Connotation Frames of Power and Agency in Modern Films

By Maarten Sap, Marcella Cindy Prasettio, Ari Holtzman, Hannah Rashkin, Yejin Choi. 2017

122 citations recorded by the source corpus.

The framing of an action influences how we perceive its actor. We introduce connotation frames of power and agency, a pragmatic formalism organized using frame semantic representations, to model how different levels of power and agency are implicitly projected on actors through their actions. We use the new power and agency frames to measure the subtle, but prevalent, gender bias in the portrayal of modern film characters and provide insights that deviate from the well-known Bechdel test. Our contributions include an extended lexicon of connotation frames along with a web interface that provides a comprehensive analysis through the lens of connotation frames.

Subfields: Artificial Intelligence, Social Psychology, Natural Language Processing, Information Extraction

How researchers see this paper

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

In Artificial Intelligence

In Social Psychology

In Natural Language Processing

In Information Extraction

Citations in the corpus

SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference (2018, background): “However, it is not perfect in this regard, particularly due to biases in movies (Schofield and Mehr, 2016; Sap et al., 2017).”
From Recognition to Cognition: Visual Commonsense Reasoning (2018, background): “21This line of work is complementary to other notions of dataset bias, like understanding what phenomena datasets cover or don’t [76], particularly how that relates to how marginalized groups are represented and portrayed [71, 90, 69, 68].”
Social Bias Frames: Reasoning about Social and Power Implications of Language (2019, background): “, 2012) or in narrative text (Sap et al., 2017; Field et al., 2019; Antoniak et al., 2019).”
PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction (2020, methodology): “8 8 We retrieve a verb from the Sap et al. (2017) lexicon that has the target agency and is most similar to the masked out”
A Framework for the Computational Linguistic Analysis of Dehumanization (2020, methodology): “Figure 5 shows the agency of each group label based on its head verb’s entry in the Connotation Frames lexicon for agency and the group label’s position relative to that verb (Sap et al., 2017).”
Gender and Representation Bias in GPT-3 Generated Stories (2021, methodology): “Words linked to people via linguistic dependencies can be used to analyze descriptions of people in text (Fast et al., 2016b; Hoyle et al., 2019; Lucy et al., 2020; Bamman et al., 2013; Sap et al., 2017).”
Toward Deconfounding the Effect of Entity Demographics for Question Answering Accuracy (2021, background): “Like other cultural artifacts—encyclopedias (Reagle and Rhue, 2011), and films (Sap et al., 2017)—QA has more men than women.”
Entity-Centric Contextual Affective Analysis (2019, methodology): “We refer to these dimensions as power , sentiment , and agency for consistency with prior work in NLP (Sap et al., 2017; Rashkin et al., 2016; Field et al., 2019).”
Understanding the Shades of Sexism in Popular TV Series (2019, background): “However, some recent works (Sap et al., 2017; Google, 2017) expose the prevalence of sexism in such multimedia contents.”
A Survey on Gender Bias in Natural Language Processing (2021, methodology): “In the context of NLP, this is often the case for machine translation [Sap et al. 2017] and coreference resolution [Webster et al. 2018] (see §7.3).”
Can Large Language Models Transform Computational Social Science? (2023, background): “Researchers can also study agents in terms of their power dynamics (Sap et al., 2017) and emotions (Brahman and Chaturvedi, 2020), which we benchmark in §3.”
Event2Mind: Commonsense Inference on Events, Intents, and Reactions (2018, methodology): “Furthermore, in order to showcase the practical implications of commonsense inference on events and people’s mental states, we apply our model to modern movie scripts, which provide a new insight into the gender bias in modern films beyond what previous studies have offered (England et al., 2011; Ag”
Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models (2022, methodology): “Finally, for agency score, we use the lexicon provided by (Sap et al., 2017) and check each generated sequence and count the number of target agency verbs that exist there.”
RtGender: A Corpus for Studying Differential Responses to Gender (2018, background): “For instance, women 1 journal-ists reach a smaller audience in terms of social media impressions (Matias and Wallach, 2012), and traditional gender stereotypes and unbalanced gender representation occur even in contemporary stories and movies (Fast et al., 2016; Sap et al., 2017).”