A Microblog Emergencies Detection Method

Abstract

Disclosed is a micro blog emergency detection method. The micro blog emergency detection method includes steps: performing dimension reduction treatment: performing mapping treatment on vocabularies in a micro blog data stream based on an LSH algorithm; creating a B-sketch model: creating B-Sketch data in a micro blog data stream; conjecturing an emergency: calculating incident acceleration a in the micro blog data stream and a distribution vector p of an incident middle term according to the B-Sketch data, and judging whether an incident is the emergency or not according to the incident acceleration a. Due to the fact that all the vocabularies are mapped into a low dimension space through the LSH algorithm, calculation complexity is reduced, the connotative emergency is conjectured based on the B-sketch model, the micro blog data stream can be rapidly and effectively processed in real time, and the emergency can be detected as soon as possible.

Description

technical field [0001] The invention relates to the technical fields of natural language processing, text data mining, and emergency detection, and in particular to a microblog emergency detection method. Background technique [0002] Microblog, or MicroBlog, is a mini-blog that allows users to write a short text (generally 140 Chinese characters on Chinese microblog platforms) to describe daily life or publish news, comment on current events and pass on these information To friends or interested bystanders, the release method can be SMS, instant messaging tool (IM), email or the Internet. Compared with instant messaging, users can specify whether the published information is public or limited to a small network; compared with blogging platforms, users' time and energy investment is lower, communication speed is faster, and there is a higher update frequency. [0003] The development of the Internet has made the release and acquisition of Weibo more convenient and fast, whi...

AI Technical Summary

Problems solved by technology

[0003] The development of the Internet has made the release and acquisition of Weibo more convenient and fast, which directly leads to the following two problems: First, the number of Weibo is huge, and it is not feasible to read all the information manually

[0006] 1) It is generally an offline mode, which cannot meet the needs of online real-time processing, and the scale of processed data is very limited;

[0007] 2) Unable to detect emergencies early, showing a lag in the discovery of emergencies, and often have extremely low practicability;

[0008] 3) The feature space is not dimensionally reduced, which often leads to slow running speed and consumes a lot of memory space

Images