Can Social Agents elicit Shame as Humans do?

Schneeberger, Tanja; Scholtes, Mirella; Hilpert, Bernhard; Langer, Markus; Gebhard, Patrick

doi:10.1109/acii.2019.8925481

Cited by 14 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Participants' age was between 21 and 29 years (M = 23.83, SD = 2.66). The participants were presented with videos of our job interview training system applied to a multi-modal job interview role-play dataset [10].…”

Section: Discussionmentioning

confidence: 99%

“…In order to verify the validity of our approach, we examined whether the counterfactuals generated by the GAN are modifying the features that the incorporated engagement classifier identified as important for the classification of low and high engagement. For this evaluation, we used five sessions of the multi-modal job interview role-play dataset [10] that have also been used in the pilot study and extracted the importance scores of every feature in regard to the model's classification with LIME [8]. We calculated the pearson correlation between the absolute value change of how much each feature has been modified by the counterfactual transformation and the importance score of every feature, see Table 1.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Generating Personalized Behavioral Feedback for a Virtual Job Interview Training System Through Adversarial Learning

Heimerl

Mertes

Schneeberger

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Job interviews are usually high-stakes social situations where professional and behavioral skills are required for a satisfactory outcome. In order to increase the chances of recruitment technological approaches have emerged to generate meaningful feedback for job candidates. We extended an interactive virtual job interview training system with a Generative Adversarial Network (GAN)-based approach that first detects behavioral weaknesses and subsequently generates personalized feedback. To evaluate the usefulness of the generated feedback, we conducted a mixed-methods pilot study using mock-ups from the job interview training system. The overall study results indicate that the GAN-based generated behavioral feedback is helpful. Moreover, participants assessed that the feedback would improve their job interview performance.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Generating Personalized Behavioral Feedback for a Virtual Job Interview Training System Through Adversarial Learning

Heimerl

Mertes

Schneeberger

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…The starting point for applying the DEEP method was a previous study examining the emotion shame during the highstakes situation of a job interview with a virtual interviewer [41]. Results indicated that participants experienced shame in the shame-eliciting interview independent of the elicitor (human vs. virtual agent).…”

Section: Application Of the Deep Methodsmentioning

confidence: 99%

“…The present study's goal was to apply the DEEP method to a tested scenario. We oriented on our previous study examining the emotion shame [41]. Beforehand, we obtained approval from the project's ethical review board.…”

Section: Study Methodsmentioning

confidence: 99%

“…Then, the experimenter guided them to the interviewer's office, which they entered alone. In the office, the virtual interviewer welcomed and asked them to sit down, then started the structured job interview conducted by the interactive social agent Susanne [41]. The interview included two shame eliciting situations: ("A brief question before we start.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Towards a Deeper Modeling of Emotions: The Deep Method and its Application on Shame

Schneeberger

Hladky

Thurner

et al. 2021

2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII)

Self Cite

View full text Add to dashboard Cite

Understanding emotions is key to Affective Computing. Emotion recognition focuses on the communicative component of emotions encoded in social signals. This view alone is insufficient for deeper understanding and computational representation of the internal, subjectively experienced component of emotions. This paper presents the DEEP method as a starting point for a deeper computational modeling of internal emotions. The method includes how to query individual internal emotional experiences, and it shows an approach to represent such information computationally. It combines social signals, verbalized introspection information, context information, and theory-driven knowledge. We apply the DEEP method exemplary on the emotion shame and present a schematic dynamic Bayesian network for modeling it.

show abstract

Can Robots Elicit Different Comfortability Levels?

et al. 2020

View full text Add to dashboard Cite

Social interactions entail often complex and dynamic situations that follow non-explicit, unwritten rules. Comprehending those signals and knowing how to respond becomes the key to the success of any social communication. Thus, in order to integrate a robot into a social context it should be capable of (at least) understanding others' emotional states. Nonetheless, mastering such skill is beyond reach for current robotics which is why we introduce the single internal state which we believe reveals the most regarding interactive communications. We named it Comfortability and defined it as (disapproving of or approving of ) the situation that arises as a result of a social interaction which influences one's own desire of maintaining or withdrawing from it. Consequently, in this paper we aim to show that Comfortability can be evoked by robots, investigating at the same time its connection with other emotional states. To do that, we performed two online experiments on 196 participants asking them to imagine being interviewed by a reporter on a sensitive topic. The interviewer's actions were presented in two different formats: the first experiment (the Narrative Context) presented the actions as text; whereas the second experiment (the Visual Context) presented the actions as videos performed by the humanoid robot iCub. The actions were designed to evoke different Comfortability levels. According to the experimental results, Comfortability differs from the other reported emotional and affective states and more importantly, it can be evoked by both, humans and robots in an imaginary interaction.

show abstract

Can Social Agents elicit Shame as Humans do?

Cited by 14 publications

References 29 publications

Generating Personalized Behavioral Feedback for a Virtual Job Interview Training System Through Adversarial Learning

Generating Personalized Behavioral Feedback for a Virtual Job Interview Training System Through Adversarial Learning

Towards a Deeper Modeling of Emotions: The Deep Method and its Application on Shame

Can Robots Elicit Different Comfortability Levels?

Contact Info

Product

Resources

About