Cluster-based language detection

摘要

Techniques for determining one or more preferred languages for a user are provided. The preferred languages may be determined based upon a set of language indicators. The language indicators are analyzed using, for example, rules-based techniques, clustering, language classifiers, and the like, or combinations thereof. Language indicators can include or be derived from information about the user's behavior, location, preferences, social connections, or other data related to the user.

主权项

1. A computer-implemented method comprising:
obtaining a set of attribute clusters, each cluster associated with a language and each cluster comprising a definition of first a set of language indicators shared among a plurality of users who have a common preferred language; obtaining a user profile for a user that contains a second set of language indicators, each language indicator related to a language potentially preferred by the user; by a processor, applying a clustering algorithm to the user profile to associate it with one of the set of attribute clusters having a highest correlation with the second set of language indicators, wherein the highest correlation indicates the likely language preference of the user is more similar to a language preference of users in the one of the set of attribute clusters than to a language preference of users in at least one other of the set of attribute clusters; and localizing a first application based upon the language associated with the cluster to which the user profile is associated, by performing at least one localization selected from the group consisting of: setting a language of at least one user interface element in the first application, setting a default input language for the user, setting a date format, setting a time format, setting a sort order, and setting a writing directionality.