Discrete Emotions Research Articles

A Comparison of Machine Learning Algorithms and Feature Sets for Automatic Vocal Emotion Recognition in Speech.

Vocal emotion recognition (VER) in natural speech, often referred to as speech emotion recognition (SER), remains challenging for both humans and computers. Applied fields including clinical diagnosis and intervention, social interaction research or Human Computer Interaction (HCI) increasingly benefit from efficient VER algorithms. Several feature sets were used with machine-learning (ML) algorithms for discrete emotion classification. However, there is no consensus for which low-level-descriptors and classifiers are optimal. Therefore, we aimed to compare the performance of machine-learning algorithms with several different feature sets. Concretely, seven ML algorithms were compared on the Berlin Database of Emotional Speech: Multilayer Perceptron Neural Network (MLP), J48 Decision Tree (DT), Support Vector Machine with Sequential Minimal Optimization (SMO), Random Forest (RF), k-Nearest Neighbor (KNN), Simple Logistic Regression (LOG) and Multinomial Logistic Regression (MLR) with 10-fold cross validation using four openSMILE feature sets (i.e., IS-09, emobase, GeMAPS and eGeMAPS). Results indicated that SMO, MLP and LOG show better performance (reaching to 87.85%, 84.00% and 83.74% accuracies, respectively) compared to RF, DT, MLR and KNN (with minimum 73.46%, 53.08%, 70.65% and 58.69% accuracies, respectively). Overall, the emobase feature set performed best. We discuss the implications of these findings for applications in diagnosis, intervention or HCI.

Comparison of Emotion Recognition in Young People, Healthy Older Adults, and Patients with Mild Cognitive Impairment.

Background: The basic discrete emotions, namely, happiness, disgust, anger, fear, surprise, and sadness, are present across different cultures and societies. Facial emotion recognition is crucial in social interactions, but normal and pathological aging seem to affect this ability. The present research aims to identify the differences in the capacity for recognition of the six basic discrete emotions between young and older healthy controls (HOC) and mildly cognitively impaired patients (MCI). Method: The sample (N = 107) consisted of 47 young adults, 27 healthy older adults, and 33 MCI patients. Several neuropsychological scales were administered to assess the cognitive state of the participants, followed by the emotional labeling task on the Ekman 60 Faces test. Results: The MANOVA analysis was significant and revealed the presence of differences in the emotion recognition abilities of the groups. Compared to HOC, the MCI group obtained a significantly lower number of hits on fear, anger, disgust, sadness, and surprise. The happiness emotion recognition rate did not differ significantly among the three groups. Surprisingly, young people and HOC did not show significant differences. Conclusions: Our results demonstrated that MCI was associated with facial emotion recognition impairment, whereas normal aging did not seem to affect this ability.

Discrete negative emotions and goal disengagement in older adulthood: Context effects and associations with emotional well-being.

This study examined whether sadness, but not anger, could facilitate adaptive goal disengagement capacity in the context of older adult's stress-related experiences. To this end, we investigated whether the within-person effects of sadness and anger on older adults' goal disengagement capacity were moderated by stress perceptions and diurnal cortisol levels. In addition, we tested whether an association between sadness and goal disengagement capacity could protect emotional well-being when older adults experience higher than normal perceived stress or cortisol. The study used data from a 6-wave 10-year longitudinal study of 184 community-dwelling older adults (Mage = 72.08, SDage = 5.70). Participants' sadness, anger, goal disengagement capacity, perceived stress, diurnal cortisol levels, emotional well-being (i.e., positive and negative affect), and sociodemographic variables were assessed at each wave. Hierarchical linear modeling showed that within-person increases in sadness, but not anger, predicted increased goal disengagement capacity among older adults who generally secreted high levels of cortisol. Moreover, older adults' who disengaged more easily when they felt sad were protected from declines in positive affect during assessments in which they secreted high, but not low, levels of cortisol. The study's findings suggest that generally enhanced cortisol output may facilitate an association between sadness and older adults' goal disengagement capacity and that this process may protect against declines in emotional well-being. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Nietzsche’s Moral Psychology

Nietzsche’s Moral Psychology

Anger regulation choice-The role of age and habitual reappraisal.

