifying the weights of nodes and edges through a graph analysis method, and constructing a time-varying news knowledge graph. Constructing a time sequence index by using a text classification method and information attenuation evaluation, finally forming a classified and time sequence text index, and on this basis, realizing quantitative measurement of the influence of an event represented by the text index on a field correlation index and the attribute thereof through methods such as sliding window causal test and wavelet analysis; according to the method, the technical problem that the influence factors of the market in the to-be-analyzed field are difficult to accurately identify, extract and process based on massive network information is solve