Category: Machine Learning

Distric-9 like ship hovering over Malmö in June 2025
Gender / Machine Learning

Unlocking Migration Insights: Personal Name Classification & Big Data at IFMS 2025

From June 16–18 in Malmö, the 4th International Forum on Migration Statistics (IFMS 2025) brings together statisticians, policymakers, demographers, and data scientists to advance innovative tools—especially Big Data and AI—for richer, more timely migration statistics.

One particularly promising innovation, already used by the UN International Organization for Migration (IOM) as part of its Diaspora Mapping and Engagement Toolkit, is personal name classification, a technique that leverages large datasets of names to infer migration patterns and origins

Photo by Kelsey Knight on Unsplash
Machine Learning

Namsor and Mixity join forces to measure diversity within organizations in France

Mixity has partnered with Namsor to enable organizations to measure the perceived ethnic diversity of their employees using artificial intelligence (AI) and machine learning. This makes it possible to identify and resolve inequalities linked to cultural and ethnic origins. According to French statistical office (INSEE), these inequalities are manifested by higher unemployment rates, less durable and qualified jobs and lower remuneration for immigrant populations.

Internet for Trust Towards Guidelines for Regulating Digital Platforms for Information as a Public Good
General / Machine Learning

UNESCO “Internet for Trust” takeaways

The UNESCO “Internet for Trust” conference provided a great opportunity to better understand the challenges relating to the regulation of generative AI and content moderation in social media. Namsor can indeed play a role in the process of making these tool safer for users.

"societal pressures encourage women to be more uncertain than their male counterparts" Illustration by DALL-E
Gender / General / Machine Learning

Do societal pressures encourage women to be more uncertain than their male counterparts?

ChatGPT is impressive … it works like magic. But how robust are its answers, compared to recent academic results? ChatGPT can write about the Neo-Assyrian period, but what if a major archeological discovery were made that would change everything we know about this period. How long would it take for ChatGPT to adjust its knowledge?
We’ve prompted ChatGPT with some of the research questions of the paper “Editing a Woman’s Voice” (2022, Anna M. Costello, Ekaterina Fedorova, Zhijing Jin, and Rada Mihalcea).

IOM Diaspora Mapping Toolkit Pagecover
Machine Learning

IOM Diaspora Mapping Toolkit : big data and onomastics

The IOM Diaspora Mapping Toolkit analyses pros & cons for the use of big data and onomastics for Diaspora Mapping. It is based on field experience learned from several project conducted by The International Organization for Migration (IOM) using NamSor technology. One particular case study cited in the report is Skills Mapping Through Big Data: A case study of Armenian diaspora in the United States of America and France

Diaspora networks accross the world (DALL-E)
Machine Learning

What is a diaspora (according to ChatGPT)

At NamSor, since 2012, we’ve helped countries reconnect with their diaspora, using our advanced AI to recognize personal names with high accuracy, and to produce new disaggregated information. It took us a while to understand the concept of “diaspora”, how they affect foreign direct investment, remittances, brain-gain vs. brain-drain, the travel industry, real estate … We’ve asked ChatGPT “what is a diaspora”.

"The Social Science Research Network" by DALL-E
General / Machine Learning

Top 20 papers using or citing NamSor in SSRN

Top 20 papers in The Social Science Research Network (SSRN) using or citing NamSor name classification software. SSRN is a high impact journal (top 14% of journals). Some papers used NamSor to infer the gender of a personal name, some other papers to supplement subject data with race / ethnicity, or cultural heritage and ethnic origin.

A portrait of Mariam KABORE #thisnamedpersondoesnotexist #DALLE
General / Machine Learning

This Mariam KABORE does not exist

Two weeks ago, we generated several portraits using DALL-E of hypothetical Fatimata SWADOGO, a Bukinabé name shared by hundreds of people in Burkina Faso, mostly in the Centre-Nord, Nord regions of the country. Today, we present some new portraits generated from personal names with the tag #thisnamedpersondoesnotexist – and we feature a “classic fail” of AI software.

A portrait of FATIMATA SAWADOGO #thisnamedpersondoesnotexist #DALLE
General / Machine Learning

This Fatimata SAWADOGO does not exist

We’ve used DALL-E text-to-image AI to generate portraits, based on names shared by a large number of people. This is our second blog post in our series with tag #thisnamedpersondoesnotexist, exploring how text-to-image AIs interpret personal names. We believe this project can illustrate the complexity of personal names interpretation, at the crossroads of ethnography, sociology, sociolinguistics, geography, history and, more recently machine learning.