The ability to choose emotion regulation strategies in accordance to contextual demands, known as emotion regulation flexibility, is key to healthy adaptation. While recent investigations on spontaneous emotion regulation choice tested the effects of emotional intensity and age using standardized negative pictures with no particular emotional quality, we elicited the discrete emotion of anger with personally relevant autobiographical memories in a sample of 52 younger and 41 older adults. In addition, we included habitual reappraisal as a predictor of emotion regulation choice. Our main hypothesis was that, compared with younger adults, older adults prefer less resource-demanding emotion regulation strategies (i.e., distraction) over more resource-demanding strategies (i.e., reappraisal), particularly if older adults' habitual reappraisal is low and the to-be-regulated anger is of high intensity. Surprisingly, our findings suggest that only older adults' emotion regulation choices depend on the emotional intensity of the autobiographical memory and habitual reappraisal. Only older adults with high habitual reappraisal preferred to reappraise their anger in situations of low anger intensity but switched to the less demanding strategy of distraction in high anger memories, indicating emotion regulation flexibility. This study extends previous research by testing emotion regulation choices in natural contexts and considering regulation habits. Although we replicate previous findings of emotion regulation flexibility according to emotional intensity in anger memories for older adults with high habitual reappraisal only, our findings illustrate the relevance of reappraisal habits to emotion regulation choice in age-comparative research. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Platform-centric vs. multi-party service failure: an examination of consumers’ negative word of mouth about sharing economy platforms

PurposeThis paper aims to identify platform-centric versus multiparty service failure on sharing economy platforms via topic modeling analysis of consumers’ negative online reviews. The authors also sought to understand consumers’ reactions to these experiences by detecting negative discrete emotions. The authors then contrasted consumers’ responses to platform-centric and multiparty service failure through the theoretical lens of failure controllability.Design/methodology/approachThe authors used a large-scale data set containing more than 81,000 negative app reviews on eight representative hospitality and tourism sharing economy platforms. Topic modeling coupled with emotion detection algorithms revealed 11 themes reflecting diverse forms of platform-centric versus multiparty service failure and their associations with negative discrete emotions based on regression analysis.FindingsThe 11 themes reflecting diverse forms of platform-centric versus multiparty service failure were as follows: app glitch, customer service, locating and pooling, account issues, transaction, offer redemption, interface challenges, intermediary inaction, service lateness and cancellation, incorrect order and fee structure. The analysis suggests that platform-centric service failure is more likely than multiparty service failure to elicit negative discrete emotions.Originality/valueThe research enriches the understanding of platform-related service failure beyond dyadic service interaction. In particular, the authors bring to light two forms of platform-related service failure that warrant scholarly attention: platform-centric versus multiparty service failure. By uncovering the distinct negative emotional associations of platform-centric versus multiparty service failure, the research adds novel empirical evidence to the service failure literature and the relevant attribution theory. Findings offer long-term implications for the sustainable development of sharing economies and platform businesses in contemporary hospitality.

CREATING A MODEL OF THE INFLUENCE OF SOUNDS ON THE EMOTIONAL STATE OF MAN

The environment is full of various sounds - signals registered by human and animal hearing organs, which in terms of frequency and strength merge into a monotonous, incoherent sound. The physical carriers of signals reaching the hearing organs are acoustic (sound) waves – mechanical waves that propagate in the air and are perceived by the hearing organs. Human hearing organs can perceive sounds in a fairly wide range of frequencies and intensities. The range of sounds heard by a person is limited by two threshold curves: the lower one is the threshold of perception, the upper one is the threshold of pain sensations. The human hearing threshold is 0 dB at a frequency of 1000 Hz, and the pain threshold occurs from a sound of 140 dB [2]. As long as there have been wars, it is known that mass battle cries and drumbeats oppress the enemy. The sirens of attack planes and bombers make him feel terrified and want to run away. Now an explanation has been found for this: loud sounds excite a person, contribute to the influx of a large amount of hormones into the blood, in particular, adrenaline, as a result of which there is a feeling of danger and fear [3]. There is a description of existing approaches to assess the impact of sounds on the emotional state of man, which will be the first step towards creating a model for analyzing the impact of sounds on the emotional state of man based on the theory of discrete emotions. Generated values for emotional evaluation of sounds.

