Assessment of ethnic and gender bias in automated first impression analysis

dc.contributor.authorKrull, Friedrich
dc.contributor.otherTartu Ülikool. Loodus- ja täppisteaduste valdkondet
dc.contributor.otherTartu Ülikool. Tehnoloogiainstituutet
dc.date.accessioned2022-07-01T10:05:52Z
dc.date.available2022-07-01T10:05:52Z
dc.date.issued2022
dc.description.abstractThis thesis aims to investigate possible gender and ethnic biases in state-of-the-art deep learning methods in first impression analysis. Analysing a person with some software, businesses want to find the best candidate, without the person being judged by their gender or ethnicity. To achieve this, a first impression dataset about the big five personality traits, with additional information about the person’s gender and ethnic background, was used. Biases were both investigated with models trained on balanced and imbalanced data, where balanced here refers to the number of frames used from people classified as Asian, African-American, or Caucasian in the dataset. The results with both the balanced and imbalanced datasets were similar. With all the models the accuracy for Asians was much higher compared to others, which may come from the fact that the dataset did not include enough variance in the Asian data, so when evaluating, all Asians were seen similarly.et
dc.identifier.urihttp://hdl.handle.net/10062/83023
dc.language.isoenget
dc.publisherTartu Ülikoolet
dc.rightsopenAccesset
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectDeep Neural Networkset
dc.subjectComputer Visionet
dc.subjectFirst Impression Analysiset
dc.subjectRespon sible AIet
dc.subjectHuman-AI Interactionet
dc.subjectSügavad Närvivõrgudet
dc.subjectTehisnägemineet
dc.subjectEsmamulje Analüüset
dc.subjectVastutustundlik Tehisintellektet
dc.subjectInimese-Tehisintellekti Interaktsioonet
dc.subject.othermagistritöödet
dc.titleAssessment of ethnic and gender bias in automated first impression analysiset
dc.typeThesiset

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Krull_MSc2022.pdf
Size:
1.22 MB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.67 KB
Format:
Item-specific license agreed upon to submission
Description: