A Python tool for QGIS for gender recognition in street directories
This is a modal window.
The media could not be loaded, either because the server or network failed or because the format is not supported.
Formal Metadata
Title |
| |
Title of Series | ||
Number of Parts | 351 | |
Author | ||
License | CC Attribution 3.0 Unported: You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor. | |
Identifiers | 10.5446/69095 (DOI) | |
Publisher | ||
Release Date | ||
Language | ||
Production Year | 2022 |
Content Metadata
Subject Area | ||
Genre | ||
Abstract |
| |
Keywords |
00:00
GenderDirectory servicePattern recognitionAssociative propertyAutomationElement (mathematics)Axiom of choiceCodeContext awarenessSoftware frameworkSquare numberInformationFunction (mathematics)AlgorithmoutputData structureIndependence (probability theory)Dependent and independent variablesImplementationNatural languageUniqueness quantificationDatabaseGenderRow (database)outputInformationField (computer science)Data structureWeb 2.0DatabaseCodeFunctional (mathematics)System administratorReal numberLocal ringSet (mathematics)Directory serviceIndependence (probability theory)Context awarenessPoint (geometry)AlgorithmEndliche ModelltheorieCASE <Informatik>Dependent and independent variablesFigurate numberPosition operatorPattern recognitionAssociative propertyElectronic mailing listStreaming mediaEqualiser (mathematics)Software frameworkResultantWikiLevel (video gaming)Personal area networkImplementationOpen setMultiplicationData loggerAxiom of choiceGoodness of fitElement (mathematics)Computer animationDiagram
Transcript: English(auto-generated)
00:01
Thank you. Good morning, everyone. I'll present you a work titled a Python tool for QGIS for gender recognition in street directories. So the framework is that in the last years the attention of gender equality in all contexts
00:22
has increased all over the world. The sensibility of a public administration towards the naming of streets and the point of interest after woman has highlighted that the toponymy has always been oriented to the choice of male figures.
00:41
So the goal of our work is to automate the gender recognizance starting from a list of names, for example a street directory. There are already available many many methods of association between the name and the gender, but
01:04
not of all natively take into account the position of the element considered. We considered several solutions and at final we choose to implement a simple
01:21
manageable solution based on the use of Wikidata's API within a Python code embedded in QGIS. The implementation, the method is based on the searching for gender information about a real human being
01:41
in Wikidata. So no Pinocchio and no Peter Pan, but yes Michelangelo Buonarroti. The implemented function starting from the street name that is contained in a field of the input geographic layer extracts the general value from the Wikidata JSON if
02:04
this entry exists. The advantages of this kind of our method we think is that it's based on universally recognized database Wikidata. It is a language independent because
02:22
the idea of a Wikidata record is unique for all languages. If the person searched does not exist we can create directly in Wikipedia a new record. It is integrated into QGIS
02:41
as a function so this function can be used within the algorithm streamings for example in a model builder and for us it is a very important point. It is independent of the structure of the input data set so we can start from
03:04
data set from coming from OpenStreetMap or for example local street directory. The disadvantage is it only works when we are connected to the web and actually it doesn't handle multiple responses in the case of
03:23
Omonemia. This is an example of a real data set of Reggion e Piemonte. We have the street name and the results is in the field for example Umberto Primo, past king of Italy, it is male.
03:44
Umberto Saba or Giovanni Pascoli really recognized it as a male and a female and if the API doesn't recognize the item and mark a star
04:02
is in the field. If we don't have, if the field is blank it means that the record doesn't exist in Wikidata for example via Trino. Trino is a city so it is not a person. Thank you.