Improving Tag Suggestion for Places using Digital Map Data

Martin Garbe

2013

Abstract

Today, tagging photos and website bookmarks is widely used. Geographical data is an additional type of resource which can be tagged. Locations representing geographic information can be tagged depending on activities done there. In this paper we present an explorative study to answer the question whether geographical map data can be used to describe similarities between places. When map data can be used to identify similar places services like tag suggestion could be improved. For the study very detailed crowd-sourced map data was used. In a period of four month places were manually tagged with activities done. A measurement for finding places which are similar in the sense of tagging is also presented. To evaluate our idea, we trained three machine learning classifiers (Decision Tree, Support Vector Machine, Naive Bayes). With a precision of 73% and a recall of 65% Decision Tree performed best. Our results indicate that crowd-based map data can assist in tagging geographical resources and can improve tag suggestion services.

Paper Citation

in Harvard Style

Garbe M. (2013). Improving Tag Suggestion for Places using Digital Map Data . In Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST, ISBN 978-989-8565-54-9, pages 453-458. DOI: 10.5220/0004372104530458

in Bibtex Style

@conference{webist13,
author={Martin Garbe},
title={Improving Tag Suggestion for Places using Digital Map Data},
booktitle={Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,},
year={2013},
pages={453-458},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004372104530458},
isbn={978-989-8565-54-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST,
TI - Improving Tag Suggestion for Places using Digital Map Data
SN - 978-989-8565-54-9
AU - Garbe M.
PY - 2013
SP - 453
EP - 458
DO - 10.5220/0004372104530458