Emotion Analysis Research Articles

Study on the Reception and Dissemination of the Brewitt-Taylor’ English Translation of Sanguo yanyi

Sanguo yanyi, a masterpiece among Chinese historical novels, boasts profound historical, cultural, and artistic value. By applying the theory of reader acceptance, we gain insights into how foreign readers perceive, interpret culturally, and emotionally experience the English translation of this novel. This understanding further uncovers the work's impact and potential in international cultural exchange. Our research utilizes the Octopus Collector to gather reader reviews of Brewitt-Taylor's English translation of the novel titled Romance of the Three Kingdoms. Subsequently, we employ KHcoder for data analysis, adopting a mixed qualitative and quantitative approach to examine high-frequency words and semantic graphs. The findings indicate that, overall, overseas readers hold a positive emotional attitude towards Brewitt-Taylor's translation. In terms of emotional analysis, readers highly rate the translator and characters, followed by the plot and narrative. This suggests that, for the international dissemination of classics, the ideological content and inherent values of the works themselves are crucial factors influencing reader acceptance. Consequently, studying overseas readers' evaluations and acceptance of "Romance of the Three Kingdoms" provides valuable insights for selecting translation strategies and promoting the international spread of Chinese literary classics.

Optimizing Deep Learning-Based Natural Language Processing for Sentiment Analysis

Deep learning (DL)-based natural language processing (NLP) technologies are applied and optimized for the analysis of emotional implications in text data. Understanding emotional intricacies in text has become necessary for a variety of industries, like social media analysis, customer feedback interpretation, and mental health monitoring, due to the exponential rise of digital material. The study emphasizes the difficulties associated with the automation of emotion analysis, including the diversities of the text formats and the NLP complexities. This research gathers that text-based emotion analysis data and pre-processing techniques are utilized for the analysis of emotion, including normalizing methods such as tokenization and lemmatization, along with the removal of stop words and punctuation. The model incorporates pre-trained embeddings and attention mechanisms to capture contextual information and emotional subtleties for any language. The study proposes the hybrid model using tuned crow search optimized dynamic graph neural network (TCSO-DGNN) on an automatically optimized process to enhance the accuracy of emotion detection. The proposed model results on emotion analysis data and superior results are obtained, indicating better performance in precision (94.72%), accuracy (96.43%), recall (94.36%), and F1-score (93.02%). The findings indicate that the inclusion of TCSO-DGNN significantly enhances the identification of complex emotional expressions concerning traditional NLP techniques. This study explores the potential of integrated DL approaches to refine the capabilities of emotion analysis tools, particularly in contexts requiring refined interpretations of human emotions expressed online. Additionally, it contributes to academic discourse in the field of emotion analysis while providing practical insights for developers of NLP applications across business and public service sectors.

Dynamic harmony: Unveiling therapeutic attunement in emotionally focused couples therapy via machine learning

AbstractObjectiveThe goals of the study were to examine therapists' and clients' emotional states and expressions in an emotionally focused therapy (EFT) couple session, to assess therapeutic attunement between the clients and the therapist, and to explore its alignment with EFT techniques.BackgroundTherapeutic attunement is crucial for fostering a therapeutic alliance in couples therapy, yet examining triadic relationships between therapist and partners is methodologically challenging. This case study introduces a novel computational social science approach to capture attunement in an EFT session.MethodA full‐length, publicly available EFT session video was analyzed. We generated text, audio, and image data for computerized tracking and conducted a multimodal analysis of emotions using mixture of experts machine learning models.ResultsSeven emotion states were analyzed: anger, fear, surprise, disgust, joy, sadness, and neutral. The results indicated a close alignment between the couple and the therapist's emotions, suggesting high attunement. Three types of attunement by timing were identified: on time, therapist initiated, and delayed. Attunement peaks aligned with EFT techniques.ConclusionHigh levels of therapeutic attunement, facilitated by EFT techniques, can be effectively captured and analyzed using machine learning.ImplicationsThis study highlights the feasibility of using machine learning to track attunement dynamics and aids therapists in exploring therapeutic ruptures.

