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

Micro-blog emotion prediction method based on weak supervised type multi-modal deep learning

A technology of deep learning and prediction methods, applied in prediction, biological neural network model, other database retrieval and other directions, can solve the problems of multi-modal discriminant representation and limited data labels, and achieve the effect of performance improvement and effect improvement

Inactive Publication Date: 2018-06-01
XIAMEN UNIV
View PDF12 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a microblog based on weakly supervised multimodal deep learning for the problem of multimodal discriminant representation and limited data labels in the emotion prediction on microblog multi-channel content (multimodal). Sentiment Prediction Methods

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
  • Micro-blog emotion prediction method based on weak supervised type multi-modal deep learning
  • Micro-blog emotion prediction method based on weak supervised type multi-modal deep learning
  • Micro-blog emotion prediction method based on weak supervised type multi-modal deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The following embodiments will further illustrate the present invention in conjunction with the accompanying drawings.

[0024] Embodiments of the present invention include the following steps:

[0025] Step 1 Microblog multimodal data preprocessing, the specific method is as follows:

[0026]First, de-duplicate the crawled Weibo data, then filter out the label symbols and external links in the Weibo content, and finally use the Chinese Academy of Sciences automatic word segmentation tool ICTCLAS to segment the Weibo text content (Text segment); As a noise label (emoji category), first collect all the emoticons in the text corpus, then screen out 49 frequently used emoticons, and finally build an emoji word bag model for each Weibo as an emoji category (Bag- of-emoticon-word) to obtain clean labels by manually labeling the emotional polarity of microblog data (emotional polarity categories: positive, negative, and neutral).

[0027] Step 2 Weakly supervised training o...

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 micro-blog emotion prediction method based on weak supervised type multi-modal deep learning and relates to the field of multi-modal emotion analysis. The method comprises the following steps of preprocessing micro-blog multi-modal data; carrying out the weak supervised training of a multi-modal deep learning model; and carrying out the micro-blog emotion prediction of the multi-modal deep learning model. The method solves the problems of the multi-modal discriminant expression and the data label limitation existing in the emotion prediction of the micro-blog multi-channel content in the prior art, and realizes the final multi-modal emotion class prediction, wherein the accuracy is adopted as the experiment evaluation standard. The consistency degree between the predicted micro-blog emotion polarity category and the pre-marked emotion category is reflected. The performance of the method is greatly improved and the correlation among multiple modals is considered. As a result, an optimal effect is achieved in the aspect of the overall multi-modal performance. An ideal classification effect is achieved for different emotion categories. Through the weak supervised training, an initial model for text and image modals is obviously improved in the aspect of emotion classification effect.

Description

technical field [0001] The invention relates to the field of multimodal sentiment analysis, in particular to a microblog sentiment prediction method based on weakly supervised multimodal deep learning. Background technique [0002] Recently, with the rapid development of large social platforms such as Sina Weibo, the scale of multimedia data in social networks is increasing every day. Taking Sina Weibo as an example, as of March 2016, the monthly active users of Sina Weibo reached 260 million. As one of the most popular platforms, Sina Weibo enables Internet users to express their emotions on topics of interest to them. Therefore, it has attracted a large amount of research on emotional information mining, which involves some emerging applications including event detection, social network analysis, and business recommendation. [0003] An obvious feature of the development of Weibo is the growth of multimodal information, such as images, videos, short texts, and rich emotic...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/00G06F17/30G06F17/27G06N3/04
CPCG06F16/951G06Q10/04G06Q50/01G06F40/289G06N3/045
Inventor 纪荣嵘陈福海
Owner XIAMEN 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