Social Tagging Analytics for Processing Unlabeled Resources:A Case Study on Non-geotagged Photos

Abstract

Abstract. Social networking services (SNS) have been an important sources of geotagged resources. This paper proposes Naive Bayes method-based framework to predict the locations of non-geotagged resources on SNS. By computing TF-ICF weights (Term Frequency and Inverse Class Frequency) of tags, we discover meaningful associations between the tags and the classes (which refer to sets of locations of the resources). As the experimental result, we found that the proposed method has shown around 75% of accuracy, with respect to F1 measurement.

Examining the Density and Diversity of Human Activity in the Built Environment: The Case of the Pearl River Delta, China

“…Geo-data mining from open sources has been a huge breakthrough in measuring human activity, economy, culture, transport, and entertainment [64]. It goes hand in hand with information technology [56,61,[65][66][67][68], which makes it possible to carry out quantitative analyses of crowd activities and spatial distribution with the help of Weibo.com, the Chinese equivalent of Twitter, and other Social Networking Services (SNS) tools. At present, there are lots of studies on traveling residents, the data of which are usually derived from telecom operators, social networking sites, taxis, and bus IC cards [69][70][71].…”

Exploiting geotagged resources for spatial clustering on social network services

“…This makes it easy for users to recommend and to find new locations easily. Although shared data that includes locations can be of benefit to users [5,7,8], some of our previous research focusing [9][10][11] on Flickr and on practical uses (as shown in Figure 1) has shown that data resources on social networking services only have a very small amount of images (less than 10%) that contain geographical location. Therefore, it is difficult to study the extraction, use, and mining of information from social big data.…”