Dictionary-based public opinion monitoring method and device

Abstract

The invention discloses a dictionary-based public opinion monitoring method and device. The method comprises the following steps: extracting public opinion data about news public opinions of a company from different network platforms; performing word segmentation on the multiple pieces of public opinion data through a dictionary group containing technical terms to obtain multiple emotion segmented words; allocating a corresponding emotion weight value to each emotion segmented word, and calculating a segmented word score value of each emotion segmented word by using the emotion weight; and determining the public opinion wind direction based on the values of the plurality of word segmentation values. According to the method, the massive public opinion data can be subjected to word segmentation through the dictionary group, the data processing efficiency can be rapidly improved, the corresponding emotion weight values can be allocated after word segmentation, the corresponding emotion score values can be calculated, and therefore the public opinion wind direction is determined according to the emotion score values; therefore, the analysis result is prevented from being inconsistent with the reality due to personal subjective thoughts, and the accuracy of analysis and monitoring is effectively improved.

Description

technical field [0001] The invention relates to the technical field of public opinion monitoring, in particular to a dictionary-based public opinion monitoring method and device. Background technique [0002] The current definition of Internet public opinion is that the Internet is the communication platform, the new media is the communication medium, and the real events are the basis for dealing with the objects. It is a group ideological tendency formed by gathering the external opinions of different individuals, and it is constantly beneficial to the occurrence of real events. or deleterious interactions. With the rapid development of the Internet, Internet news media has the characteristics of strong interaction, high openness, and large amount of information, and has become the core medium for the dissemination of Internet public opinion today. In order to accurately analyze the ideological trends of various groups on the Internet, public opinion analysis is essential....

AI Technical Summary

Problems solved by technology

[0004] However, the currently commonly used network public opinion analysis methods have the following technical problems: sentiment analysis methods based on machine learning require manual labeling of a large amount of data, and then use machine learning algorithms for supervised training. This process takes a lot of time and the processing efficiency is very low. , and manual labeling is likely to be due to personal subjective ideas, and personal subjective and network public opinion emotions may not be the same, resulting in labeling results that do not match the actual situation, reducing the accuracy of the analysis

Images