Emotion Elicitation Under Audiovisual Stimuli Reception: Should Artificial Intelligence Consider the Gender Perspective?

Blanco-Ruiz, Marian; Sainz-de-Baranda, Clara; Gutiérrez-Martín, Laura; Romero, Elena; López-Ongil, C.

doi:10.3390/ijerph17228534

Cited by 14 publications

(29 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, the labeling process will be done based on a gender perspective, taking into consideration label balancing issues and using virtual reality to produce a stronger emotional immersion. This specific work is currently under development [ 7 ]. The resultant intelligent system will be implemented into an embedded wearable device, which will be part of a cyber-physical system that is also connected to trusted responders or even law enforcement agencies.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Fear Recognition for Women Using a Reduced Set of Physiological Signals

Miranda

Canabal

Gutiérrez-Martín

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Emotion recognition is benefitting from the latest research into physiological monitoring and wireless communications, among other remarkable achievements. These technologies can indeed provide solutions to protect vulnerable people in scenarios such as personal assaults, the abuse of children or the elderly, gender violence or sexual aggression. Cyberphysical systems using smart sensors, artificial intelligence and wearable and inconspicuous devices can serve as bodyguards to detect these risky situations (through fear-related emotion detection) and automatically trigger a protection protocol. As expected, these systems should be trained and customized for each user to ensure the best possible performance, which undoubtedly requires a gender perspective. This paper presents a specialized fear recognition system for women based on a reduced set of physiological signals. The architecture proposed is characterized by the usage of three physiological sensors, lightweight binary classification and the conjunction of linear (temporal and frequency) and non-linear features. Moreover, a binary fear mapping strategy between dimensional and discrete emotional information based on emotional self-report data is implemented to avoid emotional bias. The architecture is evaluated using a public multi-modal physiological dataset with two approaches (subject-dependent and subject-independent models) focusing on the female participants. As a result, the proposal outperforms the state-of-the-art in fear recognition, achieving a recognition rate of up to 96.33% for the subject-dependent model.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The main focus of this paper is emotion recognition for women, and we propose systems that aim to protect this specific population. According to [ 7 ], a significant difference in emotional response exists between women and men. Consequently, only data from female participants were considered to train the fear recognition system.…”

Section: Introductionmentioning

confidence: 99%

Fear Recognition for Women Using a Reduced Set of Physiological Signals

Miranda

Canabal

Gutiérrez-Martín

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Note that potentially threatening situations for the participant cause specific negative emotions, such as fear, panic or stress. In this sense, UC3M4Safety claims that the identification of violence-related emotions is of paramount importance when trying to protect women's lives, not only from sexual aggressions but also for detecting violence on vulnerable social groups [20]. Although there is a significant activity in the literature regarding emotion recognition through physical and physiological signals for different purposes and considering different setups [25,26,27], none of the solutions focus on the GBV use case.…”

Section: Related Workmentioning

confidence: 99%

“…Prior to the generation of WEMAC, a mixed methodology [19] with expert judges and general public was applied to select the best audio-visual stimuli for provoking emotional reactions. A public pool was run with 1, 332 participants for labelling the pre-selected emotion-related stimuli [20]. • The modification of the labelling methodology to consider the gender perspective.…”

Section: Introductionmentioning

confidence: 99%

WEMAC: Women and Emotion Multi-modal Affective Computing dataset

Miranda¹,

Rituerto-González²,

Gutiérrez-Martín³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Among the seventeen Sustainable Development Goals (SDGs) proposed within the 2030 Agenda and adopted by all the United Nations member states, the Fifth SDG is a call for action to turn Gender Equality into a fundamental human right and an essential foundation for a better world. It includes the eradication of all types of violence against women. Within this context, the UC3M4Safety research team aims to develop Bindi. This is a cyber-physical system which includes embedded Artificial Intelligence algorithms, for user real-time monitoring towards the detection of affective states, with the ultimate goal of achieving the early detection of risk situations for women. On this basis, we make use of wearable affective computing including smart sensors, data encryption for secure and accurate collection of presumed crime evidence, as well as the remote connection to protecting agents. Towards the development of such system, the recordings of different laboratory and into-the-wild datasets are in process. These are contained within the UC3M4Safety Database. Thus, this paper presents and details the first release of WEMAC, a novel multi-modal dataset, which comprises a laboratory-based experiment for 47 women volunteers that were exposed to validated audio-visual stimuli to induce real emotions by using a virtual reality headset while physiological, speech signals and self-reports were acquired and collected. We believe this dataset will serve and assist research on multi-modal affective computing using physiological and speech information.

show abstract

“…Sin embargo, estudios previos señalan que los recursos audiovisuales empleados no tienen en cuenta la especificidad del miedo aprendido por las mujeres a la violencia ni tampoco el asociado a vivir experiencias traumáticas (Blanco-Ruiz et al, 2020;Sainz de Baranda et al, 2021;Miranda et al, 2021). Con lo cual, este estudio tiene como objetivo extraer de los relatos de las profesionales que utilizan recursos audiovisuales en su trabajo con las víctimas de violencia de género un catálogo de fuentes y experiencias con el audiovisual que pueda incorporarse en las investigaciones emergentes sobre reconocimiento emocional del miedo.…”

Section: Introductionunclassified

El rol del audiovisual en la activación de la memoria autobiográfica en víctimas de violencia de género=The role of audiovisual in the activation of autobiographical memory in victims of gender violence

Andújar¹,

Blanco-Ruiz

Manuel

2021

Cuestiones de género

Self Cite

View full text Add to dashboard Cite

ResumenEl objetivo de este artículo es catalogar los recursos audiovisuales que reflejan las situaciones de violencia contra las mujeres, siendo éstos capaces de activar la memoria autobiográfica de las víctimas. Se han realizado entrevistas semiestructuradas a 59 profesionales que trabajan con víctimas de violencia de género, se abordan estos relatos de las profesionales que utilizan recursos audiovisuales en su trabajo con las víctimas de violencia de género. Su discurso, como informantes clave, se ha analizado con Atlas.ti.v.8. Los 138 títulos audiovisuales muestran una gran heterogeneidad, con representación de las múltiples violencias que sufren las mujeres. Incorporar estos nuevos recursos posibilitarán enseñar a las máquinas emociones específicas derivadas de la experiencia traumática que supone la violencia de género.AbstractThe aim of this article is to catalogue the audiovisual resources that reflect situations of violence against women, which can activate the autobiographical memory of the victims. The methodology used is based on semi-structured interview with 59 professionals who work with victims of gender violence. Their discourse was analysed with Atlas.ti.v.8. The 138 titles mentioned show a great heterogeneity in the audiovisuals, with a representation of the multiple forms of violence suffered by women, beyond the intimate partner or ex-partner. Incorporating these new resources will make it possible to teach the machines specific emotions derived from the traumatic experience of gender-based violence.

show abstract

Emotion Elicitation Under Audiovisual Stimuli Reception: Should Artificial Intelligence Consider the Gender Perspective?

Cited by 14 publications

References 58 publications

Fear Recognition for Women Using a Reduced Set of Physiological Signals

Fear Recognition for Women Using a Reduced Set of Physiological Signals

WEMAC: Women and Emotion Multi-modal Affective Computing dataset

El rol del audiovisual en la activación de la memoria autobiográfica en víctimas de violencia de género=The role of audiovisual in the activation of autobiographical memory in victims of gender violence

Contact Info

Product

Resources

About