Emotion Prediction Research Articles

ARMNet: A Network for Image Dimensional Emotion Prediction Based on Affective Region Extraction and Multi-Channel Fusion

Compared with discrete emotion space, image emotion analysis based on dimensional emotion space can more accurately represent fine-grained emotion. Meanwhile, this high-precision representation of emotion requires dimensional emotion prediction methods to sense and capture emotional information in images as accurately and richly as possible. However, the existing methods mainly focus on emotion recognition by extracting the emotional regions where salient objects are located while ignoring the joint influence of objects and background on emotion. Furthermore, in the existing literature, when fusing multi-level features, no consideration has been given to the varying contributions of features from different levels to emotional analysis, which makes it difficult to distinguish valuable and useless features and cannot improve the utilization of effective features. This paper proposes an image emotion prediction network named ARMNet. In ARMNet, a unified affective region extraction method that integrates eye fixation detection and attention detection is proposed to enhance the combined influence of objects and backgrounds. Additionally, the multi-level features are fused with the consideration of their different contributions through an improved channel attention mechanism. In comparison to the existing methods, experiments conducted on the CGnA10766 dataset demonstrate that the performance of valence and arousal, as measured by Mean Squared Error (MSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²), has improved by 4.74%, 3.53%, 3.62%, 1.93%, 6.29%, and 7.23%, respectively. Furthermore, the interpretability of the network is enhanced through the visualization of attention weights corresponding to emotional regions within the images.

Whether Social Media Negative Emotion Could Forecast the Risk of Enterprise Finance: Evidence from Baidu Tieba

In the context of the current era, as a new form of information dissemination, social media has penetrated into every field of people’s life, and its impact on the financial industry has also attracted more and more scholars’ attention. From the perspective of social media, this paper focuses on the impact and prediction of negative emotions reflected by social media on corporate financial risk. In this paper, Pearson correlation coefficient is used for correlation analysis, and a linear regression model is built to analyze the relationship between negative social media and corporate finance. The results show that enterprises and investors can judge the financial risks of enterprises through the negative emotions of social media, thus reducing the losses of enterprises and investors. The conclusions of this study can improve the risk avoidance ability of enterprises to avoid negative emotions on social media, and provide important reference value for future operations.

Automated urban landscape design: an AI-driven model for emotion-based layout generation and appraisal

The evolution of a city is significantly shaped by the design of its urban landscape. The advancement of artificial intelligence has substantially increased convenience for individuals. This research proposes an urban landscape layout model powered by artificial intelligence that automatically generates urban landscape design based on deep learning (URDDL) with two dimensions: emotional tendency and urban landscape appraisal. The input image represents land use and surrounding road conditions, while the output image depicts the selection of the main entrance and the internal spatial function layout. The Pix2Pix model is trained to learn the internal function layout based on varying land use and road conditions. Additionally, a domain-specific dictionary is constructed using an existing semantic resource vocabulary, where positive and negative sentiment words are compared with their corresponding sentiment values, focusing on categories such as Stimulate, Sense, and Action. Experimental results indicate that the absolute average error of the URDDL model is 91.31%, with a maximum error of 96.87%. The degree of fit is highly appropriate for evaluating the emotional prediction of urban landscapes. The findings demonstrate that the URDDL model outperforms traditional design methods regarding generated results, suggesting its potential for future applications in automated landscape design.

Individual differences in emotion prediction and implications for social success.

The social world requires people to predict others' thoughts, feelings, and actions. People who successfully predict others' emotions experience significant social advantages. What makes a person good at predicting emotions? To predict others' future emotional states, a person must know how one emotion transitions to the next. People learn how emotions transition from at least two sources: (a) internal information, or one's own emotion experiences, and (b) external information, such as the social cues detected in a person's face. Across five studies collected between 2018 and 2020, we find evidence that both sources of information are related to accurate emotion prediction: individuals with atypical personal emotion transitions, difficulty understanding their own emotional experiences, and impaired emotion perception displayed impaired emotion prediction. This ability to predict others' emotions has real-world social implications. Individuals who make accurate emotion predictions have better relationships with their friends and communities and experience less loneliness. In contrast, disruptions in both internal and external information sources explain prediction inaccuracy in individuals with social difficulties, specifically with social communication difficulties common in autism spectrum disorder. These findings provide evidence that successful emotion prediction, which relies on the perception of accurate internal and external data about how emotions transition, may be key to social success. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Virtual Reality-enabled High-Performance Emotion Estimation with the Most Significant Channel Pairs

