Extraction method aiming at Twitter text event

Abstract

The invention discloses an extraction method aiming at a Twitter text event and mainly includes the following steps: step 1, collecting tweet data from a Twitter platform and saving the data into a database; step 2, carrying out duplicated data deleting and text preprocessing; step 3, carrying out event message identification and joint moment extraction, including event message identification based on trigger word matching, time expression identification, toponym entity identification based on lexicon, entity extraction based on lexicon and activity theme extraction. The invention uses the event factor extraction method based on rules, and for each event, marks its event factors, which mainly are event occurrence time, place, entity and activity theme, and makes event extraction to the tweets collected more accurately and realizes fast detection and finding of the event.

Description

technical field [0001] The invention belongs to the field of information technology and relates to a method for extracting Twitter text events. Background technique [0002] A large number of different social events occur in the world every day, which bring pros and cons and different degrees of impact on daily life and social order. Among them, mass protests such as marches, sit-ins, strikes, school strikes, city strikes, and "occupations" often have a greater or lesser impact on social stability, and some even cause turmoil and result in disastrous consequences. Take the "Arab Spring" movement that broke out in North Africa and the Middle East a few years ago as an example. This event triggered two years of turmoil across several countries, leaving countless people displaced, trapped, and even involved in wars and lost their lives. , and its subsequent role is still continuing in the Middle East and North Africa. [0003] Because it is closely related to human life, peop...

AI Technical Summary

Problems solved by technology

The problems of the former method are: confuse events with topics, use word frequency vectors or probability distributions of keywords (mainly entity names and trigger words) to describe events formally, and use unsupervised clustering to realize event discovery. As a result, what is detected is often a collection of a series of events (actually topics), and the detection results generally do not contain important information such as the time and place of the incident, the participating groups, etc.

The problem with the latter method is that since the time and location constraints are usually not added to the event message identification process, what is detected is often only a collection of event tweets, and generally cannot directly provide important information such as the time and location of the incident.

Images