Method, computer program and computer for estimating location based on social media

摘要

To provide a technique to estimate a location relating to a user who has not filled in information about the location in a profile field in social media such as a microblog.;A method for estimating association between a user in social media and a location includes the steps of acquiring a first content posted to the social media by a first user associated with a first location, determining regional localization of the first content on the basis of the first location, acquiring a second content posted to the social media by a second user not associated with a location, determining the degree of a relationship between the first content and the second content, and associating the first location with the second user on the basis of the localization and the degree of the relationship.

主权项

1. A method for estimating association between a user in social media and a location, the method comprising the steps of:
acquiring, at a processor device, via a network connection, a first content posted to a social media server device by a first user associated with a first location, the posted social media content including a profile associated with each user and the profile including a location field; determining, at the processor device, regional localization of the first content on a basis of the first location, the regional localization determining comprising:
computing a base distribution indicating a regional distribution of the first content randomly extracted, the base distribution computing comprising:
acquiring a placename filled in the location field associated with a user who posted the first content randomly extracted;accessing, from a storage device, a placename dictionary indicating association between a placename and a pair of geographic latitude and longitude coordinates to obtain a pair of geographic latitude and longitude coordinates corresponding to the acquired placename on the basis of the acquired placename; andidentifying a single cell corresponding to the acquired pair of geographic latitude and longitude coordinates among a plurality of cells into which a geographic area of interest is divided in advance;computing an event distribution indicating a regional distribution of the first content relating to a particular event; anddetermining regional localization of the first content on the basis of a difference between the base distribution and the event distribution; acquiring, at the processor device, a second content posted to the social media by a second user not associated with a location; determining, at the processor device, the degree of a relationship between the first content and the second content; and associating, at the processor device, the first location with the second user on the basis of the localization and the degree of the relationship.