Unified Classification Model for Geotagging Websites
The paper presents a novel approach to finding regional scopes (geotagging) of websites. Unlike the traditional approaches, which generally involve training a separate classification model for each class (region), the proposed method is based on training a single model which is used for all regions...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Yaroslavl State University
2013-04-01
|
Series: | Modelirovanie i Analiz Informacionnyh Sistem |
Subjects: | |
Online Access: | https://www.mais-journal.ru/jour/article/view/207 |
id |
doaj-acb523dead6340e59ae5f17ce916a671 |
---|---|
record_format |
Article |
spelling |
doaj-acb523dead6340e59ae5f17ce916a6712021-07-29T08:15:18ZengYaroslavl State UniversityModelirovanie i Analiz Informacionnyh Sistem1818-10152313-54172013-04-01202809110.18255/1818-1015-2013-2-80-91201Unified Classification Model for Geotagging WebsitesA. N. Volkov0Yandex LLCThe paper presents a novel approach to finding regional scopes (geotagging) of websites. Unlike the traditional approaches, which generally involve training a separate classification model for each class (region), the proposed method is based on training a single model which is used for all regions of the same type (e.g. cities). This approach is made possible by the usage of ”relative” features which indicate how a selected region matches up to other regions for a given website. The classification system uses a variety of features of different nature that have not been yet used together for machine-learning based regional classification of websites. The evaluation demonstrates the advantage of our ”one model per region type” method versus the traditional ”one model per region” approach. A separate experiment demonstrates the ability of the proposed classifier to successfully detect regions which were not present in the training set (which is impossible for traditional approaches).https://www.mais-journal.ru/jour/article/view/207geotaggingclassification modelsmachine learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
A. N. Volkov |
spellingShingle |
A. N. Volkov Unified Classification Model for Geotagging Websites Modelirovanie i Analiz Informacionnyh Sistem geotagging classification models machine learning |
author_facet |
A. N. Volkov |
author_sort |
A. N. Volkov |
title |
Unified Classification Model for Geotagging Websites |
title_short |
Unified Classification Model for Geotagging Websites |
title_full |
Unified Classification Model for Geotagging Websites |
title_fullStr |
Unified Classification Model for Geotagging Websites |
title_full_unstemmed |
Unified Classification Model for Geotagging Websites |
title_sort |
unified classification model for geotagging websites |
publisher |
Yaroslavl State University |
series |
Modelirovanie i Analiz Informacionnyh Sistem |
issn |
1818-1015 2313-5417 |
publishDate |
2013-04-01 |
description |
The paper presents a novel approach to finding regional scopes (geotagging) of websites. Unlike the traditional approaches, which generally involve training a separate classification model for each class (region), the proposed method is based on training a single model which is used for all regions of the same type (e.g. cities). This approach is made possible by the usage of ”relative” features which indicate how a selected region matches up to other regions for a given website. The classification system uses a variety of features of different nature that have not been yet used together for machine-learning based regional classification of websites. The evaluation demonstrates the advantage of our ”one model per region type” method versus the traditional ”one model per region” approach. A separate experiment demonstrates the ability of the proposed classifier to successfully detect regions which were not present in the training set (which is impossible for traditional approaches). |
topic |
geotagging classification models machine learning |
url |
https://www.mais-journal.ru/jour/article/view/207 |
work_keys_str_mv |
AT anvolkov unifiedclassificationmodelforgeotaggingwebsites |
_version_ |
1721256602152992768 |