Discovering and Interpreting Biased Concepts in Online Communities
Language carries implicit human biases, functioning both as a reflection and a perpetuation of stereotypes that people carry with them. Recently, ML-based NLP methods such as word embeddings have been shown to learn such language biases with striking accuracy. This capability of word embeddings has been successfully exploited as a tool to quantify and study human biases. However, previous studies only consider a predefined set of biased concepts to attest (e.g., whether gender is more or less associated with particular jobs), or just discover biased words without helping to understand their meaning at the conceptual level. As such, these approaches can be either unable to find biased concepts that have not been defined in advance, or the biases they find are difficult to interpret and study. This could make existing approaches unsuitable to discover and interpret biases in online communities, as such communities may carry different biases than those in mainstream culture. This paper improves upon, extends, and evaluates our previous data-driven method to automatically discover and help interpret biased concepts encoded in word embeddings. We apply this approach to study the biased concepts present in the language used in online communities and experimentally show the validity and stability of our method
Code (1)
Tasks
Cultural Vocal Bursts Intensity PredictionWord EmbeddingsSimilar Papers 제목 키워드 기반
Discovering Biased News Articles Leveraging Multiple Human Annotations
Unbiased and fair reporting is an integral part of ethical journalism. Yet, political propaganda and one-sided views can be found in the news and can cause distrust in media. Both accidental and deliberate political bias…
ArticlesGenerating Ethnographic Models from Communities' Online Data
In this paper we describe computational ethnography study to demonstrate how machine learning techniques can be utilized to exploit bias resident in language data produced by communities with online presence. Specificall…
Understanding Distributed Representations of Concepts in Deep Neural Networks without Supervision
Understanding intermediate representations of the concepts learned by deep learning classifiers is indispensable for interpreting general model behaviors. Existing approaches to reveal learned concepts often rely on huma…
Deep LearningDiscovering Interpretable Biological Concepts in Single-cell RNA-seq Foundation Models
Single-cell RNA-seq foundation models achieve strong performance on downstream tasks but remain black boxes, limiting their utility for biological discovery. Recent work has shown that sparse dictionary learning can extr…
Detecting Community Structures in Hi-C Genomic Data
Community detection (CD) algorithms are applied to Hi-C data to discover new communities of loci in the 3D conformation of human and mouse DNA. We find that CD has some distinct advantages over pre-existing methods: (1) …
Community Detection