Human-computer interface (HCI) and electroencephalogram (EEG) signals are widely used in user experience (UX) interface designs to provide immersive interactions with the user. In the context of UX, EEG signals can be used within a metaverse system to assess user engagement, attention, emotional responses, or mental workload. By analyzing EEG signals, system designers can tailor the virtual environment, content, or interactions in real time to optimize UX, improve immersion, and personalize interactions. However, in this case, in addition to the signals' processing cost and classification accuracy, cybersickness in Virtual Reality (VR) systems needs to be resolved. At this point, channel selection methods can perform better for HCI and UX applications by reducing noisy and redundant information in generally unrelated EEG channels. For this purpose, a new method for EEG channel selection based on phase-locking value (PLV) analysis is proposed. We hypothesized that there are interactions between EEG channels in terms of PLV in repeated tasks in different trials of the emotion estimation experiment. Subsequently, frequency-based features were extracted. The features were classified by dividing them into bags using the Multiple-Instance Learning (MIL) variant. This study provides higher classification performance using fewer EEG channels for emotion prediction. The performance rate obtained in binary classification with the Random Forests (RF) algorithm is at a promising level of 99%. The proposed method achieved an accuracy of 99.38% for valence using all channels on the new dataset (VREMO) and 98.13% with channel selection. The benchmark dataset (DEAP) achieved accuracies of 98.16% using all channels and 98.13% with selected channels.

A Reinforcement Learning-Based Approach for Promoting Mental Health Using Multimodal Emotion Recognition

This research aims to enhance mental well-being by addressing symptoms of anxiety and depression through a personalized, culturally specific multimodal emotion prediction system. It employs an emotionally aware Reinforcement Learning (RL) agent to suggest tailored Cognitive Behavioral Therapy (CBT) activities. The study focuses on developing precise, individualized emotion prediction models using facial expressions, vocal tones, and text, and integrates these models with the RL agent for emotionally aware CBT recommendations. The mHealth approach combines deep learning models with RL, achieving accuracies of 72% for facial expressions, 73% for vocal tones, and 86% for text, all fine-tuned for the Sri Lankan context. Validation through real-world use and user feedback consistently demonstrated that each model exceeds 70% accuracy, fulfilling the objective of precise emotion prediction. A weighted algorithm was introduced to refine the emotion prediction experience and personalize forecasts across the three modalities to enhance mental well-being. The RL-enabled agent suggests CBT activities approved by mental health professionals, tailored based on predicted emotions, and delivered through the same mHealth application. The effectiveness of these interventions was assessed using the DASS-21 questionnaire, revealing significant reductions in depression scores (from 21.08 to 13.54) and anxiety scores (from 19.85 to 10.46) in the study group compared to the control group. The study concludes that integrating multimodal emotion prediction models with RL-based CBT suggestions positively impacts mental well-being and contributes to personalized mental health interventions.

Personality and emotion—A comprehensive analysis using contextual text embeddings

