Mordecai: Full Text Geoparsing and Event Geocoding

Halterman, Andrew

doi:10.21105/joss.00091

Cited by 58 publications

(45 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GeoTxt uses a search engine platform (Solr) to retrieve toponyms with a score computed based on string similarity as well as a variety of other feature weights. The initial computed scores can be fed into an algorithm (Halterman, ; Liu, ; Martins & Calado, ) to train a supervised machine learning model to find optimized weights for those features.…”

Section: Discussion and Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

GeoTxt: A scalable geoparsing system for unstructured text geolocation

Karimzadeh

Pezanowski

MacEachren

et al. 2019

Transactions in GIS

View full text Add to dashboard Cite

In this article we present GeoTxt, a scalable geoparsing system for the recognition and geolocation of place names in unstructured text. GeoTxt offers six named entity recognition (NER) algorithms for place name recognition, and utilizes an enterprise search engine for the indexing, ranking, and retrieval of toponyms, enabling scalable geoparsing for streaming text. GeoTxt offers a flexible application programming interface (API), allowing for customized attribute and/or spatial ranking of retrieved toponyms. We evaluate the system on a corpus of manually geo-annotated tweets.First, we benchmark the performance of the six NERs that GeoTxt provides access to. Second, we assess GeoTxt toponym resolution accuracy incrementally, demonstrating improvements in toponym resolution achieved (or not achieved) by adding specific heuristics and disambiguation methods. Compared to using the GeoNames web service, GeoTxt's toponym resolution demonstrates a 20% accuracy gain. Our results show that places mentioned in the same tweet do not tend to be geographically proximate.

show abstract

Section: Discussion and Future Directionsmentioning

confidence: 99%

“…PlaceSpotter are not clear. Not included in this list are GeoParser.io (http://geoparser.io/) and Mordecai (Halterman, ). The implementation details of GeoParser.io (which is not free for use) are not known.…”

Section: Related Workmentioning

confidence: 99%

GeoTxt: A scalable geoparsing system for unstructured text geolocation

Karimzadeh

Pezanowski

MacEachren

et al. 2019

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…A recent study identified five geoparsing systems: GeoTxt, Geoparser, Yahoo! PlaceSpotter, CLAVIN, and TopoCluster [6]. Also the systems for recognizing geographical names and disambiguating toponyms for two data sets were tested.…”

Section: Research Results and Analysismentioning

confidence: 99%

Development of Geoinformation Technology for Monitoring Events on the Basis of Data from Unstructured Web Resource Text

Lytvynenko*¹,

Lienkov²,

Lytvynenko³

et al. 2020

IJITEE

View full text Add to dashboard Cite

The article studies unstructured text from the informational web resources as a source of obtaining of geospatial data about current events in real time. Authors propose a scheme of construction of the geoinformation technology for monitoring events through the data of the unstructured web resource text, that will allow to collect and visualize geospatial and descriptive information about events on specific topics automatically and in real time. Key elements of the proposed methodology are geoparsing of unstructured text, geocoding of detected coordinates or addresses, and storing of results in the geodatabase. Proposed technology allows to create a web application for automatic identification and monitoring of events (objects) by parameters of their category, location and time. For the purposes of developing this system, authors proposed to use free software (except for ArcGIS Pro). This factor can be attributed to the advantages of the proposed technology.

show abstract

“…In order to produce final usable event data, I also perform the final step of resolving the event location or locations to their geographical coordinates. To do so I use the Mordecai text geoparser (Halterman 2017), which uses a neural network trained on several thousand gold-standard resolved place names to infer the country of a location mention, then performs a fuzzy-string search over the Geonames gazetteer (Wick and Boutreux 2011) and selects the best location among the locations returned from the search.…”

Section: Application: Geolocating Offensives In Syriamentioning

confidence: 99%

Geolocating Political Events in Text

Halterman

2019

Proceedings of the Third Workshop on Natural Language Processing and Computational Social Science

Self Cite

View full text Add to dashboard Cite

This work introduces a general method for automatically finding the locations where political events in text occurred. Using a novel set of 8,000 labeled sentences, I create a method to link automatically extracted events and locations in text. The model achieves human level performance on the annotation task and outperforms previous event geolocation systems. It can be applied to most event extraction systems across geographic contexts. I formalize the event-location linking task, describe the neural network model, describe the potential uses of such a system in political science, and demonstrate a workflow to answer an open question on the role of conventional military offensives in causing civilian casualties in the Syrian civil war.

show abstract

Mordecai: Full Text Geoparsing and Event Geocoding

Cited by 58 publications

References 9 publications

GeoTxt: A scalable geoparsing system for unstructured text geolocation

GeoTxt: A scalable geoparsing system for unstructured text geolocation

Development of Geoinformation Technology for Monitoring Events on the Basis of Data from Unstructured Web Resource Text

Geolocating Political Events in Text

Contact Info

Product

Resources

About