Addressing age-related bias in sentiment analysis

Mark Díaz, Isaac Johnson, Amanda Lazar, Anne Marie Piper, Darren Gergle

Research output: Chapter in Book/Report/Conference proceedingConference contribution

98 Scopus citations


Computational approaches to text analysis are useful in understanding aspects of online interaction, such as opinions and subjectivity in text. Yet, 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 contribute a systematic examination of the application of language models to study discourse on aging. 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 demonstrate that significant age bias is encoded in the outputs of many sentiment analysis algorithms and word embeddings. We discuss the models' characteristics in relation to output bias and how these models might be best incorporated into research.

Original languageEnglish (US)
Title of host publicationCHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems
Subtitle of host publicationEngage with CHI
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450356206, 9781450356213
StatePublished - Apr 20 2018
Event2018 CHI Conference on Human Factors in Computing Systems, CHI 2018 - Montreal, Canada
Duration: Apr 21 2018Apr 26 2018

Publication series

NameConference on Human Factors in Computing Systems - Proceedings


Other2018 CHI Conference on Human Factors in Computing Systems, CHI 2018


  • Aging
  • Older adults, algorithmic bias
  • Sentiment analysis

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Addressing age-related bias in sentiment analysis'. Together they form a unique fingerprint.

Cite this