Event graph construction method based on social media

Abstract

The invention provides an event graph construction method based on social media. The method comprises the steps of firstly, performing multi-source data preprocessing; secondly performing multi-sourceevent information extraction on preprocessed data; thirdly, judging a relation between events through event relation evaluation; and finally, performing entity information fusion, and performing attribute complementation on entities in a heterogeneous graph. According to the method, the events are regarded as the abstract entities; basic elements of the events are extracted based on text data pairs of the social media; the events are associated; an existing structured knowledge base is fused to construct an event graph, so that more comprehensive and more direct event-oriented information retrieval services can be provided, and by converting the research of traditional non-structured text contents into the graph-based research, the exploration of deeper information is facilitated.

Description

technical field [0001] The present invention relates to a method for building an event map, in particular to a method for building an event map based on social media. Background technique [0002] With the rapid popularization of the Internet, various social network media, such as blogs, wikis, podcasts, forums, social networks, content communities, etc., have flourished. These social media have become the most important channels for people to release, obtain, and disseminate event information. The sorting and research of these events will help people understand the law of event development and guide production and life. It also has a wide range of needs and applications in fields such as news recommendation and public opinion analysis. However, the explosive growth of data sources and data volume means richer information, but the characteristics of unstructured organization and low value density also bring challenges to event information mining, transforming these data into...

AI Technical Summary

Problems solved by technology

[0003] From the overall situation of data sources, the current event data in social network media are often scattered in various unstructured web pages, containing a large amount of useless data, which is not conducive to the effective analysis and utilization of information. It mainly has the following three problems: ①The information redundancy is high but the value density is low, and the web page data is noisy; ②The data scale is large and scattered, making it difficult to efficiently query and obtain massive event data; ③Lack of uniform specifications, it is difficult to find the hierarchical structure and correlation between information

However, the event extraction technology only performs superficial processing on the text, and the final product is mainly the event library, which does not go deep into the semantic level. Give full play to the advantages of multi-source data to enrich the element information in the event database and increase the value density of information

Images