In Situ Text Summarisation for Museum Visitors
18798Authors
nan
Abstract
. This paper presents an experiment on in situ summarisation in a museum context. We implement a range of standard summarisation algorithms, and use them to generate sum- maries for individual exhibit areas in a museum, intended for in situ delivery to a museum visitor on a mobile device. Personalisation is relative to a visitor’s preference for summary length, the visitor’s relative interest in a given exhibit topic, as well as (optionally) the sum- mary history. We find that the best-performing summarisation strategy is the Centroid algo- rithm, and that content diversification and customisation of summary length have a significant impact on user ratings of summary quality. 1
Keywords
Full Content
12 In Situ Text Summarisation for Museum Visitors Timothy Baldwin a, Patrick Ye a b, Fabian Bohnert b, and Ingrid Zukerman b aDepartment of Computer Science and Software Engineering The University of Melbourne, Australia tb@ldwin.net ye.patrick@gmail.com bFaculty of Information Technology Monash University, Australia {fabian.bohnert,ingrid.zukerman}@monash.edu Abstract. This paper presents an experiment on in situ summarisation in a museum context. We implement a range of standard summarisation algorithms, and use them to generate sum- maries for individual exhibit areas in a museum, intended for in situ delivery to a museum visitor on a mobile device. Personalisation is relative to a visitor’s preference for summary length, the visitor’s relative interest in a given exhibit topic, as well as (optionally) the sum- mary history. We find that the best-performing summarisation strategy is the Centroid algo- rithm, and that content diversification and customisation of summary length have a significant impact on user ratings of summary quality. 1 Introduction With the increasing saturation of mobile technology, museums and other cultural heritage institu- tions are increasingly looking to deliver content to visitors via their personal mobile device. This has led to a move away from a traditional mode of content delivery via static information on plac- ards in the museum space, to interactive applications on mobile devices supporting path finding, social networking and personalised content delivery (Burnette et al., 2011; Filippini-Fantoni et al., 2011). This paper explores the feasibility and utility of in situ personalised content delivery in a mu- seum context, focusing on document summarisation. Museums provide a compelling context for in situ summarisation, as visitors often wish to access key information relevant to their immediate surroundings, but want to avoid information overload. Personalised summarisation is an integral component of museum content delivery, as exhibits are typically associated with vast amounts of curated information, predominantly in textual form. This can range from simple tabular infor- mation such as the date of acquisition of an exhibit, to full-length research articles published by museum curators/researchers relating to the exhibit. Personalised summarisation offers the possi- bility to present the most salient facets of information to a visitor, according to their interests and preferences. The pragmatic choice of a mobile device such as a smart phone to deliver the content poses challenges in terms of the amount of content that can be effectively presented to the visitor (Yang and Wang, 2003; Otterbacher et al., 2006). Personalised summarisation should ideally be coupled with tracking/geolocating technology to be situation aware (Bohnert et al., 2008; Bohnert and Zukerman, 2009; Bickersteth and Ainsley, 2011) and take place interactively (Callaway et al., 2005). In principle, any evaluation should take place in situ as part of an actual museum visit. However, in this preliminary research, we present the results of a web-based user study targeted at members of Melbourne Museum (Melbourne, ⋆ Copyright 2011 by Timothy Baldwin, Patrick Ye, Fabian Bohnert, and Ingrid Zukerman. ⋆⋆ This research was supported in part by grant no. DP0770931 from the Australian Research Council. The authors thank Carolyn Meehan and …
Content truncated to 500 words
Labeled Text
. This paper presents an experiment on in situ summarisation in a museum context. We implement a range of standard summarisation algorithms, and use them to generate summaries for individual exhibit areas in a museum, intended for in situ delivery to a museum visitor on a mobile device. Personalisation is relative to a visitor’s preference for summary length, the visitor’s relative interest in a given exhibit topic, as well as (optionally) the summary history. We find that the best-performing summarisation strategy is the Centroid algorithm, and that content diversification and customisation of summary length have a significant impact on user ratings of summary quality. 1
Publication Details
- Paper ID:
- 18798
- Year:
- 2011
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan