Fork me on GitHub CLAVIN logo
demo button download button tech docs button

CLAVIN (Cartographic Location And Vicinity INdexer) is an award-winning open source software package for document geotagging and geoparsing that employs context-based geographic entity resolution.

It extracts location names from unstructured text and resolves them against a gazetteer to produce data-rich geographic entities.

CLAVIN does not simply "look up" location names – it uses intelligent heuristics to identify exactly which "Springfield" (for example) was intended by the author, based on the context of the document. CLAVIN also employs fuzzy search to handle incorrectly-spelled location names, and it recognizes alternative names (e.g., "Ivory Coast" and "Côte d'Ivoire") as referring to the same geographic entity.

By enriching text documents with structured geo data, CLAVIN enables hierarchical geospatial search and advanced geospatial analytics on unstructured data.



VERSION 1.0 RELEASED!

Berico Technologies is proud to announce the version 1.0 release of CLAVIN, its award-winning open source geoparsing software! The culmination of over 18 months of effort, version 1.0 features extensive testing, documentation, and evaluation, as well as an improvement in algorithmic performance.

CLAVIN version 1.0 is available now in Berico's public code repository on GitHub. For convenience, binaries are also distributed via the Maven Central Repository.

Please sign-up for our two new mailing lists on Google Groups:

clavin-users is for discussions about how to use CLAVIN. If you've got a question about getting CLAVIN up & running, this is the place to ask it.

clavin-developers is for discussions about active software development efforts for CLAVIN. If you've got a question about how to implement a new feature for CLAVIN, this is the place to ask it.

Click here to access the technical documentation.

CLAVIN mustache



UPCOMING EVENTS

The CLAVIN nationwide road show continues to roll along with appearances at three events coming up in the near future:

Download the PDF product summary: CLAVIN - Capabilities Overview.

GEOINT 2013 logo   All Things Open logo   LocationTech Tour badge



Our friends at the MIT Center for Civic Media recently published a blog post providing an update about their research into the geography of news coverage. Of particular interest was their "Great Geoparsing Bake-off" in which they compared multiple geoparsing tools & services to see which one best fit their requirements (spoiler alert: CLAVIN wins!). Read it all here: Big Data, News and Geography: Research Update

MIT says: CLAVIN wins!


Charlie gave a talk on CLAVIN at the All Things Open conference in Raleigh, NC on October 23. Titled "Open Source Software for Geotagging Unstructured Big Data," the presentation covered how CLAVIN works and how it's used to enable advanced geospatial analytics on text data. The slides from Charlie's talk are available here.

All Things Open conference banner


Travis gave a presentation at the Mil-OSS | LANT summit on August 8 in Charleston, SC. This talk, entitled "CLAVIN: Enabling GEOINT and Cyber Security," demonstrated how CLAVIN can be used to add a geospatial perspective to traditional cyber analysis. Check out the slides here.

Mil-OSS | LANT logo


Travis conducted an experiment for Naval Postgraduate School JIFX 13-4 at Camp Roberts, CA on August 5, 2013. The experiment was titled "Context Based Geospatial Extraction with CLAVIN," and provided a system prototype demonstration in an actual environment for this Joint Interagency Field Exploration hosted by NPS.

A local newspaper, the Monterey Herald, mentioned CLAVIN in its coverage of the JIFX event.

Naval Postgraduate School logo


Travis gave a talk on CLAVIN at the USGIF Technical Workshop in Denver on July 18. The presentation, titled "Exploiting Unstructured Data using Crowdsourced Gazetteers in the Cloud," focused on using OpenStreetMap as a source of gazetteer data for CLAVIN.

USGIF Technical Workshop: Denver logo


At the July meeting of the Big Data DC Meetup group, Travis gave a lightning talk entitled "Enabling Geospatial Analysis on Unstructured Big Data." Video of the presentation is below:




Charlie gave a streaming tech talk webcast on CLAVIN for the Eclipse Foundation's LocationTech Working Group at 11:00am EDT on June 18, 2013. The talk was broadcast live via Google Hangout and was subsequently uploaded to YouTube for later viewing & sharing. The slides can be viewed here, and the video is embedded below:




We were thrilled that the Washington Post printed a half-page story on CLAVIN in a recent issue of the newspaper. It seems CLAVIN has gone from analyzing the content of news articles to being the content of a news article. The story is available online here: Clavin seeks to make its mark in open-source world and also in the June 3, 2013 print edition on page A14.

Washington Post logo


In their latest investigation, Catherine D'Ignazio and researchers from the MIT Center for Civic Media turned their attention to media coverage of the Boston Marathon bombings. In this study, they looked at three weeks of news coverage from four different sources to see which media outlets paid attention to which crises in the weeks surrounding the attacks. Using CLAVIN, they were "able to yield up to 90% correct placement of news articles at the country level." The write-up is here: How Close to Home? Crisis, Attention and Geographic Bias along with an interactive visualization.

Boston Bombing screenshot


CLAVIN was recently featured in a pair of blog posts by Google Maps Mania and Directions Magazine's All Points Blog. Thanks for the mentions, and thanks especially to the anonymous commenter who "received perfect results" from our "great demo!"

All Points Blog logo


Many thanks to Pete Warden for mentioning CLAVIN on his personal blog PeteSearch. Pete said CLAVIN is "very promising" and has "some very neat tricks up its sleeve." Thanks, Pete!

Be sure to try out Pete's Data Science Toolkit, a collection of open data sets and open source tools for data science:

Data Science Toolkit logo


We'd like to thank everyone who came out for Charlie's talk on CLAVIN ("Automatically Geotagging Unstructured Text with Open Source Tools") at the 2013 FOSS4G North America Conference in Minneapolis on May 23, 2013! The turnout was fantastic and we really appreciated all the great questions! Slides from the talk can be viewed here.

FOSS4G-NA logo


On May 21, 2013 Charlie gave a talk on CLAVIN at the Location Intelligence conference in DC during the "Open Source Technology Use Cases" session. View the slides here.

Location Intelligence logo


Charlie gave a short talk about CLAVIN and Berico Technologies at the Destination Innovation 2013 event hosted by the Northern Virginia Technology Council (NVTC) in DC on May 6, 2013. Watch the video:



Following Charlie's presentation, the NVTC judges recognized CLAVIN with the Most Innovative Capability Award (mid-size business category)!

NVTC award logo

NVTC awardees


Catherine D'Ignazio and researchers from the MIT Center for Civic Media are currently using CLAVIN in a study on the geography of news coverage. CLAVIN helps them extract & resolve place names mentioned in new articles to power their geospatial analytics and visualizations. Read the write-up for an initial experiment here: A Comparative Experiment in Mapping the News and don't miss their cool interactive visualization: NEWSMAPPING.

MIT NEWSMAPPING visualization


Charlie gave a talk on CLAVIN at the recent Open Analytics DC Summit. For the event summary & presentation slides, check out the recap here.

Charlie speaking at Open Analytics DC


At the February 2013 meeting of the Geo DC meetup group, Charlie gave a "lighting talk" on CLAVIN. Review the slides here.

Geo DC logo


CLAVIN was featured in a tech talk at the GEOINT 2012 Innovation Pavilion. Check out the video of that presentation:



Also at GEOINT 2012, Charlie recorded an interview with GISCafe.com about Berico in general and CLAVIN in particular. Watch the video here:

GISCafe interview video


Follow @CLAVIN__ on Twitter