Target-oriented sentiment classification method

Abstract

The invention discloses a target-oriented sentiment classification method, which belongs to the technical field of big data and comprises the following steps that: a client server and a central server are established, and the client server is used for collecting text information and sending the text information to the central server; a preprocessing module, a GloVe model module, a position information coding module, an attention encoder and a classifier module are established in a central server; a target sequence to be analyzed is extracted; aiming at the technical problem that target-oriented sentiment analysis is completed by aiming at the target sequence, the method is suitable for a scene needing fine-grained sentiment analysis, the text containing a plurality of targets to be analyzed and different targets with different sentiment colors in the statement can be subjected to sentiment classification, and extraction is more accurate and effective.

Description

technical field [0001] The invention belongs to the technical field of big data, and in particular relates to a target-oriented emotion classification method. Background technique [0002] Sentiment classification, also known as opinion mining, is an area of ​​natural language processing that is used to extract opinions about things in a passage of text and identify their sentimental tendencies. At present, emotion classification technology is applied in more and more fields. With the continuous growth of public information on the Internet, there are a large number of texts with subjective emotions on social networks, news resources, business, and government system platforms. Sentiment analysis technology can extract, analyze, and process unstructured text information, and finally obtain structured data, which can be intuitively displayed to users. [0003] There are two main categories of technologies used in emotion classification at this stage: methods based on machine l...

AI Technical Summary

Problems solved by technology

Feature engineering is a very important link in this process. The quality of features directly affects the final performance of the classifier. The biggest disadvantage of this method is that the features of the input classifier need to be manually designed and extracted, such as the currently widely used Text keyword extraction technology based on dictionary rules, by using TF-IDF and other technologies to convert keywords into vector representations, and use them as text features

[0005] Whether it is a method based on machine learning or a method based on deep learning, it is currently oriented to the sentiment analysis of the entire text or sentence, which belongs to a single mode. If a sentence contains multiple targets to be analyzed, different targets have different emotional colors , at this time, the results obtained by the analysis of this coarse-grained sentiment classification method will no longer be accurate, and fine-grained sentiment classification needs to be carried out for different target objects

Images