Tag expansion methods for photo-sharing websites

Abstract

Due to the fast development of affordable digital cameras and the new trend of sharing media through the web, large amounts of images have become available on the Internet. Thus, at a time when a single site alone hosts over 4 billion photos, the necessity of managing these massive numbers of photos for efficient and effective browsing/searching operations has increased. To properly organize large amounts of data, systems have been using collaborative tagging methods by assigning descriptive words, tags, to data and performing text-based search and retrieval operations on these words. Unfortunately, due to various reasons, both the amount and quality of these tags assigned by users are low. In this work, we present and analyze two applications of tag expansion methods on photo-sharing websites. The purpose of these methods is to assist users for proper tagging at upload time. The goal of the approaches is not to give users a complete set of tags that could be directly used but to give a list of, possibly, incomplete set of tags that would help or guide the users to tag in accordance with the image content. With this assistance, problems such as incorrect tagging and insufficient tagging are expected to be solved.