Face and Voice Recognition-Based Emotion Analysis System (EAS) to Minimize Heterogeneity in the Metaverse

The metaverse, where users interact through avatars, is evolving to closely mirror the real world, requiring realistic object responses based on users’ emotions. While technologies like eye-tracking and hand-tracking transfer physical movements into virtual spaces, accurate emotion detection remains challenging. This study proposes the “Face and Voice Recognition-based Emotion Analysis System (EAS)” to bridge this gap, assessing emotions through both voice and facial expressions. EAS utilizes a microphone and camera to gauge emotional states, combining these inputs for a comprehensive analysis. It comprises three neural networks: the Facial Emotion Analysis Model (FEAM), which classifies emotions using facial landmarks; the Voice Sentiment Analysis Model (VSAM), which detects vocal emotions even in noisy environments using MCycleGAN; and the Metaverse Emotion Recognition Model (MERM), which integrates FEAM and VSAM outputs to infer overall emotional states. EAS’s three primary modules—Facial Emotion Recognition, Voice Emotion Recognition, and User Emotion Analysis—analyze facial features and vocal tones to detect emotions, providing a holistic emotional assessment for realistic interactions in the metaverse. The system’s performance is validated through dataset testing, and future directions are suggested based on simulation outcomes.

Introduction to the Special Issue on Deep Learning for Robust Human Body Language Understanding

This editorial introduces the Special Issue on Deep Learning for Robust Human Body Language Understanding , hosted by the ACM Transactions on Multimedia Computing, Communications, and Applications in 2024. Human body language understanding has emerged as a critical research area, addressing challenges in analyzing, recognizing, and synthesizing multimodal human behavioral data such as gestures, poses, facial expressions . This Special Issue highlights recent advancements in deep learning techniques that enhance the robustness, scalability, and applicability of human body language understanding in diverse scenarios, including healthcare, education, and barrier-free human-computer interaction systems. The issue features a total of eight research articles focusing on key aspects of human body language understanding. These contributions are categorized into major research areas: gesture and sign language understanding , pose and action recognition , and facial expression and emotion analysis . Each article provides novel insights into challenges such as data scarcity, multimodal integration, adversarial robustness, and cross-modal generative modeling . We summarize the main contributions of the included works and emphasize their role in advancing the field of human body language understanding. Finally, we discuss ongoing challenges and future opportunities in this rapidly evolving domain, particularly in the context of integrating human-centric AI systems into real-world applications.

Emotional analysis of operating room nurses in acute care hospitals in Japan: insights using ChatGPT

AimThis study aimed to explore the emotions of operating room nurses in Japan towards perioperative nursing using generative AI and human analysis, and to identify factors contributing to burnout and turnover.MethodsA single-center cross-sectional study was conducted from February 2023 to February 2024, involving semi-structured interviews with 10 operating room nurses from a national hospital in Japan. Interview transcripts were analyzed using generative AI (ChatGPT-4o) and human researchers for thematic, emotional, and subjectivity analysis. A comparison between AI and human analysis was performed, and data visualization techniques, including keyword co-occurrence networks and cluster analysis, were employed to identify patterns and relationships.ResultsKey themes such as patient care, surgical safety, and nursing skills were identified through thematic analysis. Emotional analysis revealed a range of tones, with AI providing an efficient overview and human researchers capturing nuanced emotional insights. High subjectivity scores indicated deeply personal reflections. Keyword co-occurrence networks and cluster analysis highlighted connections between themes and distinct emotional experiences.ConclusionsCombining generative AI with human expertise offered nuanced insights into the emotions of operating room nurses. The findings emphasize the importance of emotional support, effective communication, and safety protocols in improving nurse well-being and job satisfaction. This hybrid approach can help address emotional challenges, reduce burnout, and enhance retention rates. Future research with larger and more diverse samples is needed to validate these findings and explore the broader applications of AI in healthcare.

