Method for clustering network-based short texts

Abstract

The present invention discloses a method for clustering network-based short texts. The specific implementation process comprises: firstly acquiring a network-based comment; pre-processing the acquired network-based comment, wherein the pre-processing comprises performing word segmentation on the network-based comment, then removing the word that is not used, segmenting a keyword, and performing weighted calculation on the keyword; and clustering the pre-processed texts. The method for clustering network-based short texts, as compared with the prior art, implements collection and analysis of massive data over the network, such that a user conveniently searches for valued information. With this method, the precision in clustering the network-based short texts is high, thereby accommodating practical needs of the user. Therefore, the method according to the present invention has great practicability and can be simply promoted.

Description

technical field [0001] The invention relates to the technical field of Web text clustering, in particular to a highly practical network short text clustering method. Background technique [0002] Nowadays, the Internet has become the primary platform for people to obtain information and interact with each other, such as Zhongguancun Online, Autohome, Pacific Computer, etc. People can learn about product consultation and express their own opinions through these interactive portals. Various advantages and disadvantages and opinions put forward by related products, among which there is a large amount of valuable information that needs to be discovered by people. [0003] For example, before we buy a certain mobile phone, we often go to websites like Zhongguancun Online to find out other users' comments on this mobile phone, such as "It's a pity that it is not a 4G network. Disappointed, the power adapter is very hot in summer!", "The main screen The material is made of flexibl...

AI Technical Summary

Problems solved by technology

[0009] Grid-based clustering method (Clique clustering method, etc.) because the processing time of grid clustering is related to the number of cells divided in each dimension space, it is sensitive to isolated point processing and cannot handle large data, so to a certain extent Reduced the quality and accuracy of algorithm clustering;

[0010] The more classic partition-based clustering method is the traditional K-means clustering method, because the initial clustering center is randomly selected, which will reduce the accuracy of the clustering results, and the algorithm is very sensitive to outliers, while At present, the improvement of the K-means clustering method is aimed at ordinary texts, and there are not many studies on the clustering of network short texts. Since the characteristics of ordinary texts are different from those of network short texts, if the existing K-means method based on ordinary texts is improved -means clustering method for clustering, its clustering results are not ideal

Therefore, the existing technology cannot perform clustering according to the characteristics of the network short text itself.

Images