Personality and emotions have always been closely intertwined since humans evolved, adapting to these two forms. Emotions are indicative of a person’s personality, and vice versa. This paper aims to investigate the complex relationship between these two fundamental aspects of human behavior using the concepts of machine learning and statistical analysis. The objective is to automate the process of determining the relationship between personality traits of the MBTI (Myers-Briggs Type Indicator) and Ekman’s emotions based on the context of user-written social media posts using contextual embedding. A robust mechanism is employed, involving two main phases to figure out emotions from the social media posts. The first phase involves determining the cosine similarity scores between each MBTI personality trait and predefined emotions. The second phase introduces a cross-dataset learning approach where several machine learning models are trained on a dataset labeled with emotions to learn patterns of emotions found in the text. After training, these models utilize the patterns they learned to predict emotions in a targeted dataset. With an overall accuracy of 85.23%, the Support Vector Machine (SVM) is chosen as the most effective and high-performing model for emotion prediction tasks. We employed a vetting mechanism combining two approaches to improve accuracy, reliability, and trustworthiness for the final emotion prediction. Finally, using statistical quantification, this paper finds patterns that link each MBTI personality trait with Ekman emotions. It reveals that extroverts (E), sensing (S), and feeling (F) personality types are more likely to share joyful and surprising emotional posts, while individuals with extroversion (E), intuition (N), thinking (T), and perception (P) traits tend to express negative emotions such as anger and disgust. Conversely, introverts (I), intuitive (N), thinking (T), and judging (J) personalities are more inclined to share posts reflecting fear and sadness. This comprehensive study provides valuable insights on how individuals with different personality types typically express emotions on social media.

A Study on the Relationship between Campus Environment and College Students’ Emotional Perception: A Case Study of Yuelu Mountain National University Science and Technology City

The campus environment directly impacts college students’ psychological and emotional well-being, influencing their behavioral performance and the development of their personalities. Investigating the complex relationship between the campus spatial environment and students’ emotions is crucial for designing urban environments that support mental health. Using Yuelu Mountain National University Science and Technology City as a case study, this research developed a framework to analyze campus environment characteristics and emotional perception. The study quantitatively assessed emotional perceptions, examined the specific contributions of different campus environment elements to individual emotions, and created an emotion prediction map to explore these relationships in depth. The results indicate that “campus greenery” and “diversity” negatively affect “disappointment” and “depression”, while “sky views” positively impact “happiness” and “sense of security”. Additionally, “diversity” positively affects “relaxation”, and “campus greenery” and “diversity” have negative effects on “disappointment” and “depression”, with “diversity” having a particularly strong positive effect on “relaxation”. The pronounced spatial clustering of emotional perceptions on campus further underscores the significant influence of the campus environment on individual emotional experiences. As the first study to explore the mechanisms underlying the emotional perceptions of Chinese college students in relation to the campus environment, this research overcomes the limitations of traditional environmental assessment indicators by identifying campus environmental elements and psychological factors that better align with the psychological needs of college students. This provides a scientific basis for optimizing campus environments based on the emotional perceptions of students, thereby supporting mental health promotion and guiding campus environment construction. Moreover, the research methodology is broadly applicable. The integration of campus environment image data and deep learning offers a significant tool for assessing campus space and environmental perception, thereby enhancing human-centered environmental assessment and prediction while more accurately reflecting architectural space perception.

Exploring the Impact of Visual and Aural Elements in Urban Parks on Human Behavior and Emotional Responses

As cities progress into high-quality developments, the demand for urban parks that enhance residents’ well-being and sustainability is increasing. Traditional visual-centric design methods no longer suffice. Given that vision and hearing are the primary sensory pathways through which people perceive their environment, exploring their relationship with landscape experiences offers a novel perspective for optimizing the audiovisual perception quality of urban parks. This study explores the relationship between visual and auditory elements and landscape experiences to optimize urban parks’ sensory quality. Using visual perception, soundscape perception, sound source perception, and behavioral vitality, this study evaluates the audiovisual perception quality of a representative wetland park in Chengdu’s ring ecological zone. By quantifying relationships between audiovisual characteristics, behavioral vitality, and emotional feedback, several emotional assessment models were constructed. The results show that lawns, pavements, and sound pressure levels significantly impact vitality. A sound pressure level of 77 dB has been identified as a critical threshold in emotional perception models. Consequently, distinct emotional prediction models can be employed to enhance landscape design across various sound pressure level zones. This research provides scientific evidence and flexible strategies for designing urban open spaces that improve landscape experiences based on multisensory perception.

