作者: Mark Diaz , Isaac Johnson , Amanda Lazar , Anne Marie Piper , Darren Gergle
关键词:
摘要: Computational approaches to text analysis are useful in understanding aspects of online interaction, such as opinions and subjectivity text. Yet, recent studies have identified various forms bias language-based models, raising concerns about the risk propagating social biases against certain groups based on sociodemographic factors (e.g., gender, race, geography). In this study, we contribute a systematic examination application language models study discourse aging. We analyze treatment age-related terms across 15 sentiment 10 widely-used GloVe word embeddings attempt alleviate through method processing model training data. Our results demonstrate that significant age is encoded outputs many algorithms embeddings. discuss models' characteristics relation output how these might be best incorporated into research.