On The Role Of User-Generated Metadata In Audio Visual Collections. Gligarov, R., Hildebrand, M., van Ossenbruggen, J. R., Schreiber, G., & Aroyo, L. In Proceedings of the International Conference on Knowledge Capture 2011, pages 145 - 151, June, 2011. ACM Press.
Paper abstract bibtex Recently, various crowdsourcing initiatives showed that targeted efforts of user communities result in massive amounts of tags. For example, the Netherlands Institute for Sound and Vision collected a large number of tags with the video labeling game \emphWaisda?. To successfully utilize these tags, a better understanding of their characteristics is required. The goal of this paper is twofold: (i) to investigate the vocabulary that users employ when describing videos and compare it to the vocabularies used by professionals; and (ii) to establish which aspects of the video are typically described and what type of tags are used for this. We report on an analysis of the tags collected with \emphWaisda?. With respect to the first goal, we compared the the tags with a typical domain thesaurus used by professionals, as well as with a more general vocabulary. With respect to the second goal, we compare the tags to the video subtitles to determine how many tags are derived from the audio signal. In addition, we perform a qualitative study in which a tag sample is interpreted in terms of an existing annotation classification framework. The results suggest that the tags complement the metadata provided by professional cataloguers, the tags describe both the audio and the visual aspects of the video, and the users primarily describe objects in the video using general descriptions.
@inproceedings{18476,
author = {Gligarov, R. and Hildebrand, M. and van Ossenbruggen, J. R. and Schreiber, G. and Aroyo, L.},
title = {On {The} {Role} {Of} {User-}{Generated} {Metadata} {In} {Audio} {Visual} {Collections}},
booktitle = {Proceedings of the International Conference on Knowledge Capture 2011},
conferencetitle = {International Conference on Knowledge Capture},
conferencedate = {2011, June 25 - June 29},
conferencelocation = {Banff, Canada},
pages = {145 - 151},
year = {2011},
month = {June},
publisher = {ACM Press},
isbn = {978-1-4503-0396-5},
refereed = {y},
size = {7p.},
class = { H.2.5; J.5},
group = {INS2},
language = {en},
abstract = {Recently, various crowdsourcing initiatives showed that targeted efforts of
user communities result in massive
amounts of tags. For example, the
Netherlands Institute for Sound and Vision collected a large number of tags
with the
video labeling game \emph{Waisda?}. To successfully utilize these
tags, a better understanding of their characteristics
is required.
The goal of this paper is twofold: (i) to investigate the vocabulary that
users employ when describing videos
and compare it to the vocabularies used by
professionals; and (ii) to establish which aspects of the video are typically
described
and what type of tags are used for this. We report on an analysis of
the tags collected with \emph{Waisda?}. With respect
to the first goal, we
compared the the tags with a typical domain thesaurus used by professionals,
as well as with a more
general vocabulary. With respect to the second goal, we
compare the tags to the video subtitles to determine how many tags
are derived
from the audio signal. In addition, we perform a qualitative study in which a
tag sample is interpreted in
terms of an existing annotation classification
framework. The results suggest that the tags complement the metadata provided
by
professional cataloguers, the tags describe both the audio and the visual
aspects of the video, and the users primarily
describe objects in the video
using general descriptions.
},
url = {http://oai.cwi.nl/oai/asset/18476/18476D.pdf},
url = {http://homepages.cwi.nl/%7Ejrvosse/publications/2011/kcap2011_gligorov.pdf},
}
Downloads: 0
{"_id":{"_str":"5211f22e44b2654d3d0000f7"},"__v":3,"authorIDs":["545cbba26aaec20d23000186","5NMn3nQtSs5PhrZNQ"],"author_short":["Gligarov, R.","Hildebrand, M.","van Ossenbruggen, J. R.","Schreiber, G.","Aroyo, L."],"bibbaseid":"gligarov-hildebrand-vanossenbruggen-schreiber-aroyo-ontheroleofusergeneratedmetadatainaudiovisualcollections-2011","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Gligarov"],"firstnames":["R."],"suffixes":[]},{"propositions":[],"lastnames":["Hildebrand"],"firstnames":["M."],"suffixes":[]},{"propositions":["van"],"lastnames":["Ossenbruggen"],"firstnames":["J.","R."],"suffixes":[]},{"propositions":[],"lastnames":["Schreiber"],"firstnames":["G."],"suffixes":[]},{"propositions":[],"lastnames":["Aroyo"],"firstnames":["L."],"suffixes":[]}],"title":"On The Role Of User-Generated Metadata In Audio Visual Collections","booktitle":"Proceedings of the International Conference on Knowledge Capture 2011","conferencetitle":"International Conference on Knowledge Capture","conferencedate":"2011, June 25 - June 29","conferencelocation":"Banff, Canada","pages":"145 - 