The influence of contextual uncertainty on facial expression processing: Evidence from behavior and ERPs

The brain helps individuals build expectations based on emotional prediction, facilitating the processing of faces in social interactions. Due to the intricacy of the environment, accurately predicting emotions remains a formidable task. Contextual uncertainty represents a state characterized by the inability to predict when, how, and why events occur. It leads to intensified sentiments and triggers adverse emotions like anxiety. Therefore, comprehending the influences of contextual uncertainty carries importance. The present study utilized event-related potentials (ERPs) technology to investigate contextual uncertainty's influence on facial expression processing. We employed a novel S1-S2 paradigm, using scene images as S1 and faces as S2. From the learning phase into the testing phase, the certain to uncertain group (CER to UNC) experienced more unpredictability (increased uncertainty), whereas the uncertain to certain group (UNC to CER) experienced more predictability (decreased uncertainty). This allowed for manipulating dynamic alterations in predictive relationships. The behavioral results showed that the valence ratings of neutral facial expressions were more negative in the CER to UNC group with increased contextual uncertainty. The ERP results showed that the more negative SPN (stimulus preceding negativity) amplitudes and positive LPP (late positive potential) amplitudes were observed in the UNC to CER group with decreased contextual uncertainty, compared to the CER to UNC group with increased contextual uncertainty. These findings have indicated that contextual uncertainty affects facial expression processing. In summary, these results contributed to comprehending the contextual uncertainty.

BLNN:a muscular and tall architecture for emotion prediction in music

BLNN:a muscular and tall architecture for emotion prediction in music

How do emotions evolve? The effect of emotions in the interactive scenes of a new product trial

As people pay more attention to users’ subjective experiences, emotion becomes more important for productions and designers. Emotion has been defined, classified, and evaluated through interaction process in different fields, but how emotions evolve during user interaction and affect the user experience bring a new research topic. In this paper, emotions are divided into instantaneous emotions (IE) and perceived emotions (PE) for research. As a result, different IE have different evolution rules (Curious trends to stay, Amazed trends to transform), and certain PE do have significant effects on user experience in different stages. Also, we find non-correspondence between IE and PE. The results provide designers with more details of users’ feedback and bring more help for emotion prediction and user experience evaluation.

Unifying emotion-oriented and cause-oriented predictions for emotion-cause pair extraction

Emotion-cause pair extraction (ECPE) is an extraction task aiming to simultaneously identify the emotions and causes from the text without emotion annotations. Let ci and cj represent the emotion clause and the cause clause of a document, respectively, and we can predict one from the other and vice versa. Previous works fail to take advantage of this bidirectional opportunity. We refer to the prediction from ci to cj, i.e., ci→cj, as an emotion-oriented cause prediction (EoCP) task and the prediction from cj to ci, i.e., cj→ci, as a cause-oriented emotion prediction (CoEP) task. After redefining the ECPE task, we propose a novel unified architecture for ECPE, which incorporates EoCP and CoEP as cells and unifies them into a single-chain architecture. Additionally, we redefine emotion-cause pair extraction as a closed-loop structure detection problem to alleviate the mismatch between emotion and cause clauses. To enhance the training of the architecture, we provide a procedure for estimating the confidence of the extraction system for its emotion-cause pairs. We demonstrate the superiority of our proposed model through extensive experiments on two public datasets, achieving a new state-of-the-art performance. Furthermore, our method particularly achieves significant improvements in multiple emotion-cause pair extraction.

LCSEP: A Large-Scale Chinese Dataset for Social Emotion Prediction to Online Trending Topics

LCSEP: A Large-Scale Chinese Dataset for Social Emotion Prediction to Online Trending Topics

A Visual Approach to Tracking Emotional Sentiment Dynamics in Social Network Commentaries

The expansion of social media has unlocked a real-time barometer of public opinion. This paper introduces a novel framework to analyze sentiment shifts in social network comment sections, a reflection of the broader public discourse over time. Leveraging a pre-trained uncased RoBERTa model, we predict emotional scores from user comments, mapping these to key sentiment trends such as Approval, Toxicity, Obscenity, Threat, Hate, Offensive, and Neutral. Our methodology employs machine learning techniques to train a dataset that connects emotional scores with these trends, generating trend probability scores. We utilize a bottom-up recursive algorithm to aggregate emotional scores within comment threads, enabling the prediction of trend scores using three distinct aggregation methods. The results demonstrate that our emotional prediction model achieves an AUC of 0.92, and XGBoost stands out with an F1 score exceeding 0.40. Our research elucidates the temporal evolution of online public sentiment, enhancing the understanding of digital social dynamics and offering insights for strategic online interaction, intervention, and content moderation.