Emotional Analysis of Tourism Reviews Based on Long Short-Term Memory and Fuzzy Control Algorithm

Emotional Analysis of Tourism Reviews Based on Long Short-Term Memory and Fuzzy Control Algorithm

Investigation of the effects of YouTube videos about orthognathic surgery on people using machine learning-based emotion analysis algorithm

Objectives: This study aims to analyze the comments about orthognathic surgery-themed YouTube videos through artificial intelligence and remarking the emotional effects of videos on people. Material and Methods: In this study, the keyword “orthognathic surgery” was searched on YouTube. In pursuit of recording sub-video comments, comments were analyzed with a machine learning-based emotion analysis algorithm. Results: One thousand one hundred and forty-five comments were analyzed in the study. 2 of 4 surgery videos contain real surgery images. Two videos are animated videos about the details of the surgery. Emotions described in comments are sorted as fear (43.7%), joy (21%), anger (14.6%), and sadness (11.6%). Where comments are reviewed in the aspect of sentiment, negative comments were dense (59.3%), respectively, followed by positive (18.3%), very negative (10.6%), and very positive (2.7 %). Regarding sentiment, differences in comments on real and animation surgery videos are statistically significant (P < 0.05). A significance level of very negative comments was higher in real surgery videos (P = 0.015). Conclusion: Different video formats, animation or real videos, may be used for informing, but we think that watching real surgical operation videos may increase people’s preoperative anxiety.

An integrated framework for emotion and sentiment analysis in Tamil and Malayalam visual content

An integrated framework for emotion and sentiment analysis in Tamil and Malayalam visual content

Facial emotion recognition based on upper features and transfer learning

Facial expression recognition (FER) in the upper face focuses on the analysis and recognition of emotions based on features extracted from the upper region of the face. This region typically affects the eyes, eyebrows, forehead, and sometimes the upper cheeks. Since these areas are often less affected by face masks or other facial coverings, FER algorithms can concentrate on capturing and interpreting the relevant facial cues, such as eye movements, eyebrow positions, and forehead wrinkles, to accurately recognize and classify different emotions. By focusing on the upper face, FER systems can mitigate the impact of occlusions caused by masks and still provide meaningful insights into the emotional states of individuals. In this work, a FER approach focusing on the upper region is proposed. Several experiments have been made using the CK+ dataset in addition to a comparison between the emotion recognition scores using the upper and the entire face in order to determine whether this area can reflect the real expressed emotion. The results of our approach are promising compared to previous studies with an accuracy up to 96%.

Birds of a feather? Mis- and dis-information on the social media platform X related to avian influenza.

Social media has become an important tool in monitoring infectious disease outbreaks such as coronavirus disease 2019 and highly pathogenic avian influenza (HPAI). Influenced by the recent announcement of a possible human death from H5N2 avian influenza, we analyzed tweets collected from X (formerly Twitter) to describe the messaging regarding the HPAI outbreak, including mis- and dis-information, concerns, and health education. We collected tweets involving keywords relating to HPAI for 5 days (June 04 to June 08, 2024). Using topic modeling, emotion, sentiment, and user demographic analyses, we were able to describe the population and the HPAI-related topics that users discussed. With an original pool of 14,796 tweets, we analyzed a final data set of 13,319 tweets from 10,421 unique X users, with 50.4% of the tweets exhibiting negative sentiments (< 0 on a scale of -4 to +4). Predominant emotions were anger and fear shown in 36.4% and 29.5% of tweets, respectively. We identified 5 distinct, descriptive topics within the tweets. The use of emotionally charged language and spread of misinformation were substantial. Mis- and dis-information about the causes of and ways to prevent HPAI infections were common. A large portion of the tweets contained references to a planned epidemic or "plandemic" to influence the upcoming 2024 US presidential election. These tweets were countered by a limited number of tweets discussing infection locations, case reports, and preventive measures. Our study can be used by public health officials and clinicians to influence the discourse on current and future outbreaks.

