Contextual Affective Analysis: A Case Study of People Portrayals in Online #MeToo Stories

In October 2017, numerous women accused producer Harvey Weinstein of sexual harassment. Their stories encouraged other women to voice allegations of sexual harassment against many high profile men, including politicians, actors, and producers. These events are broadly referred to as the #MeToo movement, named for the use of the hashtag "#metoo" on social media platforms like Twitter and Facebook. The movement has widely been referred to as "empowering" because it has amplified the voices of previously unheard women over those of traditionally powerful men. In this work, we investigate dynamics of sentiment, power and agency in online media coverage of these events. Using a corpus of online media articles about the #MeToo movement, we present a contextual affective analysis---an entity-centric approach that uses contextualized lexicons to examine how people are portrayed in media articles. We show that while these articles are sympathetic towards women who have experienced sexual harassment, they consistently present men as most powerful, even after sexual assault allegations. While we focus on media coverage of the #MeToo movement, our method for contextual affective analysis readily generalizes to other domains.

[1]  Tami Spry,et al.  In the Absence of Word and Body: Hegemonic Implications of "Victim" and "Survivor" in Women's Narratives of Sexual Violence , 1995 .

[2]  David A. Smith,et al.  Predicting News Coverage of Scientific Articles , 2018, ICWSM.

[3]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[4]  Nathanael Chambers,et al.  Unsupervised Learning of Narrative Schemas and their Participants , 2009, ACL.

[5]  Miriam R. L. Petruck.  FRAME SEMANTICS , 1996 .

[6]  C. Osgood,et al.  The Measurement of Meaning , 1958 .

[7]  Noah A. Smith,et al.  Analyzing Framing through the Casts of Characters in the News , 2016, EMNLP.

[8]  Saif Mohammad,et al.  Obtaining Reliable Human Ratings of Valence, Arousal, and Dominance for 20,000 English Words , 2018, ACL.

[9]  Xiaojin Zhu,et al.  Seeing stars when there aren’t many stars: Graph-based semi-supervised learning for sentiment categorization , 2006 .

[10]  Jure Leskovec,et al.  Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora , 2016, EMNLP.

[11]  D. R. Heise.  Understanding Events: Affect and the Construction of Social Action , 1981 .

[12]  L. Smith-Lovin,et al.  Affect Control Theory , 2006 .

[13]  Bing Liu,et al.  Sentiment Analysis and Opinion Mining , 2012, Synthesis Lectures on Human Language Technologies.

[14]  Jon M. Kleinberg,et al.  Echoes of power: language effects and power differences in social interaction , 2011, WWW.

[15]  Krishna P. Gummadi,et al.  Media Bias Monitor: Quantifying Biases of Social Media News Outlets at Large-Scale , 2018, ICWSM.

[16]  David R. Heise.  Expressive Order: Confirming Sentiments in Social Actions , 2006 .

[17]  J. Russell.  A circumplex model of affect. , 1980 .

[18]  Gloria Mark,et al.  Fostering Civil Discourse Online , 2018, Proc. ACM Hum. Comput. Interact..

[19]  Owen Rambow,et al.  Dialog Structure Through the Lens of Gender, Gender Environment, and Power , 2017, Dialogue Discourse.

[20]  Yejin Choi,et al.  Connotation Frames: A Data-Driven Investigation , 2015, ACL.

[21]  Yejin Choi,et al.  Connotation Frames of Power and Agency in Modern Films , 2017, EMNLP.

[22]  J. Russell.  Core affect and the psychological construction of emotion. , 2003, Psychological review.

[23]  Eric Gilbert,et al.  Phrases that signal workplace hierarchy , 2012, CSCW.

[24]  Snigdha Chaturvedi,et al.  Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships , 2016, NAACL.

[25]  Kathleen M. Carley,et al.  Girls Rule, Boys Drool: Extracting Semantic and Affective Stereotypes from Twitter , 2017, CSCW.

[26]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[27]  Brendan T. O'Connor,et al.  Learning Latent Personas of Film Characters , 2013, ACL.

[28]  J. R. French,et al.  The bases of social power. , 1959 .