Public opinion robot system sentiment analysis and image annotation method based on microblogs

A robot system and sentiment analysis technology, applied in the field of sentiment analysis and image labeling, can solve problems such as no text

Inactive Publication Date: 2019-10-11
XIAMEN UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Nowadays, more and more users will only send a picture to express their current emotional tendency, wit

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
  • Public opinion robot system sentiment analysis and image annotation method based on microblogs
  • Public opinion robot system sentiment analysis and image annotation method based on microblogs
  • Public opinion robot system sentiment analysis and image annotation method based on microblogs

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The following embodiments will further illustrate the present invention in conjunction with the accompanying drawings.

[0060] Embodiments of the present invention include a microblog-based sentiment analysis module and a topic-oriented image descriptive text generation module:

[0061] 1. The microblog-based sentiment analysis module includes the following steps:

[0062] 1.1 Feature extraction of microblog data, the specific method is: social media on the Internet contains data with a large amount of data and a wide variety of data types, and there are three types of data in the selected microblog: text data, image data and emoticons data; firstly, it is necessary to extract features from data of three different modalities, and adopt a multimodal joint sentiment analysis model. For the selection of feature representation, it is necessary to select emotional features that are simple to obtain, stable in performance, and highly descriptive. Among them, text data Selec...

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 discloses a public opinion robot system sentiment analysis and image annotation method based on microblogs, and relates to sentiment analysis and image annotation. The microblog-based emotional tendency analysis module comprises the following steps: feature extraction of microblog data, modeling of a multi-modal joint model and an emotional tendency classifier; and 2, the topic-oriented image descriptive text generation module comprises the following steps of image data feature processing, text data feature processing and topic-oriented image descriptive text generation. According to the scheme provided by the invention, a section of text related to the specified topic can be generated for the picture, and meanwhile, the function of automatically publishing the generated textto the microblog is realized by interacting with the microblog server.

Description

technical field [0001] The present invention relates to emotion analysis and image labeling, especially relates to an end-to-end (end- to-end) based on the microblog public opinion robot system sentiment analysis and image annotation method of the fully automatic system. Background technique [0002] With the massive popularization and rapid development of Internet social media, it has become an inevitable part of people's daily life to publish news about their daily life, entertainment activities, social work, and public opinion on social media. An example of Sina Weibo user data, as of September 2017, there are 376 million monthly active users on Sina Weibo, and 165 million daily active users ("2017 Weibo User Development Report"). Therefore, it has become a very meaningful research for sentiment analysis on social media and generating text related to a certain topic based on pictures. At the same time, enabling computers to automatically generate text and realize automa...

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): G06K9/62G06F17/27G06F16/35
CPCG06F16/353G06F40/253G06F40/242G06F18/24G06F18/214
Inventor 纪荣嵘苏劲松刘宗岳
Owner XIAMEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products