Tagging is an important way for users to succinctly describe the content they upload to the Internet. However, most tag-suggestion systems recommend words that are highly correlated with the existing tag set, and thus add little information to a user’s contribution. This paper describes a means to determine the ambiguity of a set of (user-contributed) tags and suggests new tags that disambiguate the original tags. We introduce a probabilistic framework that allows us to find two tags that appear in different contexts but are both likely to co-occur with the original tag set. If such tags can be found, the current description is considered “ambiguous” and the two tags are recommended to the user for further clarification. In contrast to previous work, we only query the user when information is most needed and good suggestions are available. We verify the efficacy of our approach using geographical, temporal and semantic metadata, and a user study. We built our system using statistics from a large (100M) database of images and their tags.

Tags are an important part of today’s multimedia databases. They are often contributed by users when they submit an image or video and form a key part of the search experience. Content-based multimedia search remains out of reach, and a simple tag like “Tokyo” provides more information than we can possibly glean from content-based algorithms. Thus, making it as easy as possible for users to enter tags alongside multimedia content is important. This work addresses the problem of eliciting high-quality tags from users.

There have been numerous efforts to suggest tags to users [4, 15, 17, 19]. A common method is to suggest the most likely co-occuring tags. However, in many cases, the most likely tag is also the most obvious and least informative. For example, given the tag “goldengate,” another common tag is“sanfrancisco,” but this tag does not add any new information. Instead, we want to ask the user if they want to add “night,”“sunny” or “fog”.

Download pdf Resolving Tag Ambiguity