Documentation of art museum collections has been traditionally written by and for art historians. To make art museum collections broadly accessible, and to enable art museums to engage their communities, means of access need to reflect the perspectives of other groups and communities. Social Tagging (the collective assignment of keywords to resources) and its resulting Folksonomy (the assemblage of concepts expressed in such a cooperatively developed system of classification) offer ways for art museums to engage with their communities and to understand what users of on-line museum collections see as important. Proof of Concept studies at The Metropolitan Museum of Art compared terms assigned by trained cataloguers and untrained cataloguers to existing museum documentation, and explored the potential for social tagging to improve access to museum collections. These preliminary studies, the results of which are reported here, have shown the potential of social tagging and folksonomy to open museum collections to new, more personal meanings. Untrained cataloguers identified content elements not described in formal museum documentation. Results from these tests – the first in the domain – provided validation for exploring social tagging and folksonomy as an access strategy within The Metropolitan Museum, motivation to proceed with a broader inter-institutional collaboration, and input into the development of a multi-institutional collaboration exploring tagging in art museums. Tags assigned by users might help bridge the semantic gap between the professional discourse of the curator and the popular language of the museum visitor. The steve collaboration

Abstract. In this paper, we present a fully-implemented system using computational linguistic techniques to apply automatic text mining for the extraction of metadata for image access. We describe the implementation of a workbench created for, and evaluated by, image catalogers. We discuss the current functionality and future goals for this image catalogers ’ toolkit, developed in the Computational Linguistics for Metadata Building (CLiMB) research project. 1 Our primary user group for initial phases of the project is the cataloger expert; in future work we address applications for end users. 1 The Problem: Insufficient Subject Access to Images The CLiMB project addresses the existing gap in subject metadata for images, particularly for the domains of art history, architecture, and landscape architecture. Within each of these domains, image collections are increasingly available online yet subject access points for these images remain minimal, at best. In an initial observational study conducted with six image catalogers, we found that typically 1 – 8 subject terms are assigned, and many legacy records lack subject entries altogether.

This paper presents a qualitative study of domestic Webbased image use, and specifically asks why users access images online. This work is not limited to image search per se, but instead aims to understand holistically the circumstances in which images are accessed through Webbased tools. As such, we move beyond the existing information seeking literature, and instead provide contextual examples of image use as well as an analysis of both how and why images are used. The paper concludes with design recommendations that take into account this wider range of activities.

We present a system which applies text mining using computational linguistic techniques to automatically extract, categorize, disambiguate and filter metadata for image access. Candidate subject terms are identified through standard approaches; novel semantic categorization using machine learning and disambiguation using both WordNet and a domain specific thesaurus are applied. The resulting metadata can be manually edited by image catalogers or filtered by semi-automatic rules. We describe the implementation of this workbench created for, and evaluated by, image catalogers. We discuss the system's current functionality, developed under the Computational Linguistics for Metadata Building (CLiMB) research project. The CLiMB Toolkit has been tested

2. The CLiMB Toolkit........................................................................................................ 4

Some documents provoke emotions in people viewing them. Will it be possible to describe emotions consistently and use this information in retrieval systems? We tested collective (statistically aggregated) emotion indexing using images as examples. Considering psychological results, basic emotions are anger, disgust, fear, happiness, and sadness. This study follows an approach developed by Lee and Neal (2007) for music emotion retrieval and applies scroll bars for tagging basic emotions and their intensities. A sample comprising 763 persons tagged emotions caused by images (retrieved from www.Flickr.com) applying scroll bars and (linguistic) tags. Using SPSS, we performed descriptive statistics and correlation analysis. For more than half of the images, the test persons have clear emotion favorites. There are prototypical images for given emotions. The document-specific consistency of tagging using a scroll bar is, for some images, very high. Most of the (most commonly used) linguistic tags are on the basic level (in the sense of Rosch’s basic level theory). The distributions of the linguistic tags in our examples follow an inverse power-law. Hence, it seems possible to apply collective image emotion tagging to image information systems and to present a new search option for basic emotions. This article is one of the first steps in the research area of emotional information retrieval (EmIR).

Abstract not found

Building) project addresses the existing gap in subject metadata for images, particularly for the domains of art history, architecture, and landscape architecture. Within each of these domains, image collections are increasingly available online yet subject access points for these images remain minimal. In an observational study with six image catalogers, we found that typically 1 – 8 subject terms are assigned, and that many legacy records lack subject entries altogether. Studies on end users ’ image searching indicate that this level of subject description is often insufficient. In a study of the imagesearching behaviors of faculty and graduate students in American history, Choi and Rasmussen 2003 found that 92 % of the 38 participants in their study considered the textual information associated with the images in the Library of Congress ’ American Memory Collection to be inadequate. The number of subject descriptors assigned to an image in this collection is comparable to what we found in the exploratory CLiMB studies. Furthermore, these searchers submitted more subject-oriented queries than known-artist and title queries. Similar results demonstrating the importance of subject retrieval have been reported in other studies, including Keister, Collins, and