Assessing geographic relevance for mobile search: A computational model and its validation via crowdsourcing

The selection and retrieval of relevant information from the information universe on the web is becoming increasingly important in addressing information overload. It has also been recognized that geography is an important criterion of relevance, leading to the research area of geographic information retrieval. As users increasingly retrieve information in mobile situations, relevance is often related to geographic features in the real world as well as their representation in web documents. We present 2 methods for assessing geographic relevance (GR) of geographic entities in a mobile use context that include the 5 criteria topicality, spatiotemporal proximity, directionality, cluster, and colocation. To determine the effectiveness and validity of these methods, we evaluate them through a user study conducted on the Amazon Mechanical Turk crowdsourcing platform. An analysis of relevance ranks for geographic entities in 3 scenarios produced by two GR methods, 2 baseline methods, and human judgments collected in the experiment reveal that one of the GR methods produces similar ranks as human assessors.