Predicting game-induced emotions using EEG, data mining and machine learning

BackgroundEmotion is a complex phenomenon that greatly affects human behavior and thinking in daily life. Electroencephalography (EEG), one of the human physiological signals, has been emphasized by most researchers in emotion recognition as its specific properties are closely associated with human emotion. However, the number of human emotion recognition studies using computer games as stimuli is still insufficient as there were no relevant publicly available datasets provided in the past decades. Most of the recent studies using the Gameemo public dataset have not clarified the relationship between the EEG signal’s changes and the emotion elicited using computer games. Thus, this paper is proposed to introduce the use of data mining techniques in investigating the relationships between the frequency changes of EEG signals and the human emotion elicited when playing different kinds of computer games. The data acquisition stage, data pre-processing, data annotation and feature extraction stage were designed and conducted in this paper to obtain and extract the EEG features from the Gameemo dataset. The cross-subject and subject-based experiments were conducted to evaluate the classifiers’ performance. The top 10 association rules generated by the RCAR classifier will be examined to determine the possible relationship between the EEG signal's frequency changes and game-induced emotions.ResultsThe RCAR classifier constructed for cross-subject experiment achieved highest accuracy, precision, recall and F1-score evaluated with over 90% in classifying the HAPV, HANV and LANV game-induced emotions. The 20 experiment cases’ results from subject-based experiments supported that the SVM classifier could accurately classify the 4 emotion states with a kappa value over 0.62, demonstrating the SVM-based algorithm’s capabilities in precisely determining the emotion label for each participant’s EEG features’ instance.ConclusionThe findings in this study fill the existing gap of game-induced emotion recognition field by providing an in-depth evaluation on the ruleset algorithm’s performance and feasibility of applying the generated rules on the game-induced EEG data for justifying the emotional state prediction result.

Deep parallel contextual analysis framework based emotion prediction in community wellness communications on social media

Understanding public emotion on social media about community wellness is crucial for enhancing health awareness and guiding policy-making. In order to more fully mine the deep contextual semantical information of short texts and further enhance the effectiveness of emotion prediction in social media, we propose the Deep Parallel Contextual Analysis Framework (DPCAF) in the community wellness domain, specifically addressing the challenges of limited text length and available semantical features in social media text. Specifically, at the embedding layer, we first utilize two different word embedding techniques to generate high-quality vector representations, aiming to achieve more comprehensive semantical capture, stronger generalization ability, and more robust model performance. Subsequently, in the deep contextual layer, the obtained representations are fused with POS and locational representations, and processed through a deep parallel layer composed of Convolutional Neural Networks and Bidirectional Long Short-Term Memory Network. An attention model is then used to further extract semantical features of social media texts. Finally, these deep parallel contextual representations are post-integrated for emotion prediction. Experiments on a dataset collected from social media regarding community wellness demonstrate that compared to benchmark models, DPCAF achieves at least a 4.81 % increase in Precision, a 3.44 % increase in Recall, and a 10.81 % increase in F1-score. Relative to the most advanced models, DPCAF shows a minimum improvement of 2.65 % in Precision, 3.02 % in Recall, and 2.53 % in F1-score.

Psychotherapies for the treatment of borderline personality disorder: A systematic review.

