Method, system and device for discovering and tracking hot topics based on network media data stream

Abstract

The invention provides a method for discovering hot topics based on network media data stream. The method for discovering the hot topics based on the network media data stream comprises the followingsteps: obtaining plurality pieces of text data with different types in the current time window t from a network media platform according to a preset time interval, and preprocessing the obtained data;recognizing the category of each piece of preprocessed text data by means of a classification algorithm, and filtering each piece of text data according to the recognized categories; performing statistics on keyword co-occurrence relationship using each piece of preprocessed and filtered text data as the input; constructing or updating a corresponding keyword graph according to the statistical results of the keyword co-occurrence relationship; segmenting the keyword graph step by step according to a predetermined rule to obtain a series of sub-graphs as a candidate topic set; and performing clustering and merging based on the corresponding sub-graphs for each candidate topic in the candidate topic set to obtain the hot topics as the result. The invention also provides a system and devicefor discovering the hot topics based on the network media data stream.

Description

technical field [0001] The invention belongs to the technical field of Internet data mining, and in particular relates to a method, system and device for discovering and tracking hot topics based on network media data streams. Background technique [0002] The rapid development of computer, communication, and network technologies has continuously improved the performance of terminal equipment including PCs, tablet computers, smart phones, and Internet TVs. Correspondingly, Internet media, especially Internet social media, has gradually become one of the main ways for the public to obtain news and information due to its characteristics of diversity, speed, interactivity, easy replication, and multimedia. Internet social media, as a tool for people to communicate, is increasingly used to disseminate news reports, update personal status, publish witness records and exchange ideas. The amount of data on social media is growing rapidly at a rate of millions every day. How to dis...

AI Technical Summary

Problems solved by technology

[0003] However, the existing hot topic discovery and tracking technical solutions more or less have the following defects: 1) the data source is single, and the hot topics discovered are not comprehensive; The brevity and irregularity of social media data make the accuracy low; 3) For methods that simply define topics as commonly used / common keywords, phrases, hashtags, or articles at a specific time and place according to the type of source data, there are Insufficient analysis and description of the rich and semantic level of the topic, and tracking of the topic; 4) Segmentation of word co-occurrence graphs (word graphs for short) using graph search (such as breadth-first search) In order to realize the method of hot topic discovery, due to the large size of the word graph, the complexity of the graph search algorithm is high, and the algorithm efficiency is low

Images