Emerging hot topic detection system on basis of multiclass feature fusion

Abstract

The invention relates to an emerging hot topic detection system on the basis of multiclass feature fusion. The emerging hot topic detection system comprises a data preprocessing module, a hierarchicalsequence model, a word encoder layer, a sentence level feature solving layer, a topic level feature solving layer and a topic predicting module. The data preprocessing module is used for preprocessing microblog texts; the hierarchical sequence model is used for training bidirectional recurrent neural network models and training inputted microblog texts by the aid of bidirectional LSTM (long shortterm memory) networks; the word encoder layer is used for vectorizing various words in sentences and forming preliminary vector representation; the sentence level feature solving layer is used for constructing static feature vectors for microblog sentences, linking the static feature vectors of the microblog sentences with neural network dynamic features of the sentence level feature solving layer and forming microblog sentence vector representation; the topic level feature solving layer is used for constructing static feature vectors for topics, linking the static feature vectors of the topics with neural network dynamic features of the topic level feature solving layer and forming topic vector representation; the topic predicting module is used for predicting the topics. The emerging hot topic detection system has the advantages that the emerging hot topic detection system is based on bidirectional long short term memory network architecture, the corresponding dynamic features and the corresponding static features are added, and accordingly the emerging hot topic detection capability can be improved.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to an emerging hot topic detection system based on multi-category feature fusion. Background technique [0002] At present, there are some emerging hot topic detection methods that are biased towards topic content features (static features). The growth rate, etc., are used as real features, and then use a judgment function (such as a classification algorithm) to determine whether it is an emerging hot topic. [0003] At present, there are still some biases that use the propagation characteristics of topics to detect emerging hot topics. The basic idea is to use related specific data structures (such as: trees, graphs, particle swarms, neural networks, etc.) to calculate or train topics. Features, here the features tend to be disseminated, that is, there is a connection between the data, not static. Then use the classification algorithm to find out whether the topic is an...

AI Technical Summary

Problems solved by technology

[0004] However, although these method models have achieved corresponding results to a certain extent, they have also promoted the development of topic detection tasks; but there are also shortcomings. Methods based on static characteristics of topic content are certainly accurate in predicting emerging hot topics. rate, but it lacks the contextual semantic analysis of the topic text, so the tracking effect of the topic is poor

Those based on propagation features (dynamic features) also take into account the contextual semantic information of the text in the topic, and there is a certain delay in the prediction time of emerging hot topics, so its accuracy is not enough, but it has better performance in topic tracking

Images