# FrameAxis: Characterizing Microframe Bias and Intensity with Word Embedding

arXiv: https://arxiv.org/abs/2002.08608 · HTML: https://mlsanity.com/paper/2002.08608/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 21 of 21)

- [Discovering Differences in the Representation of People using Contextualized Semantic Axes](https://mlsanity.com/paper/2210.12170/) (2022)
- [The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias](https://mlsanity.com/paper/2312.16148/) (2023)
- [Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Media](https://mlsanity.com/paper/2205.12382/) (2022)
- [SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings](https://mlsanity.com/paper/2301.04704/) (2023)
- [Characterizing Partisan Political Narrative Frameworks about COVID-19 on Twitter](https://mlsanity.com/paper/2103.06960/) (2021)
- [Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning](https://mlsanity.com/paper/2401.17228/) (2024)
- [Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings](https://mlsanity.com/paper/2401.06112/) (2024)
- [Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Models](https://mlsanity.com/paper/2310.12049/) (2023)
- [Enhancing Stance Classification on Social Media Using Quantified Moral Foundations](https://mlsanity.com/paper/2310.09848/) (2023)
- [Adjusting Interpretable Dimensions in Embedding Space with Human Judgments](https://mlsanity.com/paper/2404.02619/) (2024)
- [Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings](https://mlsanity.com/paper/2411.16527/) (2024)
- [Detecting Anti-Vaccine Users on Twitter](https://mlsanity.com/paper/2110.11333/) (2021)
- [FrameFinder: Explorative Multi-Perspective Framing Extraction from News Headlines](https://mlsanity.com/paper/2312.08995/) (2023)
- [Towards Transparency: Exploring LLM Trainings Datasets through Visual Topic Modeling and Semantic Frame](https://mlsanity.com/paper/2406.06574/) (2024)
- [Beyond English: Evaluating Automated Measurement of Moral Foundations in Non-English Discourse with a Chinese Case Study](https://mlsanity.com/paper/2502.02451/) (2025)
- [Moral consensus and divergence in partisan language use](https://mlsanity.com/paper/2310.09618/) (2023)
- [Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Appeals](https://mlsanity.com/paper/2312.05990/) (2023)
- [Do Language Models Understand Morality? Towards a Robust Detection of Moral Content](https://mlsanity.com/paper/2406.04143/) (2024)
- [Narratives at Conflict: Computational Analysis of News Framing in Multilingual Disinformation Campaigns](https://mlsanity.com/paper/2408.13651/) (2024)
- [Quantifying Feature Importance for Online Content Moderation](https://mlsanity.com/paper/2510.19882/) (2025)
- [Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models](https://mlsanity.com/paper/2602.15273/) (2026)

## Abstract (arXiv)

Framing is a process of emphasizing a certain aspect of an issue over the others, nudging readers or listeners towards different positions on the issue even without making a biased argument. Here, we propose FrameAxis, a method for characterizing documents by identifying the most relevant semantic axes ("microframes") that are overrepresented in the text using word embedding. Our unsupervised approach can be readily applied to large datasets because it does not require manual annotations. It can also provide nuanced insights by considering a rich set of semantic axes. FrameAxis is designed to quantitatively tease out two important dimensions of how microframes are used in the text. textitMicroframe bias captures how biased the text is on a certain microframe, and textitmicroframe intensity shows how actively a certain microframe is used. Together, they offer a detailed characterization of the text. We demonstrate that microframes with the highest bias and intensity well align with sentiment, topic, and partisan spectrum by applying FrameAxis to multiple datasets from restaurant reviews to political news. The existing domain knowledge can be incorporated into FrameAxis by using custom microframes and by using FrameAxis as an iterative exploratory analysis instrument. Additionally, we propose methods for explaining the results of FrameAxis at the level of individual words and documents. Our method may accelerate scalable and sophisticated computational analyses of framing across disciplines.