Text emotion analysis method and device, computer equipment and storage medium

Abstract

The invention provides a text emotion analysis method, a text emotion analysis device, computer equipment and a storage medium. The method comprises the steps of acquiring a first text on an appointedplatform; building a word embedding on each statement included in the first text; inputting each built word embedding into a text emotion analysis model acquired by training based on a long and shortmemory network model to output an emotion label of each word embedding, and using the emotion label as the emotion label corresponding to each statement; and counting the quantity of each kind of emotion labels in the emotion labels corresponding to all statements of the first text, and analyzing the emotion labels corresponding to the first text according to the quantity of each kind of emotionlabels. According to the text emotion analysis method, the text emotion analysis device, the computer equipment and the storage medium provided by the invention, the emotion feedback of the user on the public platform to the enterprise is automatically recognized.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a text sentiment analysis method, device, computer equipment and storage medium. Background technique [0002] On public platforms such as Weibo, users often express their own opinions on enterprises and enterprise services. Weibo is an open platform, and users' evaluation of the company has a great impact on the image of the company. Therefore, it is particularly important to obtain user feedback on the company's services on the Weibo platform. Relying on staff to obtain feedback is not only labor-intensive, but also inefficient. . [0003] At present, there is no automatic recognition of the text content such as comments, mentions, and reposts received by the company’s official Weibo on the Weibo platform in real time; The influence of corporate brand and product. Contents of the invention [0004] The main purpose of this application is to provide a text senti...

AI Technical Summary

Problems solved by technology

Weibo is an open platform, and users' evaluation of the company has a great impact on the company's image. Therefore, it is particularly important to obtain user feedback on the company's services on the Weibo platform. Relying solely on staff to obtain feedback is not only labor-intensive, but also inefficient

[0003] At present, there is no automatic identification of text content such as comments, mentions, and reposts received by the company’s official Weibo in real time on the Weibo platform; it is impossible to automatically identify the emotions of the company’s brand and products contained in the above text content, and the content’s impact on the company’s products. Influence of corporate brand and products

Images