A method for microblogging emotion analysis combined with user structure similarity
A technology of structural similarity and sentiment analysis, applied in the field of big data analysis, can solve problems such as different expressions, short sentences, interference with sentiment analysis methods, etc., and achieve the effect of accurate models
Active Publication Date: 2019-03-22
HARBIN ENG UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] However, since the contents of these emerging social networks are generated by users, their expressions are different, and the generated sentences are short and contain a lot of noise to interfere with traditional sentiment analysis methods.
Traditional methods based solely on selecting different text features are not applicable in this new context
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0059] The present invention specifically comprises the steps:
[0060] (1) Calculate the structural similarity between users according to the attention relationship between microblog users, establish a user similarity matrix, that is, an emotional infectious matrix, and establish an emotional infectious model;
[0061] (2) According to the emotional consistency theory in sociology, establish the emotional consistency relationship matrix between microblogs, and establish the emotional consistency model at the same time;
[0062] (3) Use the model generated in the first two steps to establish a microblog sentiment analysis model formed according to the relationship matrix between microblogs;
[0063] (4) On the basis of the first three steps, add a sentiment analysis model using microblog text content;
[0064] (5) Optimize the model established in the fourth step to solve the Weibo sentiment analyzer.
[0065] The implementation process of the present invention will be furth...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a method for analyzing micro-blog emotion combined with user structure similarity. The method comprises the following steps: (1) calculating the structural similarity betweenusers according to the attention relationship between users of micro-blog, establishing a user similarity matrix, namely an emotional contagion matrix, and simultaneously establishing an emotional contagion model; (2) According to the affective consistency theory in sociology, establishin the affective consistency relation matrix and affective consistency model; (3) Establishing a micro-blog emotion analysis model based on the relationship matrix between micro-blogs by using the model generated in the first two steps; (4) Based on the first three steps, adding the affective analysis model using the content of micro-blog text; (5) Optimizing the model established in the fourth step, and solve the micro-blog emotion analyzer. The invention has the advantage that, according to the characteristics of the micro-blog data, a method combining the relationship between the micro-blog data is proposed for affective analysis, and the accuracy of the affective analysis of the micro-blog is effectively improved.
Description
technical field [0001] The invention belongs to the field of big data analysis, and in particular relates to a method for microblog sentiment analysis in combination with user structure similarity. Background technique [0002] With the development of Internet technology, a large number of new social platforms such as Twitter and Sina Weibo have emerged. They attract a large number of users, and users post a large number of tweets and micro-blogs containing their various opinions on these sites. Analyzing user opinions plays an important role and significance in various fields, such as predicting the stock market, improving the accuracy of recommendation systems, investigating user feedback on products, and helping government departments conduct public opinion supervision by analyzing user opinions. The above-mentioned process of analyzing user opinions is called sentiment analysis. Although there have been some related works before, most of the currently recognized system...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F16/35G06K9/62
CPCG06F18/22
Inventor 杨静邹晓梅张健沛韩宏宇张薇
Owner HARBIN ENG UNIV