Unlock instant, AI-driven research and patent intelligence for your innovation.

Microblogging summary generation method based on multimodal manifold learning and social network features

A manifold learning and social network technology, applied in the field of automatic text summarization, can solve problems such as increasing the cost of effective information, and achieve the effect of novelty and summarization.

Active Publication Date: 2022-07-01
CHONGQING UNIV OF POSTS & TELECOMM
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The rapid development of social network media, such as Twitter, Weibo, etc., provides people with a lot of information, but also increases the cost of obtaining effective information

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
  • Microblogging summary generation method based on multimodal manifold learning and social network features
  • Microblogging summary generation method based on multimodal manifold learning and social network features
  • Microblogging summary generation method based on multimodal manifold learning and social network features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] see figure 1 , when this method is used for the generation of multi-topic text summaries, it selects microblogs as summaries from social recognition and microblog salience, and controls the similarity of the final summaries, so that the generated summaries of microblogs comprehensively consider coverage. Sex, diversity, and social identity. .

[0042] Considering the diversity of topics in user summarization, its task can be viewed as a multi-document summarization task. Multimodal manifold learning is a widely used multi-document summarization method that comprehensively considers full-text topics, in-document importance, and documents. importance of time. For user summaries, since there is no predefined topic sentence information, this method improves the multimodal popular learning algorithm so that it can be applied to microblog summaries without topic sentences. At the same time, since Weibo contains social network interactive information, such as each Weibo has...

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 method for generating microblog abstracts based on multi-modal manifold learning and social network features, comprising the following steps: acquiring a user's microblog collection of specific topics and user interaction information; The relationship matrix of the text; the microblog salience is calculated by combining the matrix; the social identity degree is calculated by combining the user interaction information; the final microblog salience can be obtained by combining the microblog salience and the social identity degree, and then the one with the highest salience is selected. Several sentences become abstract. The present invention improves the popular learning method commonly used in multi-document summaries, and integrates social network information, which makes better use of sentence relationship features between different subject documents and sentence relationship features within the same document, while using maximum The boundary correlation algorithm (MMR) is used to reduce redundant information, taking into account the coverage and diversity of abstracts.

Description

technical field [0001] The invention relates to an automatic text summarization technology in natural language processing, in particular to the automatic generation of summaries of microblog speeches based on multimodal manifold learning and social network features. Background technique [0002] The rapid development of social network media, such as Twitter, Weibo, etc., provides people with a lot of information, but also increases the cost of obtaining effective information. This necessitates the research on microblog summarization that compresses the massive microblog information. At present, the main research methods of microblog abstract are: (1) Based on traditional extractive abstract methods: Sumbic, Textrank, Lexrank, Centriod, Data Reconstruction. (2) Use the static and dynamic data of social networks: the number of likes, the number of Weibo forwarding and replies, the user influence, etc. to summarize people's discussions on a certain topic. Most of the latest r...

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 Patents(China)
IPC IPC(8): G06F16/33G06F16/34G06F16/9536G06Q50/00
CPCG06F16/3335G06F16/3344G06F16/345G06F16/9536G06Q50/01
Inventor 夏书银曹洋洋陈子忠
Owner CHONGQING UNIV OF POSTS & TELECOMM