Subject matter categorization of tags applied to digital images from art museums

The cultural heritage sector has embraced social tagging as a way to increase both access to online content and to engage users with their digital collections. In this article, we build on two current lines of research. (a) We use Waisda?, an existing labeling game, to add timebased annotations to content. (b) In this context, we investigate the role of experts in human-based computation (nichesourcing). We report on a small-scale experiment in which we applied Waisda? to content from film archives. We study the differences in the type of timebased tags between experts and novices for film clips in a crowdsourcing setting. The findings show high similarity in the number and type of tags (mostly factual). In the less frequent tags, however, experts used more domain-specific terms. We conclude that competitive games are not suited to elicit real expert-level descriptions. We also confirm that providing guidelines, based on conceptual frameworks that are more suited to moving images in a time-based fashion, could result in increasing the quality of the tags, thus allowing for creating more tag-based innovative services for online audiovisual heritage.

Section: Discussionsupporting

confidence: 87%

Time‐based tags for fiction movies: comparing experts to novices using a video labeling game

Estrada

Hildebrand

Boer

et al. 2016

“…This problem may be solved by social tagging systems, one of the new approaches adopted by online museums. It presents opportunities to enhance user experience and level of engagement, helping to build a community and attract new audiences (Klavans, LaPlante, & Golbeck, 2014;Ridge, 2013;Trant, 2006). Furthermore, social tagging allows curators to understand artworks from the perspective of the audience and reduce the semantic gap with the novice audience (Cairns, 2013;Chae & Kim, 2011a).…”

Section: Social Tagging Systems For Artworkmentioning

confidence: 96%

Linking and clustering artworks using social tags: Revitalizing crowd‐sourced information on cultural collections

Chae

Park

et al. 2015

Social tagging is one of the most popular methods for collecting crowd-sourced information in galleries, libraries, archives, and museums (GLAMs). However, when the number of social tags grows rapidly, using them becomes problematic and, as a result, they are often left as simply big data that cannot be used for practical purposes. To revitalize the use of this crowdsourced information, we propose using social tags to link and cluster artworks based on an experimental study using an online collection at the Gyeonggi Museum of Modern Art (GMoMA). We view social tagging as a folksonomy, where artworks are classified by keywords of the crowd's various interpretations and one artwork can belong to several different categories simultaneously. To leverage this strength of social tags, we used a clustering method called "link communities" to detect overlapping communities in a network of artworks constructed by computing similarities between all artwork pairs. We used this framework to identify semantic relationships and clusters of similar artworks. By comparing the clustering results with curators' manual classification results, we demonstrated the potential of social tagging data for automatically clustering artworks in a way that reflects the dynamic perspectives of crowds.

“…Huang and Jörgensen () found that the popular tags in Flickr's general collection had a high number of generic objects and specific locations‐related tags and that the popular tags in the Library of Congress's Photostream in Flickr described more in the specific objects and time categories. By using tags for a collection of artwork images from the Steve museum project (http://www.steve.museum/), Klavans, LaPlante, and Golbeck () also show that the majority of tags described the people and objects in the image. These findings validate Jörgensen's () point that users describing images tend to be more concerned with describing specific image objects and scenes rather than their abstract meaning.…”

Section: Discussionmentioning

confidence: 99%

Characteristics of tagging behavior in digitized humanities online collections

Choi

Syn

2015

The purpose of this study was to examine user tags that describe digitized archival collections in the field of humanities. A collection of 8,310 tags from a digital portal (Nineteenth‐Century Electronic Scholarship, NINES) was analyzed to find out what attributes of primary historical resources users described with tags. Tags were categorized to identify which tags describe the content of the resource, the resource itself, and subjective aspects (e.g., usage or emotion). The study's findings revealed that over half were content‐related; tags representing opinion, usage context, or self‐reference, however, reflected only a small percentage. The study further found that terms related to genre or physical format of a resource were frequently used in describing primary archival resources. It was also learned that nontextual resources had lower numbers of content‐related tags and higher numbers of document‐related tags than textual resources and bibliographic materials; moreover, textual resources tended to have more user‐context‐related tags than other resources. These findings help explain users' tagging behavior and resource interpretation in primary resources in the humanities. Such information provided through tags helps information professionals decide to what extent indexing archival and cultural resources should be done for resource description and discovery, and understand users' terminology.