Geotag propagation in social networks based on user trust model

Abstract

In the past few years sharing photos within social networks has become very popular. In order to make these huge collections easier to explore, images are usually tagged with representative keywords such as persons, events, objects, and locations. In order to speed up the time consuming tag annotation process, tags can be propagated based on the similarity between image content and context. In this paper, we present a system for efficient geotag propagation based on a combination of object duplicate detection and user trust modeling. The geotags are propagated by training a graph based object model for each of the landmarks on a small tagged image set and finding its duplicates within a large untagged image set. Based on the established correspondences between these two image sets and the reliability of the user, tags are propagated from the tagged to the untagged images. The user trust modeling reduces the risk of propagating wrong tags caused by spamming or faulty annotation. The effectiveness of the proposed method is demonstrated through a set of experiments on an image database containing various landmarks.

In Tags We Trust: Trust modeling in social tagging of multimedia content

“…In centralized trust systems, users' trust models are maintained by one central authority, i.e., manager, while in distributed trust systems each user maintains his/her own trust manager based on the previous interactions with other users. Distributed trust models are mainly used in P2P networks [15], while social networks usually use centralized systems (e.g., [18], [27], [24], and [30]). …”

“…The DomFp feature (likelihood that a content is spam based on its structure) also appeared important but may not be available since it relies on an infrastructure to enable access to the content, and therefore its feasibility depends on the circumstances of a particular social tagging system. Recently, Ivanov et al [24] explored features extracted from the knowledge accumulated in photo sharing social networks such as Panoramio [44]. They proposed an approach to model the user trust by making use of the feedback from other users who agree or disagree with a tag associated with an image.…”

“…Not all data sets for trust modeling have large-scale data. For example, Ivanov et al [24] argued that their approach requires a small number of images to learn models for geotag propagation with user trust modeling, and they evaluated their approach on a data set of 1,320 images of famous landmarks downloaded from Google Images [46], Flickr, and Wikipedia [47], and 44 users who annotated images.…”

“…To speed up this time-consuming manual tagging process, geotags can be propagated based on the similarity between image content (usually famous landmarks) and context (associated geotags). Ivanov et al [24] developed an efficient system for automatic geotag propagation in images by associating locations with distinctive landmarks and using object duplicate detection. The system overview is shown in Figure 4.…”

Spam Fighting in Social Tagging Systems

“…For example, tag recommendation approaches suggest appropriate tags to resources (e.g., videos) in order to make it easy for users to search and access information in social systems [11]. In order to speed up the time-consuming manual tagging process, tags can be automatically assigned to images by making use of tag propagation techniques based on the similarity between image content (e.g., famous landmarks) and its context (e.g., associated geotags) [7]. Since user-contributed tags are known to be uncontrolled, ambiguous and personalized, one of the fundamental issues in tagging is how to reliably determine the relevance of a tag with respect to the content it is describing [1].…”