@inproceedings{b24a62bd70c34ad5a46cb8664257b269,
title = "Machine learning to improve retrieval by category in big volunteered geodata",
abstract = "Nowadays, Volunteered Geographic Information (VGI) is commonly used in research and practical applications. However, the quality assurance of such a geographic data remains a problem. In this study we use machine learning and natural language processing to improve record retrieval by category (e.g. restaurant, museum, etc.) from Wikimapia Points of Interest data.We use textual information contained in VGI records to evaluate its ability to determine the category label. The performance of the trained classifier is evaluated on the complete dataset and then is compared with its performance on regional subsets. Preliminary analysis shows significant difference in the classifier performance across the regions. Such geographic differences will have a significant effect on data enrichment efforts such as labeling entities with missing categories.",
keywords = "Crowd-sourcing, Machine learning, Natural language processing",
author = "Alex Sorokine and Gautam Thakur and Rachel Palumbo",
note = "Publisher Copyright: {\textcopyright} 2018 Copyright held by the owner/author(s).; 12th Workshop on Geographic Information Retrieval, GIR 2018 ; Conference date: 06-11-2018",
year = "2018",
month = nov,
day = "6",
doi = "10.1145/3281354.3281358",
language = "English",
series = "Proceedings of the 12th Workshop on Geographic Information Retrieval, GIR 2018",
publisher = "Association for Computing Machinery, Inc",
editor = "Jones, {Christopher B.} and Purves, {Ross S.}",
booktitle = "Proceedings of the 12th Workshop on Geographic Information Retrieval, GIR 2018",
}