BOSTON--(BUSINESS WIRE)--Affectiva, the leader in artificial emotional intelligence (Emotion AI) technology, today announced that PLOS One, a major science resource organization, has published the results of the first large-scale, naturalistic analysis of gender differences in facial expressions, conducted using Affectiva’s software. The study, “A Large-scale Analysis of Sex Differences in Facial Expressions”, examined gender differences in expressing emotions across five countries, including the United States, the UK, France, England, and Germany. The lead author of the paper was Dr. Daniel McDuff, at the time head of Affectiva’s science team and now a researcher at Microsoft Research. The data was collected as part of a collaboration with MIT and McDuff’s Ph.D. thesis work.
Considerable research has been conducted analyzing how men and women differ in expressing emotions, but this research has often been done in controlled lab environments with a limited number of participants (10-100). Affectiva’s study covered a large number of participants (1,862) in five countries, and collected data of people in their natural environment, such as their home.
Each participant was asked to watch a number of online videos on their laptop or device, exposing people to a range of emotion-eliciting content, and a range of both positive and negative emotions were collected. “A study of this scope and sophistication probing gender differences in facial expression is rare and welcome,” said Marianne LaFrance, Professor of Psychology at Yale University and co-author of the paper. “This cross-cultural study of gender differences in facial expression will answer a lot of questions.”
The study found that women show significantly more positive expressions of emotion, smiling more often and longer. However, when it comes to negative emotions, the differences across gender are more nuanced: men show more negative expressions associated with anger, while women show more negative expressions associated with sadness and fear. Despite the fact that there are differences across cultures in norms around expressing emotion, these results with regards to gender differences are consistent across cultures.
Additional findings from the study include:
- Women smiled in just over a quarter of the facial video responses. They smiled significantly more than men (32%) and their smiles were longer in duration.
- The brow furrow is a prototypic expression of anger, in many cultures the brow furrow is a frown. Brow furrows were significantly more frequent and longer in duration in men compared to women. Men brow furrowed 14% more than women.
- Women showed significantly more “inner brow raise” which is associated with prototypic expressions of sadness and fear. Specifically, women showed 20% more “inner brow raise” than men.
- Generally these results were consistent across the 5 countries.
“A large-scale study of this nature takes a significant step toward furthering our understanding of how people express emotion,” said Dr. Rana el Kaliouby, CEO and co-founder of Affectiva, and one of the authors of the report. “The findings of the study also illustrate the socialization pressures placed on both men and women, in terms of what is considered acceptable emotional expressions in social and professional settings.”
While these findings may map to inherent gender biases, this is the first large-scale, cross-cultural study to validate these views on gender and emotional expressions using emotion recognition technology in a naturalistic setting.
About Affectiva: Affectiva is the pioneer in Emotion AI, the next
frontier of artificial intelligence. Affectiva's mission is to bring
emotional intelligence to the digital world with its emotion recognition
technology that senses and analyzes facial expressions and emotions.
Affectiva's patented software is built on an emotion AI science platform
that uses computer vision, deep learning and the world's largest emotion
data repository of nearly 6 million faces analyzed from 75 countries,
amounting to more than 2 billion facial frames.
For more
information: www.affectiva.com
About PLOS ONE: The world’s first multidisciplinary Open
Access journal, PLOS ONE accepts scientifically rigorous
research, regardless of novelty. PLOS ONE’s broad scope provides
a platform to publish primary research including interdisciplinary and
replication studies as well as negative results. The journal’s
publication criteria are based on high ethical standards and the rigor
of the methodology and conclusions reported.
For more information: http://journals.plos.org/plosone/
