Postal address extraction from the web: a comprehensive survey

Kayed, Mohammed; Dakrory, Sara; Ali, Abdelmgeid A.

doi:10.1007/s10462-021-09983-1

Cited by 6 publications

(4 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first study [11] mainly addresses the geographical coordinates' prediction of entire documents based on their textual contents, by conducting a survey on previous research in this field, with address geocoding being explicitly excluded from its scope, due to the significant difference in the used methods. As for the second of the mentioned studies [12], a review of different approaches to postal address extraction from the Web is performed with a twofold aim: firstly, to analyze the data quality of gazetteers (geographical dictionaries) like the Volunteered Geographical Information (VGI) based GeoNames (https://www.geonames.org/ (accessed on 9 November 2021)) and OpenStreetMap (https://www.openstreetmap.org (accessed on 9 November 2021)) [13]; secondly, to identify the factors that most hinder postal address extraction performance, including the diversity of styles and sources of addresses on the Web as well as their ambiguous and dynamic nature. The main conclusions point to the coverage of real Web pages and social networks with a view to obtain increased geographical knowledge on Points of Interest (restaurants, schools, hospitals, etc.…”

Section: Introductionmentioning

confidence: 95%

“…Bibliometric analysis is a particularly useful method to discover hot topics, trends, research gaps, top authors and institutions [10] and, to the best of our knowledge, no similar studies have been previously published in the field under analysis. However, a brief reference should be made to related surveys, namely in the field of geographic information extraction from textual documents [11] and unstructured and diverse data, such as addresses on the Web [12]. The first study [11] mainly addresses the geographical coordinates' prediction of entire documents based on their textual contents, by conducting a survey on previous research in this field, with address geocoding being explicitly excluded from its scope, due to the significant difference in the used methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Identification of Addresses: A Systematic Literature Review

Cruz

Vanneschi

Paìnho

et al. 2021

IJGI

View full text Add to dashboard Cite

Address matching continues to play a central role at various levels, through geocoding and data integration from different sources, with a view to promote activities such as urban planning, location-based services, and the construction of databases like those used in census operations. However, the task of address matching continues to face several challenges, such as non-standard or incomplete address records or addresses written in more complex languages. In order to better understand how current limitations can be overcome, this paper conducted a systematic literature review focused on automated approaches to address matching and their evolution across time. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed, resulting in a final set of 41 papers published between 2002 and 2021, the great majority of which are after 2017, with Chinese authors leading the way. The main findings revealed a consistent move from more traditional approaches to deep learning methods based on semantics, encoder-decoder architectures, and attention mechanisms, as well as the very recent adoption of hybrid approaches making an increased use of spatial constraints and entities. The adoption of evolutionary-based approaches and privacy preserving methods stand as some of the research gaps to address in future studies.

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 99%

Automatic Identification of Addresses: A Systematic Literature Review

Cruz

Vanneschi

Paìnho

et al. 2021

IJGI

View full text Add to dashboard Cite

show abstract

“…Then, an application can be chosen or developed that uses a particular identification strategy. In the case of postal addresses, the identification process varies from country to country [36].…”

Section: Information Identificationmentioning

confidence: 99%

Twitter Data Mining for the Diagnosis of Leaks in Drinking Water Distribution Networks

2023

View full text Add to dashboard Cite

This article presents a methodology for using data from social networks, specifically from Twitter, to diagnose leaks in drinking water distribution networks. The methodology involves the collection of tweets from citizens reporting leaks, the extraction of information from the tweets, and the processing of such information to run the diagnosis. To demonstrate the viability of this methodology, 358 Twitter leak reports were collected and analyzed in Mexico City from 1 May to 31 December 2022. From these reports, leak density and probability were calculated, which are metrics that can be used to develop forecasting algorithms, identify root causes, and program repairs. The calculated metrics were compared with those calculated through telephone reports provided by SACMEX, the entity that manages water in Mexico City. Results show that metrics obtained from Twitter and phone reports were highly comparable, indicating the usefulness and reliability of social media data for diagnosing leaks.

show abstract

“…As users utilize a natural language to communicate through the internet, this information appears in terms of qualitative descriptions of objects and events [12]. Although these descriptions rarely contain the spatial location of objects (e.g., in terms of postal addresses [13]), they may contain place names, spatial relations, and directions. Research on the extraction of spatial relations from textual content and natural languages has been growing rapidly in recent years [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Get Spatial from Non-Spatial Information: Inferring Spatial Information from Textual Descriptions by Conceptual Spaces

Abbasi,

Alesheikh,

Razavi-Termeh

2023

Mathematics

View full text Add to dashboard Cite

With the rapid growth of social media, textual content is increasingly growing. Unstructured texts are a rich source of latent spatial information. Extracting such information is useful in query processing, geographical information retrieval (GIR), and recommender systems. In this paper, we propose a novel approach to infer spatial information from salient features of non-spatial nature in text corpora. We propose two methods, namely DCS and RCS, to represent place-based concepts. In addition, two measures, namely the Shannon entropy and the Moran’s I, are proposed to calculate the degree of geo-indicativeness of terms in texts. The methodology is compared with a Latent Dirichlet Allocation (LDA) approach to estimate the accuracy improvement. We evaluated the methods on a dataset of rental property advertisements in Iran and a dataset of Persian Wikipedia articles. The results show that our proposed approach enhances the relative accuracy of predictions by about 10% in case of the renting advertisements and by 13% in case of the Wikipedia articles. The average distance error is about 13.3 km for the advertisements and 10.3 km for the Wikipedia articles, making the method suitable to infer the general region of the city in which a property is located. The proposed methodology is promising for inferring spatial knowledge from textual content that lacks spatial terms.

show abstract

Postal address extraction from the web: a comprehensive survey

Cited by 6 publications

References 87 publications

Automatic Identification of Addresses: A Systematic Literature Review

Automatic Identification of Addresses: A Systematic Literature Review

Twitter Data Mining for the Diagnosis of Leaks in Drinking Water Distribution Networks

Get Spatial from Non-Spatial Information: Inferring Spatial Information from Textual Descriptions by Conceptual Spaces

Contact Info

Product

Resources

About