Identifying and Mitigating Gender Bias in Social Media Sentiment Analysis: A Post-Training Approach on Example of the 2023 Morocco Earthquake

20813 8 110759 2 335284 document 110759 information-16-00679.pdf application/pdf eb4e785cdd7e4f489ad0c35539854bf9 MD5 1502911 2025-08-11 07:49:03 https://pure.iiasa.ac.at/id/eprint/20813/1/information-16-00679.pdf 20813 1 1 application/pdf text en public cc_by_4

information-16-00679.pdf

published 110761 1 335301 document 110761 indexcodes.txt text/plain 6443a16aa52a12d3dd9194123ddf6126 MD5 9895 2025-08-11 07:59:27 https://pure.iiasa.ac.at/id/eprint/20813/2/indexcodes.txt 20813 2 2 text/plain other Generate index codes conversion from text to indexcodes en public

indexcodes.txt

lightbox.jpg

preview.jpg

medium.jpg

small.jpg

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/110759 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/110759 http://eprints.org/relation/issmallThumbnailVersionOf https://pure.iiasa.ac.at/id/document/110759 archive 353 disk0/00/02/08/13 2025-08-11 07:51:28 2025-08-11 07:51:28 2025-08-11 07:51:28 article show Yeganegi R. 2456 0000-0003-4109-0690 Hassani H. 9469 Komendantova N. 1880 0000-0003-2568-6179 Identifying and Mitigating Gender Bias in Social Media Sentiment Analysis: A Post-Training Approach on Example of the 2023 Morocco Earthquake pub ASA CAT social media; sentiment analysis; gender bias; natural language processing Sentiment analysis is a cornerstone in many contextual data analyses, from opinion mining to public discussion analysis. Gender bias is one of the well-known issues in sentiment analysis models, which can produce different results for the same text depending on the gender it refers to. This gender bias leads to further bias in other text analyses that use such sentiment analysis models. This study reviews existing solutions to reduce gender bias in sentiment analysis and proposes a new method to address this issue. The proposed method offers more practical flexibility as it focuses on sentiment estimation rather than model training. Furthermore, it provides a quantitative measure to investigate the gender bias in sentiment analysis results. The performance of the proposed method across five sentiment analysis models is presented using texts containing gender-specific words. The proposed method is applied to a set of social media posts related to Morocco’s 2023 earthquake to estimate the gender-unbiased sentiment of the posts and evaluate the gender-unbiasedness of five different sentiment analysis models in this context. The result shows that, although the sentiments estimated with different models are very different, the gender bias in none of the models is drastically large. 2025-08-08 published doi:10.3390/info16080679 3692 3410 161 public Information 16 8 e679 1 TRUE 2078-2489 Multi-hazard and risk informed system for Enhanced local and regional Disaster risk management (MEDiate, HE 101074075) yes info:eu-repo/grantAgreement/EC/HE/101074075/EU//MEDiate info:eu-repo/semantics/article info:eu-repo/semantics/openAccess