MMTF-DES: A fusion of multimodal transformer models for desire, emotion, and sentiment analysis of social media data

MMTF-DES: A fusion of multimodal transformer models for desire, emotion, and sentiment analysis of social media data

Evaluating Inclusivity and Fairness of AI Recruitment Tools for Hiring People with Disabilities in the United Arab Emirates(UAE)

IntroductionThis research aims to explore the effectiveness and inclusivity of AI-powered recruitment tools in hiring people with disabilities within the United Arab Emirates. Such is the situation where AI integration into the arena of recruitment is increasingly rapid, while there are vital issues on the side of bias, accessibility, and fairness for applicants of diverse needs. MethodsThis study was a mixed-methods approach, examining sentiment analysis, emotion detection, and HR analytics of feedback from applicants with a disability, 415 in total. The research focused on scores referring to sentiment, the progression rate, and the outcome of the final hiring. ResultsThe sentiment score varied significantly across disability types (p-value &lt;0.05). The applicants with cognitive disability expressed the highest sentiment sore while applicants with hearing impairment had the lowest, which indicated the varying adaptability of AI. The emotion analysis depicted a mix of positive and negative emotions. A few applicants liked technology and have trust in it, while others report fear. Clearly, the applicants, both disabled and non-disabled did not differ in their rate of progression (p-value &gt;0.05), hence never indicating any significant difference within the initial steps of the process. The final hiring stage showed significant differences in results with (p-value &lt;0.05), where the proportionate number of disabled applicants was recorded to be lower than that of non-disabled applicants

Emotion analysis techniques and development directions in social networks

Emotion analysis techniques and development directions in social networks

Time Facial Expression Recognition Using Optimized CNN Models for Behavioral and Emotional Analysis

Time Facial Expression Recognition Using Optimized CNN Models for Behavioral and Emotional Analysis

Navigating #StopAsianHate Upon Atlanta Shooting Incident: Focused on Emotion and Sentiment Analysis on Twitter (X)

Navigating #StopAsianHate Upon Atlanta Shooting Incident: Focused on Emotion and Sentiment Analysis on Twitter (X)

Student Emotion Analysis by Integrating Attention Mechanism Algorithm and Neural Network Algorithm

Student Emotion Analysis by Integrating Attention Mechanism Algorithm and Neural Network Algorithm

Sentiment Analysis in Arabic Text and Emoji Using Deep Learning Methods

The advent of social media has simplified the rapid publishing of explanations on inclusive announcements, movies, politics, and the economy. This growth has led to an increase in the breadth of topics covered. This emotion analysis includes many aspects. Arabic and OMCD survey big data were integrated with data from Twitter to inform this study. Different word embedding methods were implemented, such as Spacy (W2V), FastText, and Arabic Bidirectional Encoder Representation (AraBERT). In the context of sentiment analysis models, convolutional neural network (CNN), long short-term memory (LSTM), and recurrent neural network (RNN) were employed. The evaluation of model performance was based on accuracy. Deep learning (DL) methods using the AST (Arabic sentiment Twitter) dataset yielded 72% and 95% model accuracy rates. The accuracy rates for the OMCD (Offensive Moroccan Comments Dataset) is a dataset containing offensive comments in the Moroccan dialect. dataset fell within the range of 54% to 84%.

Using Simple Algorithms for Social Media Sentiment Analysis: Analyzing User Emotions on Social Platforms

Under the background of the vigorous development of social media, it is very important for business decision-making and social governance to accurately capture and analyze users' emotions. This article aims to explore a simple and effective way to analyze users' emotions on social media by using the basic NLP (Natural Language Processing) technology, especially the word frequency statistics method. Taking Weibo as the data source, this article constructs an emotional analysis model. By collecting data, preprocessing, constructing an emotion dictionary and calculating the emotion score, the model realizes the emotion tendency recognition of Weibo's posts. The experimental results show that the model can accurately identify the dominant emotional tendency in Weibo's posts, and perform well in capturing emotional trends. The research in this article not only provides a feasible solution for the emotional analysis of social media, but also provides reference for the follow-up research.

Sentiment analysis versus aspect-based sentiment analysis versus emotion analysis from text: a comparative study

Sentiment analysis versus aspect-based sentiment analysis versus emotion analysis from text: a comparative study