Public opinion analysis method based on probability feature association

Abstract

The invention discloses a public opinion analysis method based on probability feature association. The method comprises the steps of 1, collecting long-term information of a certain news event, and obtaining long-term feature word items in the long-term information to form a long-term dictionary of the text information; 2, obtaining a current feature set formed by the feature word items of the current news text information; 3, adopting the current feature word items as the center, arranging a circular association gate according to the radius of the certain association gate, and obtaining a feature set of the feature word items inside the association gate; 4, obtaining the association probability between word vectors of the long-term feature word items inside the association gate and word vectors of the current feature word items; 5, calculating an optimal feature weight of the current feature word items and a corresponding optimal current feature weight vector, and adopting the optimal current feature weight vector for a soft sensor model for performing situation estimation on the current news event, and obtaining situation fusion estimation and whole feature expression of the current news event. The event situation estimation fusion effect is improved, and the situation estimation is more reliable.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a public opinion analysis method based on probabilistic feature association. Background technique [0002] Online news information directly reflects the current situation of the event through the intuitive reporting of public events. For example, in a certain event in the United States, the reports of the American news media reflect the White House’s judgment on the event, and the analysis of online news reports can provide reliable events for decision-making. Situation estimation. This kind of online news information comes from human observation. Compared with the traditional radar measurement information, it is difficult to measure directly, and the computer cannot directly understand it. The processing and fusion of this kind of unstructured or semi-structured information is a new research hotspot in the field of information fusion. challenge. [0003] Traditi...

AI Technical Summary

Problems solved by technology

However, these association algorithms usually only associate event elements in soft information, such as people, time, destinations

Images