Borderline personality disorder (BPD) is the most common personality disorder, affecting 1.8% of the general population, 10% of psychiatric outpatients, and 15%-25% of psychiatric inpatients. Practice guidelines recommend psychotherapies as first-line treatments. However, psychotherapies commonly used for the treatment of BPD are numerous, and little is known about the comparative effectiveness of each individual psychotherapy versus treatment as usual (TAU) or other psychotherapies. To systematically assess the comparative effectiveness of commonly used psychotherapies versus TAU or versus other psychotherapies for BPD treatment. We conducted systematic literature searches in MEDLINE, EMBASE, the Cochrane Library, and APA PsycINFO up to July 14, 2022, and searched reference lists of pertinent articles and reviews. Inclusion criteria were (a) patients 13 years or older with a diagnosis of BPD, (b) treatment with commonly used psychotherapies, (c) comparison with TAU or another psychotherapy, (d) assessment of relevant BPD-related health outcomes, and (e) randomized or nonrandomized trials or controlled observational studies. Two investigators independently screened abstracts and full-text articles and graded the certainty of evidence using the Grading of Recommendations Assessment, Development, and Evaluation approach. We found 25 psychotherapy studies meeting inclusion criteria with data on 2,545 participants. Seventeen studies compared nine psychotherapies with TAU and nine studies compared eight psychotherapies with another psychotherapy for the treatment of BPD. Overall, both TAU and included psychotherapies were effective in treating the severity and symptoms of BPD. Moderate certainty of evidence suggests that systems training for emotional predictability and problem solving is more effective than TAU for the treatment of BPD; low certainty of evidence suggests that dialectical behavior therapy, schema therapy, transference-focused psychotherapy, acceptance and commitment therapy, manual-assisted cognitive therapy, and cognitive behavioral therapy are more effective than TAU for treating BPD. We were unable to draw conclusions from head-to-head comparisons of psychotherapies, which were limited to single studies with very low to low certainty of evidence. All commonly used psychotherapies improve BPD severity, symptoms, and functioning. Our assessment found no strong evidence suggesting that any one psychotherapy is more beneficial than another. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Correlation of negative emotion, fatigue level and internet addiction in college students: implication for coping strategies

BackgroundInternet addiction has an important influence on the development of physical and mental health of college students. The purpose of this study is to evaluate the current status and the correlation between college students’ negative emotion, fatigue level and Internet addiction disorder, and to provide reference for the care and management of college students.MethodsWe conducted a questionnaire survey on a cluster sample of college students from October to November 15, 2022. Internet addiction scale, fatigue assessment scale and positive and negative emotion scale were used for survey. Pearson correlation analysis and mediating effect test were performed to analyze the correlation and effects.ResultsA total of 1546 valid questionnaires were collected. The incidence of internet addiction in college student was 20.38%. The total score of internet addiction was 52.94 ± 12.47, the total fatigue score was 69.27 ± 3.19, the score of positive emotion of college students was 31. 41 ± 5.09, and the negative emotion score was 18.54 ± 5.68. The total score of internet addiction were positively correlated with score of negative emotion (all P < 0. 05). The total score of internet addiction scale of college students were positively correlated and each factor score of with the score of fatigue severity (all P < 0. 05). Fatigue played an intermediary role in the prediction of negative emotion and internet addiction of college students, with an intermediary role of-0.433, accounting for 76.35% of the total effect.ConclusionThe college students’ positive emotion may be strengthened to reduce their fatigue level and negative emotion so as to reduce internet addiction.

MGEED: A Multimodal Genuine Emotion and Expression Detection Database

Multimodal emotion recognition has attracted increasing interest from academia and industry in recent years, since it enables emotion detection using various modalities, such as facial expression images, speech and physiological signals. Although research in this field has grown rapidly, it is still challenging to create a multimodal database containing facial electrical information due to the difficulty in capturing natural and subtle facial expression signals, such as optomyography (OMG) signals. To this end, we present a newly developed Multimodal Genuine Emotion and Expression Detection (MGEED) database in this paper, which is the first publicly available database containing the facial OMG signals. MGEED consists of 17 subjects with over 150K facial images, 140K depth maps and different modalities of physiological signals including OMG, electroencephalography (EEG) and electrocardiography (ECG) signals. The emotions of the participants are evoked by video stimuli and the data are collected by a multimodal sensing system. With the collected data, an emotion recognition method is developed based on multimodal signal synchronisation, feature extraction, fusion and emotion prediction. The results show that superior performance can be achieved by fusing the visual, EEG and OMG features. The database can be obtained from <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/YMPort/MGEED</uri> .