# Towards Detection of Subjective Bias using Contextualized Word Embeddings

Source: [Towards Detection of Subjective Bias using Contextualized Word Embeddings](<https://www.sota2.com/research/paper/68fa67ba1e209131cea18294>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-25T07:45:07.684Z

Authors: Tanvi Dadu, Kartikey Pant, Radhika Mamidi

Published: 2020-02-16T18:39:16.000Z

## Abstract

Subjective bias detection is critical for applications like propaganda detection, content recommendation, sentiment analysis, and bias neutralization. This bias is introduced in natural language via inflammatory words and phrases, casting doubt over facts, and presupposing the truth. In this work, we perform comprehensive experiments for detecting subjective bias using BERT-based models on the Wiki Neutrality Corpus(WNC). The dataset consists of $360k$ labeled instances, from Wikipedia edits that remove various instances of the bias. We further propose BERT-based ensembles that outperform state-of-the-art methods like $BERT\_{large}$ by a margin of $5.6$ F1 score.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Subjectivity Detection on WNC (test)](<https://www.sota2.com/research/sota/subjectivity-detection-on-wnc-test.md>): Subjectivity Detection; WNC (test); Precision: 73.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.06644>)

[PDF](<https://arxiv.org/pdf/2002.06644.pdf>)

[Implementation](<https://github.com/tanvidadu/Subjective-Bias-Detection>)