Addressing Age-Related Bias in Sentiment Analysis
Abstract
Recent studies have identified various forms of bias in language-based models, raising concerns about the risk of propagating social biases against certain groups based on sociodemographic factors (e.g., gender, race, geography). In this study, we analyze the treatment of age-related terms across 15 sentiment analysis models and 10 widely-used GloVe word embeddings and attempt to alleviate bias through a method of processing model training data. Our results show significant age bias is encoded in the outputs of many sentiment analysis algorithms and word embeddings, and we can alleviate this bias by manipulating training data.
Cite
Text
Díaz et al. "Addressing Age-Related Bias in Sentiment Analysis." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/852Markdown
[Díaz et al. "Addressing Age-Related Bias in Sentiment Analysis." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/diaz2019ijcai-addressing/) doi:10.24963/IJCAI.2019/852BibTeX
@inproceedings{diaz2019ijcai-addressing,
title = {{Addressing Age-Related Bias in Sentiment Analysis}},
author = {Díaz, Mark and Johnson, Isaac and Lazar, Amanda and Piper, Anne Marie and Gergle, Darren},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2019},
pages = {6146-6150},
doi = {10.24963/IJCAI.2019/852},
url = {https://mlanthology.org/ijcai/2019/diaz2019ijcai-addressing/}
}