151","year":"2011","month":"June","publisher":"ACM Press","isbn":"978-1-4503-0396-5","refereed":"y","size":"7p.","class":"H.2.5; J.5","group":"INS2","language":"en","abstract":"Recently, various crowdsourcing initiatives showed that targeted efforts of user communities result in massive amounts of tags. For example, the Netherlands Institute for Sound and Vision collected a large number of tags with the video labeling game \\emphWaisda?. To successfully utilize these tags, a better understanding of their characteristics is required. The goal of this paper is twofold: (i) to investigate the vocabulary that users employ when describing videos and compare it to the vocabularies used by professionals; and (ii) to establish which aspects of the video are typically described and what type of tags are used for this. We report on an analysis of the tags collected with \\emphWaisda?. With respect to the first goal, we compared the the tags with a typical domain thesaurus used by professionals, as well as with a more general vocabulary. With respect to the second goal, we compare the tags to the video subtitles to determine how many tags are derived from the audio signal. In addition, we perform a qualitative study in which a tag sample is interpreted in terms of an existing annotation classification framework. The results suggest that the tags complement the metadata provided by professional cataloguers, the tags describe both the audio and the visual aspects of the video, and the users primarily describe objects in the video using general descriptions. ","url":"http://homepages.cwi.nl/%7Ejrvosse/publications/2011/kcap2011_gligorov.pdf","bibtex":"@inproceedings{18476,\nauthor = {Gligarov, R. and Hildebrand, M. and van Ossenbruggen, J. R. and Schreiber, G. and Aroyo, L.},\ntitle = {On {The} {Role} {Of} {User-}{Generated} {Metadata} {In} {Audio} {Visual} {Collections}},\nbooktitle = {Proceedings of the International Conference on Knowledge Capture 2011},\nconferencetitle = {International Conference on Knowledge Capture},\nconferencedate = {2011, June 25 - June 29},\nconferencelocation = {Banff, Canada},\npages = {145 - 151},\nyear = {2011},\nmonth = {June},\npublisher = {ACM Press},\nisbn = {978-1-4503-0396-5},\nrefereed = {y},\nsize = {7p.},\nclass = { H.2.5; J.5},\ngroup = {INS2},\nlanguage = {en},\nabstract = {Recently, various crowdsourcing initiatives showed that targeted efforts of\r\nuser communities result in massive\n amounts of tags. For example, the\r\nNetherlands Institute for Sound and Vision collected a large number of tags\r\nwith the\n video labeling game \\emph{Waisda?}. To successfully utilize these\r\ntags, a better understanding of their characteristics\n is required.\r\nThe goal of this paper is twofold: (i) to investigate the vocabulary that\r\nusers employ when describing videos\n and compare it to the vocabularies used by\r\nprofessionals; and (ii) to establish which aspects of the video are typically\r\ndescribed\n and what type of tags are used for this. We report on an analysis of\r\nthe tags collected with \\emph{Waisda?}. With respect\n to the first goal, we\r\ncompared the the tags with a typical domain thesaurus used by professionals,\r\nas well as with a more\n general vocabulary. With respect to the second goal, we\r\ncompare the tags to the video subtitles to determine how many tags\n are derived\r\nfrom the audio signal. In addition, we perform a qualitative study in which a\r\ntag sample is interpreted in\n terms of an existing annotation classification\r\nframework. The results suggest that the tags complement the metadata provided\r\nby\n professional cataloguers, the tags describe both the audio and the visual\r\naspects of the video, and the users primarily\n describe objects in the video\r\nusing general descriptions.\r\n},\nurl = {http://oai.cwi.nl/oai/asset/18476/18476D.pdf},\nurl = {http://homepages.cwi.nl/%7Ejrvosse/publications/2011/kcap2011_gligorov.pdf},\n}\n\r\n\r\n\r\n","author_short":["Gligarov, R.","Hildebrand, M.","van Ossenbruggen, J. R.","Schreiber, G.","Aroyo, L."],"key":"18476","id":"18476","bibbaseid":"gligarov-hildebrand-vanossenbruggen-schreiber-aroyo-ontheroleofusergeneratedmetadatainaudiovisualcollections-2011","role":"author","urls":{"Paper":"http://homepages.cwi.nl/%7Ejrvosse/publications/2011/kcap2011_gligorov.pdf"},"metadata":{"authorlinks":{"van ossenbruggen, j":"https://bibbase.org/show?bib=http://homepages.cwi.nl/~jrvosse/publications/pubs.bib&proxy=1"}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"http://homepages.cwi.nl/~jrvosse/publications/pubs.bib","downloads":0,"keywords":[],"search_terms":["role","user","generated","metadata","audio","visual","collections","gligarov","hildebrand","van ossenbruggen","schreiber","aroyo"],"title":"On The Role Of User-Generated Metadata In Audio Visual Collections","title_words":["role","user","generated","metadata","audio","visual","collections"],"year":2011,"dataSources":["5GYijBLBgdYqK9T7H"]}