Financial news stream emergency detection method based on hierarchical clustering

Abstract

The invention discloses a financial news stream emergency detection method based on hierarchical clustering. The method comprises the following steps: preprocessing a text; extracting keywords and constructing a keyword co-occurrence graph; clustering the keywords by adopting a bisection K-Means algorithm, dividing the keyword co-occurrence graph into a plurality of sub-graphs, with the keyword in each sub-graph being a financial theme; identifying the financial theme to which each piece of financial news belongs through similarity calculation; constructing an undirected graph with each piece of financial news as a node, clustering the financial news by adopting the bisection K-Means algorithm, dividing the financial news node undirected graph into a plurality of sub-graphs, with the financial news in each sub-graph being a financial event; generating a story chain through similarity calculation; performing emergency detection. According to the method, event clustering is carried out on financial news through natural language processing and graph theory related technologies, the problem that related news of the same event cannot be comprehensively considered in traditional financial emergencies is solved, the financial emergencies are efficiently and accurately detected, and certain industrial value is achieved.

Description

technical field [0001] The invention relates to the field of financial news data mining, in particular to a method for burst detection of financial news streams based on hierarchical clustering. Background technique [0002] Investors are important participants in the financial market. Once a financial emergency breaks out, it will bring disaster to the majority of investors. The detection of financial emergencies helps investors avoid risks. [0003] In recent years, public opinion related to the financial industry has shown a "surge" trend, with a relatively concentrated time of occurrence, a large amount of information interaction, and frequent interactions. The generation, expansion and dissemination of financial public opinion will have an important impact on investors, financial institutions, the financial industry and even macroeconomic operations. Often some small credit crises may lead to financial crisis events. Therefore, monitoring financial public opinion and ...

AI Technical Summary

Problems solved by technology

[0004] 1. Weak awareness of crisis and insufficient monitoring of financial emergencies;

[0005] 2. The financial emergency response system is not perfect;

[0006] 3. The guidance and handling of online public opinion when a financial emergency occurs is not professional enough

[0021] 4. Major risk events of the company itself;

[0024] From the above content, it can be seen that there are many news data and factors that need to be considered in the monitoring of financial emergencies. Only relying on manpower to analyze and judge cannot satisfy the multi-level, all-round, full-screen, full-network, full-time, all-weather monitoring of financial events; it is impossible to establish a timely response System to investigate the source, path, and scope of financial news and public opinion dissemination; it is impossible to train a large number of relevant personnel at low cost to quickly monitor and handle financial events

Images