May I have your Attention, please? An eye tracking study on emotional social media comments

Emotions are essential in today's complex information environments, as they catch readers' attention and impact the depth of information processing. In online interactions - such as user comments on social media platforms - emotions are increasingly present. We performed a preregistered eye-tracking study to understand the effects of emotional user comments on attention. Participants (N = 155) in our study read a series of user comments with different emotional tones. We measured the effects of emotions on information processing and visual attention by comparing the dwell times of participants of two experimental groups: a heuristic processing group and a systematic processing group. Our results revealed differences in visual attention towards comments with a negative versus positive valence and between the discrete emotions of anger and fear. These findings led to a discussion about emotions' role in information processing when individuals read user comments on social media.

Examining the effects of negative emotions on review helpfulness: The moderating role of product price

Negative emotional contents have been demonstrated to be persuasive when consumers judge review helpfulness across many existing studies. Drawing on emotions as social information (EASI) theory, signaling theory, and cognitive appraisal theory, we extended the current understanding of this underlying mechanism by considering the moderating role of the product price, an underestimated environmental signal. We focused on two negative emotions prominent in review content: anger and anxiety. A data sample of 73,408 reviews of businesses with three different price levels from Yelp.com was analyzed to explore how anger and anxiety embedded in online reviews impact consumers’ perceptions of review helpfulness and how product price moderates the relationship between these two emotions and review helpfulness. The results of linear regression analyses show that anger and anxiety positively impact review helpfulness in most cases, and product price moderates their relationships. Furthermore, our findings suggest that the positive effects of both discrete emotions on review helpfulness decrease as the price increases, and this influence is more pronounced in an angry emotion. Our findings advance the knowledge of discrete emotions on review helpfulness and provide practical insights for online retailers and third-party platforms to manage posted reviews efficiently.

Synergistic effects of disgust and anger on amygdala activation while recalling memories of interpersonal stress: An fMRI study

Occurrence of an unpleasant interpersonal event in daily life may cause an individual to experience unpleasant emotions and recall memories regarding it. These emotions, manifesting in daily social interactions, are often complex and mixed. In the laboratory, autobiographical recall is frequently used to induce emotions; however, it often involves recalling memories associated with a specific discrete emotion (e.g., sadness). To examine the neural activity of emotions similar to real-life experiences, we examined neural activity while recalling memories of stressful interpersonal events in daily life, without specifying a discrete emotion. Of the 23 university students recruited, 21 were analyzed and asked to freely recall memories and answer a series of questions on a monitor concerning their recalled memories while their neural activity was measured with functional magnetic resonance imaging. Amygdala activity increased while receiving the instructions, followed by a decrease in activity. This indicates that the participants' arousal and vigilance initially increased in response to a novel stimulus, and then decreased by habituation. Disgust and anger, which frequently occur as negative interpersonal feelings, were most prominently produced with strong associations with each other. More importantly, activation of the right amygdala while responding to questions regarding the recalled memories was positively correlated with disgust or anger only when not controlling for anger or disgust, respectively. These results indicate that responding to questions facilitated the generation of a mixed emotional response compared to during free recall alone. Furthermore, disgust and anger as a mixed emotion can synergistically activate amygdala.

