Inferring User Context from Spatio-Temporal Pattern Mining for Mobile Application Services

Recent research on geographical data mining that focuses on user behavior is lacking some fundamental aspects, measurements rely on large quantities of geographic data and lack contextual information. This work introduces a novel knowledge discovery architecture that brings together machine learning techniques with readily available information from popular Location Social Networks, in order to enrich geographical locations with context and add meaning to user behavior. Results show that through analysis of context enriched data we are capable of inferring context for detected user points of interest and patterns, such as where the user lives, works and spends his free time, without a large quantity of information or prior knowledge of the user and his private data.