Mueller, J.; Doerfel, S.; Becker, M.; Hotho, A. & Stumme, G.: Tag Recommendations for SensorFolkSonomies. Recommender Systems and the Social Web Workshop at 7th ACM Conference on Recommender Systems, RecSys 2013, Hong Kong, China - October 12-16, 2013. Proceedings. ACM, 2013, S. New York, NY, USA
With the rising popularity of smart mobile devices, sensor data-based
pplications have become more and more popular. Their users record
ata during their daily routine or specifically for certain events.
he application WideNoise Plus allows users to record sound samples
nd to annotate them with perceptions and tags. The app is being
sed to document and map the soundscape all over the world. The procedure
f recording, including the assignment of tags, has to be as easy-to-use
s possible. We therefore discuss the application of tag recommender
lgorithms in this particular scenario. We show, that this task is
undamentally different from the well-known tag recommendation problem
n folksonomies as users do no longer tag fix resources but rather
ensory data and impressions. The scenario requires efficient recommender
lgorithms that are able to run on the mobile device, since Internet
onnectivity cannot be assumed to be available. Therefore, we evaluate
he performance of several tag recommendation algorithms and discuss
heir applicability in the mobile sensing use-case.
@inproceedings{mueller2013recommendations,
author = {Mueller, Juergen and Doerfel, Stephan and Becker, Martin and Hotho, Andreas and Stumme, Gerd},
title = {Tag Recommendations for SensorFolkSonomies},
booktitle = {Recommender Systems and the Social Web Workshop at 7th ACM Conference on Recommender Systems, RecSys 2013, Hong Kong, China -- October 12-16, 2013. Proceedings},
publisher = {ACM},
year = {2013},
pages = {New York, NY, USA},
note = {accepted for publication},
keywords = {2013, RecSys, everyaware, folksonomy, myown, recommendation, rsweb, sensor, tag, widenoise},
abstract = {With the rising popularity of smart mobile devices, sensor data-based
pplications have become more and more popular. Their users record
ata during their daily routine or specifically for certain events.
he application WideNoise Plus allows users to record sound samples
nd to annotate them with perceptions and tags. The app is being
sed to document and map the soundscape all over the world. The procedure
f recording, including the assignment of tags, has to be as easy-to-use
s possible. We therefore discuss the application of tag recommender
lgorithms in this particular scenario. We show, that this task is
undamentally different from the well-known tag recommendation problem
n folksonomies as users do no longer tag fix resources but rather
ensory data and impressions. The scenario requires efficient recommender
lgorithms that are able to run on the mobile device, since Internet
onnectivity cannot be assumed to be available. Therefore, we evaluate
he performance of several tag recommendation algorithms and discuss
heir applicability in the mobile sensing use-case.}
}