Parents’ and friends’ responses to discrete negative emotions: Associations with adolescent emotional experiences

AbstractEmotion socialization (ES) impacts a range of youth socioemotional outcomes. However, research often examines parent socialization of negative emotions more broadly. Research examining multiple socializers demonstrates that variety in ES messages may promote flexibility in youth socio‐emotional adjustment. The current study examined how parents’ and friends’ supportive socialization of discrete negative emotions (anger, sadness, worry) related to adolescents’ emotional experiences. Eighty‐seven adolescents (50 girls; 13–15 years old, M age = 14.23 years) reported on parent and friend supportive ES in 8th grade. Sixty‐four of these adolescents reported their own emotional experiences in 9th and/or 10th grade. Parents’ supportive ES was higher than friends’ for sadness and worry. Divergence between parent and friend ES of sadness related to lower increases in anger over time. There were effects of convergence in ES of anger, as matches between parent and friend ES were related to less experience of all three negative emotions. There were unique effects of parent and friend ES of worry. Parent ES of worry related to adolescents’ balance of anger and sadness, whereas friend ES of worry related to decreased sadness over time. These findings suggest that ES and its relations with adolescent emotional experience varied by discrete emotions, as each carries a different meaning and function. Future research should examine processes connecting discrete emotional experiences within interactions and across time.

Expectant parents’ emotions evoked by pregnancy: A longitudinal dyadic analysis of couples in the Swedish Pregnancy Panel

RationaleHolistic antenatal care requires knowledge of individuals’ emotional response to pregnancy. Little is known about how a pregnant woman and her partner influence each other emotionally during a pregnancy. ObjectiveThis study examines six discrete emotions that expectant couples experience during pregnancy, how these emotions change mid-to late-pregnancy, and whether the partners’ emotional responses influence each other. MethodsA longitudinal dyadic study where pregnant women and their partners (1432 couples) rated the extent to which the pregnancy evoked joy, strength, security, worry, shame, and anger at pregnancy week 12–19, 22–24, and 36. Latent curve models with structured residuals identify levels of and change in these emotions over time, while accounting for between- and within-couple variance. ResultsPregnancy evoked mainly joy, strength, security, and worry, and lower levels of anger and shame. Pregnant women and partners felt similar levels of joy, strength, and security, but pregnant women felt more worry, shame, and anger. There was little to no mean-level change in all six measured emotions evoked by pregnancy (between-couple change), and no reciprocal effects between the partners (within-couple change). ConclusionsEmotions in mid-pregnancy were also felt in late pregnancy. Furthermore, the pregnant woman and her partner have individual emotional trajectories. The results can assist healthcare professionals and researchers target interventions to expectant mothers and partners, specifically by understanding emotional response to pregnancy as a stable confound and by not approaching the couple as one emotional unit.

Investigating the relationships between emotional experiences and behavioral responses amid the Covid‐19 pandemic: A cross‐sectional survey

The Covid‐19 pandemic produced a complex combination of intense negative emotions among the general public, influencing people's coping reactions toward the pandemic. Yet each discrete emotion may affect people's behaviors in different ways. Unveiling the specific emotion–behavior relationships can provide valuable implications for designing effective intervention programs. Through the lens of the appraisal theory of emotion, we assessed the relationships between negative emotions and pandemic‐related behaviors among the Chinese population midst the early outbreak of the pandemic. An anonymous online survey was distributed to mainland Chinese participants (n = 2976), which assessed individuals' emotional states and behavioral reactions to the pandemic. Consistent with the differential appraisal theme underlying each negative emotion as delineated by the appraisal theory, mixed relationships between emotions and pandemic‐related behaviors were revealed. Specifically, anxiety was positively associated with behaviors of seeking pandemic‐related information, sharing such information, and stockpiling preventive goods, yet, contrary to prediction, anxious people were reluctant to adopt preventive measures, which is maladaptive. Sad people sought information less frequently and exhibited lower intention to stockpile preventive goods; but, opposing prediction, they shared information less frequently. Angry people were more active in sharing information and in stockpiling preventive goods. These findings suggest that public health practitioners can utilize the emotion–behavior relationships to identify the vulnerable individuals who tend to adopt maladaptive coping behaviors, help them address emotional distress, and encourage their adoption of effective coping behaviors.

