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

A Method for Processing Chinese Microblog Topic Information

An information processing method and a technology for microblog topics, which are applied in the fields of electronic digital data processing, special data processing applications, unstructured text data retrieval, etc.

Active Publication Date: 2018-09-07
哈尔滨工业大学人工智能研究院有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the rough work of the predecessors, the work of Abhimanyu and Anitha in 2014 (literature [4]DasA, Kannan A.Discovering topical aspects in microblogs[C] / / Proceedings of COLING.The 25th International Conference on Computational Linguistics:Technical Papers ,2014:860-871) is much more sufficient. In order to dig out hot topics in Twitter, they obtained three evaluation indicators by observing the commonality of Weibo events, namely "diversity" and "uniqueness". (Uniqueness)” and “Burstiness”, use the weakly labeled training corpus to fit the data distribution through a Gaussian mixture model, so as to output whether the candidate angle is a microblog event, such a supervised learning topic extraction The method can also achieve good results, but unfortunately this algorithm does not involve clustering and sorting of topics

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
  • A Method for Processing Chinese Microblog Topic Information
  • A Method for Processing Chinese Microblog Topic Information
  • A Method for Processing Chinese Microblog Topic Information

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0047] Specific implementation mode one: as figure 1 As shown, a Chinese microblog topic information processing method includes the following steps:

[0048] Step 1: Judgment of Weibo related to hot events;

[0049] Input the relevant microblog of a single hot event, use the language technology platform to preprocess the text and judge whether the microblog is relevant through the keyword matching method, and the language technology platform is the language technology platform of Harbin Institute of Technology (Che W, Li Z, LiuT.Ltp: A chinese language technology platform[C] / / Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations.Association for Computational Linguistics,2010:13-16);

[0050] Step 2: Microblog topic discovery;

[0051] By counting the Hashtag information in the microblog, the topic information in the hot event microblog is mined, wherein the Hashtag is the topic information, that is, the text between two "#" symbols in ...

specific Embodiment approach 2

[0083] Embodiment 2: This embodiment differs from Embodiment 1 in that: in the step 4, the threshold value of the addition rate of microblogs corresponding to S topics is 0.1.

specific Embodiment approach 3

[0084]Specific embodiment three: the difference between this embodiment and specific embodiment one or two is: in step four, after obtaining the final output in step (7), return to repeat steps (1) to (7) again, and the initial input is the self-expanded S topics and their related microblogs finally output in step (7).

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 Chinese microblog topic information processing method, and relates to reason analysis algorithms for emotional distribution of microblog events. The invention aims to solve the problems that a hierarchical clustering algorithm and a correction algorithm adopted in an existing microblog topic information processing method are low in accuracy and incapable of including event-related microblogs in correct topics. According to the Chinese microblog topic information processing method, event topics and related microblogs are mined with a hierarchical clustering ordering method of unsupervised learning and a microblog topic correction algorithm of semi-supervised learning, so that the purpose of performing emotional distribution statistics and analysis on the related microblogs is finally achieved. The Chinese microblog topic information processing method can perform microblog topic information processing more accurately. The present invention is applied to the microblog topic information processing field.The Chinese microblog topic information processing method is applied to the field of microblog topic information processing.

Description

technical field [0001] The invention relates to a method for processing microblog topic information. Background technique [0002] As an emerging social media platform, Weibo is also one of the most popular social media platforms in China. There are hundreds of millions of active users. More and more netizens choose to obtain and share information they are interested in on Weibo. In the face of big data of tens of millions per day on Weibo, it is very meaningful to analyze netizens’ opinions and attitudes towards a certain event. More and more scholars have begun to pay attention to the information behind such big data on Weibo. [0003] Since microblogging as a form of social media has not been in people's lives for a long time, there are not many related researches on the analysis of the causes of microblogging event emotion distribution at home and abroad. The current microblogging event mining methods mainly include, in 2011, Weng et al. used the relevant principle of w...

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): G06F17/30
CPCG06F16/313G06F16/35
Inventor 赵妍妍秦兵李泽魁
Owner 哈尔滨工业大学人工智能研究院有限公司
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