Demographic inference and corrections for non-representativeness when working with multilingual social media data

Flöck, Fabian
Dr. Fabian Flöck introduces a new state of the art for inferring demographic attributes of social media profiles with deep learning in 32 languages. In his paper from last year he showed how to estimate the probabilities to be on Twitter for different socio-demographic strata ...
published 2020-04, Version 1
On-site

Full Metadata Record

Language of Resource

English

Titles

Title

Demographic inference and corrections for non-representativeness when working with multilingual social media data

Collective Title

  • GESIS Blog, No. 4 (2020)

Creator

Flöck, Fabian

Origin Information

Publisher

Publication Date

2020-04

Access

Availability

On-site

Subjects

Description

  • Abstract

    Dr. Fabian Flöck introduces a new state of the art for inferring demographic attributes of social media profiles with deep learning in 32 languages. In his paper from last year he showed how to estimate the probabilities to be on Twitter for different socio-demographic strata in over 1000 regions in the EU. Read the blog post to learn more about the paper, the pretrained model or the Web demo.

Relations

Related Identifiers

  • Is part of
    URL: https://blog.gesis.org/ (Text)
  • Is derived from
    URL: http://www.euagendas.org/index.php/2019/05/14/demo-inference-and-correction/ (Text)

Update Metadata: 2021-01-05 | Issue Number: 3 | Registration Date: 2020-04-20