A fine-grained sentiment classification method based on stochastic co-occurrence network of sentiment words

A sentiment classification, random network technology, applied in the field of information retrieval

CN106547866BActive Publication Date: 2017-12-26XIAN UNIV OF POSTS & TELECOMM
2 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2017-12-26

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides a fine-granularity sentiment classification method based on a sentimental word random co-occurrence network. The method comprises the steps of: forming a random network model based on a word sequence and constructed with sentiment characteristics, namely a sentimental word co-occurrence network model, by use of a random network theory and a word co-occurrence phenomenon through annotation of a sentimental noumenon vocabulary library; and carrying out model reduction on the basis, combining a sentimental word longest match (SWLM) method with a TC (Text Category) algorithm to carry out SWLM-TC unsupervised learning classification, or further combining the sentimental word longest match method with an HMM (Hidden Markov Model) machine learning algorithm to establish a fine-granularity sentiment classification model, and realizing classification prediction by use of the model. According to the method, the fine-granularity sentiment classification of a paragraph-level text can be realized, the precision of a pure TC algorithm is improved so that the classification is accurate; and after an HMM model training is carried out on a sample set by use of the SWLM-TC algorithm, the sentiment classification is carried out on a to-be-tested sample database, the automation of a pure machine learning algorithm is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of information retrieval, in particular to a fine-grained sentiment classification method based on a random co-occurrence network of sentiment words. Background technique

[0002] In recent years, with the rapid development of the economy and information technology, the Internet has profoundly affected the development of the social form, and has had a huge role in promoting the economy. Internet residents have produced a vast amount of information. In the process of accelerating the landing of the mobile Internet, The popularity of various smart mobile devices allows information to spread on the Internet at a lower cost and faster speed. Different types of information will have different impacts. Negative speech will have a negative impact on netizens. Vicious group messages and The occurrence of public events will not only affect the individual's feelings, but even cause huge economic losses. Mining emotion...

Examples

Embodiment Construction

[0061] The implementation of the present invention will be described in detail below in conjunction with the drawings and examples.

[0062] Such as figure 1 As shown, a fine-grained emotion classification method based on the random co-occurrence network of emotional words in the present invention, first, adopts the random network theory, utilizes the co-occurrence phenomenon of words, and forms an emotional feature-based emotional classification method through the labeling of the emotional ontology vocabulary lexicon. A random network model based on the order of words, that is, the co-occurrence network model of emotional words, on this basis, the model is reduced, and the longest matching method of emotional words (SWLM, Sentimental Word Longest Match) and TC algorithm are combined for SWLM-TC ​​unsupervised Learn to classify, or further combine the longest matching method of emotional words and the HMM machine learning algorithm to establish a fine-grained emotional classif...