Social-network-oriented extraction method of specific events

Abstract

The invention discloses a social-network-oriented extraction method of specific events; on one hand, representation learning of text is achieved via a neural network, and characteristics of great generalization ability suitable for mass data are extracted; on the other hand, a supervised learning method used herein is more specific than a non-supervised learning method, event representations of good semantic clarity can be provided, mass event-irrelevant tweets are filtered using a keyword-based primary filter algorithm, and algorithm speed is increased; event sorting for the tweets is achieved using the neural network, artificial design characteristics are not required, and the algorithm has better generalization ability; hierarchical sorting from event type to event instance is constructed to form a systematic event system; an event instance cluster is subjected to information extraction, namely, event information is comprehensively extracted from different tweets in the same event,and the information is more comprehensive.

Description

technical field [0001] The invention belongs to the field of natural language processing, in particular to a social network-oriented specific event extraction method. Background technique [0002] As an emerging network application, social network has attracted a large number of users from all over the world. Users can publish and share text, pictures, audio, video and other information through social network, and pay attention to other people's dynamics. Twitter is one of the most active social platforms in recent years. As a microblogging application, Twitter allows users to edit their dynamics into short texts of less than 140 characters and post them on the website. Because Twitter has a large number of registered active users and a fast information sharing mode, the spread speed and influence range of emergencies or hot events on Twitter are far greater than traditional news media, so mining massive data on social networks is beneficial. Detect emergencies early and ex...

AI Technical Summary

Problems solved by technology

However, the signal of the event is weak before it is fermented, and it cannot form a spike signal in the social network, so the first method is difficult to detect the event in the early stage

Existing event detection algorithms based on unsupervised clustering mainly use a feature cluster to represent an event. This representation method is not very interpretable, and some are even meaningless clusters, which cannot provide a clear semantic event representation. And the similarity threshold and the number of clusters need to be set artificially based on experience, which has a great impact on the final result

Images