Microblog hot topic detection method and device aiming at specific group

Abstract

The invention relates to a microblog hot topic detection method and device aiming at a specific group. The detection method comprises the following steps of performing community classifying on all users in the microblog according to the attention relation between the certificated users and the users concerned by the certificated users; extracting a topic according to the microblog content issued by each obtained certificated user and the users concerned by the certificated users so as to obtain multiple summary topic types; establishing a topic matrix according to the user communities and the summary topic types; placing a microblog text corresponding to the micorblog text vector in each summary topic type with the maximum cosine similarity with the microblog text vector; selecting a plurality of summary topic types with the maximum matrix element numbers in the community topic matrix for clustering and classifying respectively; respectively extracting central hot event of each event clustering type and showing the central hot spot event for the corresponding community users. A multilayered result of the hot topic event is obtained, and the hot event interesting to a certain community is represented by the microblog.

Description

technical field [0001] The invention relates to the field of public opinion situation awareness of data mining, in particular to a microblog hot topic detection method and device for a specific group. Background technique [0002] In recent years, social networks represented by Weibo are playing an increasingly important role in people's lives, and the number of users of social networks is also increasing rapidly. The large number of users and the resulting large number of microblogs contain rich public opinion information, which is of great significance for capturing current social hotspots and tracking public opinion orientation and social situation. Therefore, the hot topic detection technology for Weibo has become a core public opinion research point in recent years. Due to the short length of microblog text (no more than 140 Chinese characters), fast update, many new words, and huge traffic, the detection of microblog hot topics is still a research difficulty. At pres...

AI Technical Summary

Problems solved by technology

Although such methods can also successfully mine Weibo hotspots to a certain extent, they cannot solve the following two problems: First, the hot topics mined are not targeted, because the public opinion information generated by Weibo not only has text content, as well as the obvious distribution of user interests, therefore, a specific hot topic is only meaningful if it specifies a specific user group that is interested in it

Second, the current hotspot mining methods only excavate some phrase-like summary hot topics, which cannot fully reflect the current hot events

And the definition of the current hot topic is very vague, from a phrase to a Weibo event can be understood as a hot topic, because the results of mining are not uniform

Images