Linking Perceived Organizational Politics to Workplace Cyberbullying Perpetration: The Role of Anger and Fear.

The introduction of information and communication technologies in the workplace has extended the scope of bullying behaviors at work to the online context. However, less is known about the role of situational factors in encouraging cyberbullying behavior in the workplace. The purpose of this study is to investigate the role of perceived organizational politics in fueling cyberbullying in the workplace, and to examine the central role of negative emotions in this process. The sample comprised 279 faculty members of three large public sector universities in Islamabad, Pakistan. Results demonstrated that perceived organizational politics was positively associated with discrete negative emotions of anger and fear. Moreover, results indicated that anger was positively associated with cyberbullying perpetration, whereas fear was positively associated with face-to-face bullying victimization. Results also supported the idea that victims of face-to-face bullying may develop a positive attitude toward cyberbullying and retaliate against their more powerful face-to-face bullies online, possibly anonymously. We contribute to the literature by demonstrating that both forms of bullying can co-occur in the workplace as a consequence of perceived organizational politics, and the two roles—bully and victim—may be swapped among victims and perpetrators.

Recognition of Student Emotions in Classroom Learning Based on Image Processing

During the learning process, students should keep positive emotions like delightfulness, cheerfulness, joy, and enthusiasm, and try to realize happy learning. This would improve learning efficiency and learning effect. However, most of the existing models cannot recognize negative discrete emotions and dimensional emotions, such as indignation and sadness, of students in classroom learning. To solve the problem, this paper deeply explores the recognition of student emotions in classroom learning based on image processing. Specifically, the authors designed a recognition model of emotional state of classroom learning, modeled the discrete emotions of students in classroom learning, and discussed the relationship between learning effect, response efficacy and stimulus. Furthermore, the generation process of student emotions in classroom learning was analyzed, and the recognition model of emotional state of classroom learning was finalized based on ResNet18. In addition, the recognition model was optimized by introducing the local importance pooling and adding a recalibration module. The experimental results verify the effectiveness of the constructed model.

Crisis factors, emotions, and perceived informational channel significance during emergencies

ABSTRACT Individuals’ information seeking and the role of emotions are important to crisis communication research. A survey was conducted (N = 1100) to examine the chain effects of crisis factors on college young adults’ discrete emotions and perceived channel significance. Key findings suggest that crisis factors affect channel significance both directly and indirectly. Crisis factors overall elicit more fear and anxiety (attribution-independent emotions) than anger and sympathy (attribution-dependent emotions). Uncertainty does not affect perceived channel significance, while urgency prompts individuals to seek out non-traditional media and severity affects information seeking on all channels. Attribution-independent emotions such as fear and sadness have positive mediating effects, and attribution-dependent emotions such as anger and sympathy have negative mediating effects. Finally, media richness per se may not be a prominent concern during emergencies.

Memory effects of semantic attributes: A method of controlling attribute contamination.

Rating norms for semantic attributes (e.g., concreteness, familiarity, valence) are widely used to study the content that people process as they encode meaningful material. Intensity ratings of individual attributes have been manipulated in numerous experiments with a range of memory paradigms, but those manipulations are contaminated by substantial correlations with the intensity ratings of other attributes. A method of controlling such contamination is needed, which requires a determination of how many distinct attributes there are among the large collection of attributes for which published norms are available. Identification of overlapping words in multiple rating projects yielded a data base containing normed values for each word's perceived intensity (M rating) and ambiguity (rating SD) on 20 different attributes. Principal component analyses then revealed that the intensity space was spanned by just three latent semantic attributes, and the ambiguity space was spanned by five. Psychologically, the big three intensity factors (emotional valence, size, age) were highly interpretable, as were the big five ambiguity factors (discrete emotion, emotional valence, age, meaningfulness, and verbatim memory). We provide a data base of intensity and ambiguity factor scores that can be used to conduct uncontaminated studies of the memory effects of the intensity and ambiguity of latent semantic attributes.

