Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Chinese weibo sentiment analysis method based on lexical item subjective and objective directivity

A sentiment analysis and biased technology, applied in semantic analysis, text database clustering/classification, unstructured text data retrieval, etc. Make good use of the emotional characteristics of emojis and other issues to achieve the effect of accurate emotional classification

Inactive Publication Date: 2018-05-15
WUHAN UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (1) They only think that there is a dependency between emotion and theme, and do not consider the influence of bias on emotion;
[0007] (2) When used in the microblogging field, they cannot make good use of emoticons, the most typical emotional feature;
[0008] (3) Since bias is not taken into account, they cannot exploit the biased prior knowledge contained in the part of speech of emoji and lexical items

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Chinese weibo sentiment analysis method based on lexical item subjective and objective directivity
  • Chinese weibo sentiment analysis method based on lexical item subjective and objective directivity
  • Chinese weibo sentiment analysis method based on lexical item subjective and objective directivity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Embodiment one: see figure 1 , this is a Chinese microblog sentiment analysis method based on the subjective and objective bias of terms. The relationship between bias, emotion and theme uses the Gibbs sampling algorithm to jointly sample the three, and then determine the emotional polarity of microblogs.

[0068] The process of introducing emotional prior knowledge and biased prior knowledge is as follows:

[0069] (3a) Construct empty S×V emotion transfer matrix λ, K×V biased transfer matrix η, K×S×T×V β matrix and final prior matrix F(β,η,λ). Among them, S, T, K, and V respectively represent the number of emotions, the number of topics, the number of biases, and the number of different terms in the data set;

[0070] (3b)η K×V and lambda S×V The elements of are initialized to 1;

[0071] (3c) For each term w ∈ {1,...,V}, each biased label c ∈ {1,...,K} and each sentiment label l ∈ {1,..., S}, if w is biased prior knowledge, η K×V Element η in cw Updates are a...

Embodiment 2

[0087] Embodiment 2: This Chinese microblog sentiment analysis method based on the subjective and objective bias of terms crawls 3000 words from the Sina Weibo website

[0088] Microblogs are used as the target data set to be analyzed. Such as figure 1 As shown, a kind of term based on subjective and objective bias in this embodiment

[0089] Chinese Weibo sentiment analysis method, the steps are as follows:

[0090] S1. Crawl 3,000 pieces of Weibo data from the Sina Weibo website as the target data set to be analyzed, such as Weibo "I bought a new mobile phone today, so happy! [haha]";

[0091] S2. Perform pre-operations such as word segmentation, part-of-speech tagging, and stop word filtering on each microblog, and perform combination operations on emotional words preceded by negative words. For example, using the NLPIR of the Chinese Academy of Sciences as a word segmentation and part-of-speech tagging tool, Weibo "I bought a new mobile phone today, I am so happy! [haha...

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

No PUM Login to View More

Abstract

The invention relates to a Chinese weibo sentiment analysis method based on lexical item subjective and objective directivity. The Chinese weibo sentiment analysis method comprises the following stepsof 1, obtaining a to-be-analyzed target weibo dataset; 2, conducting pre-operations like word splitting, word class tagging and stopword filtering on each weibo, and conducting combined operation onsentiment words of which the front are privatives; 3, introducing emotional transcendence knowledge and directivity transcendence knowledge on the preprocessed weibo data; 4, using a Gibbs sampling algorithm to sample the directivity, the sentiment and the subject tab of each lexical item; 5, calculating the directivity and sentiment joint distribution variable of each weibo; 6, calculating the final sentiment polarity probability distribution of each weibo, and then determining the sentiment polarity of each weibo. By means of the Chinese weibo sentiment analysis method based on the lexical item subjective and objective directivity, the conception of the subjective and objective directivity (for short, directivity) of the lexical items is put forward aiming at the weibo data, and the Gibbs algorithm is utilized to jointly model the relation of the directivity, the sentiment and the subject. The Chinese weibo sentiment analysis method is simple and practical, and the weibo sentiment analysis performance can be obviously improved.

Description

technical field [0001] The invention relates to a sentiment analysis method for Chinese microblogs, in particular to proposing the concept of term bias for microblog data sets, and simultaneously introducing emotional prior knowledge and biased prior knowledge, based on bias, emotion The relationship with the topic uses the Gibbs sampling algorithm to jointly sample the three, then calculate the bias and emotion joint distribution variables of each microblog, and then calculate the final emotional probability distribution of each microblog, and then determine the emotional polarity of the microblog , is a Chinese microblog sentiment analysis method based on the subjective and objective bias of terms. Background technique [0002] In recent years, with the rapid development of Internet technology, various social media platforms have risen rapidly, and people are increasingly using social media such as Weibo to express their emotions or opinions. spread. Compared with tradit...

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
no application Login to View More
IPC IPC(8): G06F17/30G06F17/27
CPCG06F16/35G06F40/216G06F40/30
Inventor 刘进郭峻材陈雪崔晓晖
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com