A POI Categorization by Composition of Onomastic and Contextual Information

Choi, Su Jeong; Song, Hyun Je; Park, Seong-Bae; Lee, Sang Jo

doi:10.1109/wi-iat.2014.78

Cited by 7 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Oftentimes, several POIs either lack labels about their category or are erroneously categorized (e.g., a nightclub classified as a cultural space). Commonly, machine learning (ML) classifiers are employed to label POIs with a place category (Choi et al, 2020;Giannopoulos et al, 2019). Pre-labeled POI data from a single or multiple data sources serve as the baseline for the categorization of unlabeled or mislabeled POIs.…”

Section: Poi Labeling and Categorizationmentioning

confidence: 99%

“…The process involves extraction of features from annotated POI data and their representation as feature vectors, which are used to train the labeling classifier. Common approaches to POI classification use either several or limited features (Lu et al, 2020;Choi et al, 2020). Recent evidence suggests that different features have a varying influence on the classification results (Milias & Psyllidis, 2021).…”

Section: Poi Labeling and Categorizationmentioning

confidence: 99%

See 1 more Smart Citation

Points of Interest (POI): a commentary on the state of the art, challenges, and prospects for the future

Psyllidis

Gao

et al. 2022

Comput.Urban Sci.

View full text Add to dashboard Cite

In this commentary, we describe the current state of the art of points of interest (POIs) as digital, spatial datasets, both in terms of their quality and affordings, and how they are used across research domains. We argue that good spatial coverage and high-quality POI features — especially POI category and temporality information — are key for creating reliable data. We list challenges in POI geolocation and spatial representation, data fidelity, and POI attributes, and address how these challenges may affect the results of geospatial analyses of the built environment for applications in public health, urban planning, sustainable development, mobility, community studies, and sociology. This commentary is intended to shed more light on the importance of POIs both as standalone spatial datasets and as input to geospatial analyses.

show abstract

Section: Poi Labeling and Categorizationmentioning

confidence: 99%

Section: Poi Labeling and Categorizationmentioning

confidence: 99%

Points of Interest (POI): a commentary on the state of the art, challenges, and prospects for the future

Psyllidis

Gao

et al. 2022

Comput.Urban Sci.

View full text Add to dashboard Cite

show abstract

“…Four different classification ensembles, namely SVM, kNN, clustering+SVM and clustering+kNN, were tested and achieved 60% accuracy for top-1 recommendation on 1400 categories. A POI categorization method that incorporates both onomastic and local contextual information as POI features was proposed by Choi et al (2014). Although the method achieved high accuracy of 73.053%, their method requires additional POI contextual information, such as online reviews, thus not applicable for a large-scale setting where an abundance of metadata is not usually available.…”

Section: Introductionmentioning

confidence: 99%

Large-scale Vietnamese point-of-interest classification using weak labeling

Tran¹,

Le²,

Pham³

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Point-of-Interests (POIs) represent geographic location by different categories (e.g., touristic places, amenities, or shops) and play a prominent role in several location-based applications. However, the majority of POIs category labels are crowd-sourced by the community, thus often of low quality. In this paper, we introduce the first annotated dataset for the POIs categorical classification task in Vietnamese. A total of 750,000 POIs are collected from WeMap, a Vietnamese digital map. Large-scale hand-labeling is inherently time-consuming and labor-intensive, thus we have proposed a new approach using weak labeling. As a result, our dataset covers 15 categories with 275,000 weak-labeled POIs for training, and 30,000 gold-standard POIs for testing, making it the largest compared to the existing Vietnamese POIs dataset. We empirically conduct POI categorical classification experiments using a strong baseline (BERT-based fine-tuning) on our dataset and find that our approach shows high efficiency and is applicable on a large scale. The proposed baseline gives an F1 score of 90% on the test dataset, and significantly improves the accuracy of WeMap POI data by a margin of 37% (from 56 to 93%).

show abstract

Learning Domain Driven and Semantically Enriched Embeddings for POI Classification

Giannopoulos

Meimaris

2019

Proceedings of the 16th International Symposium on Spatial and Temporal Databases

View full text Add to dashboard Cite

A POI Categorization by Composition of Onomastic and Contextual Information

Cited by 7 publications

References 15 publications

Points of Interest (POI): a commentary on the state of the art, challenges, and prospects for the future

Points of Interest (POI): a commentary on the state of the art, challenges, and prospects for the future

Large-scale Vietnamese point-of-interest classification using weak labeling

Learning Domain Driven and Semantically Enriched Embeddings for POI Classification

Contact Info

Product

Resources

About