Coaching older adults discharged home from the emergency department: The role of competence and emotion in following up with outpatient clinicians

ObjectiveMotivating older adults to follow up with an outpatient clinician after discharge from emergency departments (ED) is beneficial yet challenging. We aimed to answer whether psychological needs for motivation and discrete emotions observed by care transition coaches would predict this behavioral outcome. MethodsCommunity-dwelling older adults following ED discharge were recruited from three EDs in two U.S. states. We examined home visit notes documented by coaches (N = 725). Retrospective chart reviews of medical records tracked participants’ health care utilization for 30 days. ResultsObserved knowledge-based competence predicted higher likelihood of outpatient follow-up within 30 days, while observed sadness predicted a lower likelihood of follow-up within seven days following discharge. Moreover, participants who demonstrated happiness were marginally more likely to have an in-person follow-up within seven days, and those who demonstrated knowledge-based competence were more likely to have an electronic follow-up within 30 days. ConclusionsKnowledge-based competence and emotions, as observed and documented in coach notes, can predict older adults’ subsequent outpatient follow-up following their ED-discharge. Practice implicationsIntervention programs might encourage coaches to check knowledge-based competence and to observe emotions in addition to delivering the content. Coaches could also customize strategies for patients with different recommended timeframes of follow-up.

Processing emotional prosody in a foreign language: the case of German and Hebrew

This study investigated the universality of emotional prosody in perception of discrete emotions when semantics is not available. In two experiments the perception of emotional prosody in Hebrew and German by listeners who speak one of the languages but not the other was investigated. Having a parallel tool in both languages allowed to conduct controlled comparisons. In Experiment 1, 39 native German speakers with no knowledge of Hebrew and 80 native Israeli speakers rated Hebrew sentences spoken with four different emotional prosodies (anger, fear, happiness, sadness) or neutral. The Hebrew version of the Test for Rating of Emotions in Speech (T-RES) was used for this purpose. Ratings indicated participants’ agreement on how much the sentence conveyed each of four discrete emotions (anger, fear, happiness and sadness). In Experient 2, 30 native speakers of German, and 24 Israeli native speakers of Hebrew who had no knowledge of German rated sentences of the German version of the T-RES. Based only on the prosody, German-speaking participants were able to accurately identify the emotions in the Hebrew sentences and Hebrew-speaking participants were able to identify the emotions in the German sentences. In both experiments ratings between the groups were similar. These findings show that individuals are able to identify emotions in a foreign language even if they do not have access to semantics. This ability goes beyond identification of target emotion; similarities between languages exist even for “wrong” perception. This adds to accumulating evidence in the literature on the universality of emotional prosody.

Rumour identification on Twitter as a function of novel textual and language-context features.

Social microblogs are one of the popular platforms for information spreading. However, with several advantages, these platforms are being used for spreading rumours. At present, the majority of existing approaches identify rumours at the topic level instead of at the tweet/post level. Moreover, prior studies used the sentiment and linguistic features for rumours identification without considering discrete positive and negative emotions and effective part-of-speech features in content-based approaches. Similarly, the majority of prior studies used content-based approaches for feature generation, and recent context-based approaches were not explored. To cope with these challenges, a robust framework for rumour detection at the tweet level is designed in this paper. The model used word2vec embeddings and bidirectional encoder representations from transformers method (BERT) from context-based and discrete emotions, linguistic, and metadata characteristics from content-based approaches. According to our knowledge, we are the first ones who used these features for rumour identification at the tweet/post level. The framework is tested on four real-life twitter microblog datasets. The results show that the detection model is capable of detecting 97%, 86%, 85%, and 80% of rumours on four datasets respectively. In addition, the proposed framework outperformed the three latest state-of-the-art baselines. BERT model presented the best performance among context-based approaches, and linguistic features are best performing among content-based approaches as a stand-alone model. Moreover, the utilization of two-step feature selection further improves the detection model performance.