Entity-Centric Contextual Affective Analysis

By Anjalie Field, Yulia Tsvetkov. 2019

34 citations recorded by the source corpus.

While contextualized word representations have improved state-of-the-art benchmarks in many NLP tasks, their potential usefulness for social-oriented tasks remains largely unexplored. We show how contextualized word embeddings can be used to capture affect dimensions in portrayals of people. We evaluate our methodology quantitatively, on held-out affect lexicons, and qualitatively, through case examples. We find that contextualized word representations do encode meaningful affect information, but they are heavily biased towards their training data, which limits their usefulness to in-domain analyses. We ultimately use our method to examine differences in portrayals of men and women.

Subfields: Sentiment & Opinion Analysis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Sentiment & Opinion Analysis

Citations in the corpus

Measuring Bias in Contextualized Word Representations (2019, background): “Field and Tsvetkov (2019) revealed biases in ELMo embeddings that limit their applicability across data domains.”
HONEST: Measuring Hurtful Sentence Completion in Language Models (2021, background): “…word embeddings (Chaloner and Maldon-ado, 2019; Zhou et al., 2019; Nissim et al., 2020) and more recently on pre-trained contextualized embeddings models (Kurita et al., 2019; May et al., 2019; Zhao et al., 2019; Field and Tsvetkov, 2019; Sheng et al., 2019; Nangia et al., 2020; Vig et al., 2020).”
Finding Microaggressions in the Wild: A Case for Locating Elusive Phenomena in Social Media Posts (2019, background): “Our work builds upon a growing body of literature focused on identifying and mitigating gender disparity through computational means (e.g., Magno and Weber, 2014; Garimella and Mihalcea, 2016; Li et al., 2018; Field et al., 2019; Field and Tsvetkov, 2019).”
PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction (2020, background): “Our ﬁndings on movie scripts show the promise of using Controllable Debiasing to successfully mitigate gender biases in portrayal of characters, which could be extended to other domains (e.g., news or ﬁction, Field and Tsvetkov, 2019; Fast et al., 2016).”
A Survey on Gender Bias in Natural Language Processing (2021, background): “Based on social psychology, NLP research has identified three primary affect dimensions: power/dominance (strength/weakness), valence (goodness/badness), and agency/arousal (activeness/passiveness of an identity) [Field and Tsvetkov 2019].”
“You Are Grounded!”: Latent Name Artifacts in Pre-trained Language Models (2020, methodology): “Prior work showed that the representations of named entities incorporate sentiment (Prabhakaran et al., 2019), which is often transferable across entities via a shared given name (Field and Tsvetkov, 2019).”
Quantifying Social Biases in Contextual Word Representations (2019, background): “Field and Tsvetkov (2019) revealed biases in ELMo embeddings that limit their applicability across data domains.”
A Framework for the Computational Linguistic Analysis of Dehumanization (2020, methodology): “We also induce a valence score directly from a group label’s vector representation by adapting the regression-based sentiment prediction from Field and Tsvetkov (2019) for word embeddings.”