By Laréb Fatima Ahmad – Master research project Vrije Universiteit Amsterdam, August 2024
Stereotyping of groups or minorities in official media channels can largely and negatively influence public opinion. Stereotyping is often hidden, subtle and difficult to detect in written text. It is therefore important to find methods that can objectively detect stereotypes in the media. Computational models, if well-designed, offer the possibility to do so for large amounts of textual data. Recent studies by Fokkens et al. [1] have shown promising result using microportraits, a natural language processing method that identifies and labels certain positive, negative or stereotyping concepts, for a given inividual or group in text. In the master research study by computer science student Fatima Ahmad, we use microportraits to detect stereotyping of Muslims in Norwegian conventional media inclusing news papers. This study [2] aims to explore the potential of an already existing proposed Natural Language Processing model to explore and detect weak associations as stereotypical and to propose improvements to the method.
[1] Antske Fokkens, Nel Ruigrok, Camiel Beukeboom, Gagestein Sarah, and Wouter van Atteveldt. Studying Muslim Stereotyping through
Microportrait Extraction. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, May 2018. European Language Resources Association (ELRA). Available from: https://aclanthology.org/L18-1590.
[2] Laréb Fatima Ahmad. “The Islamic Elephant in the News Room”. Using Natural Language Processing to Uncover Stereotypes of Muslims and Ethnic Minorities in Norwegian News in 2017-2019. Master thesis in the framework of EURIDICE’s Inclusive Education on Digital Society, Social Innovation and Global Citizenship. Computer Science master project. Vrije Universiteit Amsterdam, 2024. [pdf]