An official website of the United States government
Abstract Processing facial expressions of emotion draws on a distributed brain network. In particular, judging ambiguous facial emotions involves coordination between multiple brain areas. Here, we applied multimodal functional connectivity analysis to achieve network-level understanding of the neural mechanisms underlying perceptual ambiguity in facial expressions. We found directional effective connectivity between the amygdala, dorsomedial prefrontal cortex (dmPFC), and ventromedial PFC, supporting both bottom-up affective processes for ambiguity representation/perception and top-down cognitive processes for ambiguity resolution/decision. Direct recordings from the human neurosurgical patients showed that the responses of amygdala and dmPFC neurons were modulated by the level of emotion ambiguity, and amygdala neurons responded earlier than dmPFC neurons, reflecting the bottom-up process for ambiguity processing. We further found parietal-frontal coherence and delta-alpha cross-frequency coupling involved in encoding emotion ambiguity. We replicated the EEG coherence result using independent experiments and further showed modulation of the coherence. EEG source connectivity revealed that the dmPFC top-down regulated the activities in other brain regions. Lastly, we showed altered behavioral responses in neuropsychiatric patients who may have dysfunctions in amygdala-PFC functional connectivity. Together, using multimodal experimental and analytical approaches, we have delineated a neural network that underlies processing of emotion ambiguity.
more »
« less
Impact of Affective Multimedia Content on the Electroencephalogram and Facial Expressions
Abstract Most of the research in the field of affective computing has focused on detecting and classifying human emotions through electroencephalogram (EEG) or facial expressions. Designing multimedia content to evoke certain emotions has been largely motivated by manual rating provided by users. Here we present insights from the correlation of affective features between three modalities namely, affective multimedia content, EEG, and facial expressions. Interestingly, low-level Audio-visual features such as contrast and homogeneity of the video and tone of the audio in the movie clips are most correlated with changes in facial expressions and EEG. We also detect the regions associated with the human face and the brain (in addition to the EEG frequency bands) that are most representative of affective responses. The computational modeling between the three modalities showed a high correlation between features from these regions and user-reported affective labels. Finally, the correlation between different layers of convolutional neural networks with EEG and Face images as input provides insights into human affection. Together, these findings will assist in (1) designing more effective multimedia contents to engage or influence the viewers, (2) understanding the brain/body bio-markers of affection, and (3) developing newer brain-computer interfaces as well as facial-expression-based algorithms to read emotional responses of the viewers.
more »
« less
- Award ID(s):
- 1734883
- PAR ID:
- 10153778
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- Scientific Reports
- Volume:
- 9
- Issue:
- 1
- ISSN:
- 2045-2322
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Analyzing different modalities of expression can provide insights into the ways that humans interpret, label, and react to images. Such insights have the potential not only to advance our understanding of how humans coordinate these expressive modalities but also to enhance existing methodologies for common AI tasks such as image annotation and classification. We conducted an experiment that co-captured the facial expressions, eye movements, and spoken language data that observers produce while examining images of varying emotional content and responding to description-oriented vs. affect-oriented questions about those images. We analyzed the facial expressions produced by the observers in order to determine the connection between those expressions and an image's emotional content. We also explored the relationship between the valence of an image and the verbal responses to that image, and how that relationship relates to the nature of the prompt, using low-level lexical features and more complex affective features extracted from the observers' verbal responses. Finally, in order to integrate this multimodal data, we extended an existing bitext alignment framework to create meaningful pairings between narrated observations about images and the image regions indicated by eye movement data. The resulting annotations of image regions with words from observers' responses demonstrate the potential of bitext alignment for multimodal data integration and, from an application perspective, for annotation of open-domain images. In addition, we found that while responses to affect-oriented questions appear useful for image understanding, their holistic nature seems less helpful for image region annotation.more » « less
-
In order to build more human-like cognitive agents, systems capable of detecting various human emotions must be designed to respond appropriately. Confusion, the combination of an emotional and cognitive state, is under-explored. In this paper, we build upon prior work to develop models that detect confusion from three modalities: video (facial features), audio (prosodic features), and text (transcribed speech features). Our research improves the data collection process by allowing for continuous (as opposed to discrete) annotation of confusion levels. We also craft models based on recurrent neural networks (RNNs) given their ability to predict sequential data. In our experiments, we find that text and video modalities are the most important in predicting confusion while the explored audio features are relatively unimportant predictors of confusion in our data.more » « less
-
The role of affect has been long studied in human–computer interactions. Unlike previous studies that focused on seven basic emotions, an avatar named Diana was introduced who expresses a higher level of emotional intelligence. To adapt to the users various affects during interaction, Diana simulates emotions with dynamic facial expressions. When two people collaborated to build blocks, their affects were recognized and labeled using the Affdex SDK and a descriptive analysis was provided. When participants turned to collaborate with Diana, their subjective responses were collected and the length of completion was recorded. Three modes of Diana were involved: a flat-faced Diana, a Diana that used mimicry facial expressions, and a Diana that used emotionally responsive facial expressions. Twenty-one responses were collected through a five-point Likert scale questionnaire and the NASA TLX. Results from questionnaires were not statistically different. However, the emotionally responsive Diana obtained more positive responses, and people spent the longest time with the mimicry Diana. In post-study comments, most participants perceived facial expressions on Diana’s face as natural, four mentioned uncomfortable feelings caused by the Uncanny Valley effect.more » « less
-
In this study, we investigate how different types of masks affect automatic emotion classification in different channels of audio, visual, and multimodal. We train emotion classification models for each modality with the original data without mask and the re-generated data with mask respectively, and investigate how muffled speech and occluded facial expressions change the prediction of emotions. Moreover, we conduct the contribution analysis to study how muffled speech and occluded face interplay with each other and further investigate the individual contribution of audio, visual, and audio-visual modalities to the prediction of emotion with and without mask. Finally, we investigate the cross-corpus emotion recognition across clear speech and re-generated speech with different types of masks, and discuss the robustness of speech emotion recognition.more » « less
