User Emotions Research Articles

Assessing the Impact of Social Media Use on Everyday Emotion in Health Crises: A Study of International Students in China during COVID-19.

Social media has become a valuable tool in providing an opportunity to stay in touch with one’s social networks, providing reassurance and practical advice to individuals to pre-empt panic and rumors in COVID-19. However, the implications of social media use on the everyday emotion (anxiety and depression) of users especially, international students, are not well understood. Thus, this study sought to examine the impact of social media use on the everyday emotion of international students in China during COVID-19. Using a structured online questionnaire based on modified questions from the generalized anxiety disorder 7 (GAD-7) and the Patient Health Questionnaire 9 (PHQ-9) and social media use instruments, data were collected from 480 participants. Of the total responses received, 474 were further analyzed employing the Partial Least Squares Path Modelling (PLS-PM). This study showed a significant positive relationship between social media use and everyday emotion (B = 0.34, 95% CI (0.26, 0.44)). Additionally, self-rated anxiety and depression associated with social media use among international students were generally mild (n = 249, 52.50% and n = 350, 73.80%, respectively). Moderating effects revealed that age and sex do not significantly moderate the relationship between social media use and everyday emotion in COVID-19. Given the nature of social media among international students, who are also prone to suffering from anxiety and depression associated with social media use, the positive effect of social media use and everyday emotion, especially in COVID-19, has important implications for international students’ education stakeholders. Thus, gaining a deeper understanding of this relationship could enable them to harness social media and use it as a valuable tool to overcome the social distancing constraints in COVID-19.

Sequential Emotion-Aware Recommendation: A Preliminary Study on Data Acquisition and Modeling

The rapid development of recommender systems makes researchers pay more and more attention to the utilization of users’ subjective factors. Among various subjective factors, emotion plays an important role that can truly reflect the temporal changes of users’ preferences. However, the acquisition of user emotion is difficult, and is obtained passively in many methods. Moreover, there are few datasets suitable for continuous emotion modeling in existing recommendation research. To address these shortcomings, this work collects and organizes a dataset of users watching movies containing their temporal emotional data, which is appropriate for recommendation tasks based on sequential emotions. In addition, we propose a sequential emotion-aware recommendation method suitable for continuous emotion modeling, which outperforms other advanced sequential modeling approaches on our dataset. The contribution of this work is to conduct preliminary study and exploration on the modeling of users’ sequential emotion, so that this research direction can be further developed in future. The Sequential EMotion-Aware Recommendation (SEMAR) dataset we collected is available at: https://github.com/LinZheng666/Sequential-Emotion-Dataset-for-Recommendation.

Analyzing User Digital Emotions from a Holy versus Non-Pilgrimage City in Saudi Arabia on Twitter Platform

Humans are the product of what society and their environment conditions them into being. People living in metropolitan cities have a very fast-paced life and are constantly exposed to different situations. A social media platform enables individuals to express their emotions and sentiments and thus acts as a reservoir for the digital emotion footprints of its users. This study proposes that the user data available on Twitter has the potential to showcase the contrasting emotions of people residing in a pilgrimage city versus those residing in other, non-pilgrimage areas. We collected the Arabic geolocated tweets of users living in Mecca (holy city) and Riyadh (non-pilgrimage city). The user emotions were classified on the basis of Plutchik’s eight basic emotion categories, Fear, Anger, Sadness, Joy, Surprise, Disgust, Trust, and Anticipation. A new bilingual dictionary, AEELex (Arabic English Emotion Lexicon), was designed to determine emotions derived from user tweets. AEELex has been validated on commonly known and popular lexicons. An emotion analysis revealed that people living in Mecca had more positivity than those residing in Riyadh. Anticipation was the emotion that was dominant or most expressed in both places. However, a larger proportion of users living in Mecca fell under this category. The proposed analysis was an initial attempt toward studying the emotional and behavioral differences between users living in different cities of Saudi Arabia. This study has several other important applications. First, the emotion-based study could contribute to the development of a machine learning-based model for predicting depression in netizens. Second, behavioral appearances mined from the text could benefit efforts to identify the regional location of a particular user.

Way of application of convolutional neural networks for personality recognition and user emotions by keyboard handwriting

An important direction of increasing the security and expanding the functionality of modern information systems is the introduction of face recognition tools and user emotions by their keyboard handwriting. The expediency of improving the indicated recognition means by introducing modern neural network solutions into them is shown. A way has been developed for using a convolutional neural network for recognizing a user's face and emotions from keyboard handwriting, the features of which are the procedure for adapting the structural parameters of a convolutional neural network of the VGG type to the expected conditions of use and a procedure for determining the input field, which provides the representation of the parameters of colored channels. After adapting the structural parameters, the VGG network was implemented using the MATLAB R2018b application package, which made it possible to carry out computer experiments aimed at verifying the proposed method. As a result of the conducted computer experiments, it was determined that the use of the proposed method of applying a convolutional neural network makes it possible to achieve a user face recognition accuracy of about 82% with 50 learning epochs. The need for further research in the direction of the formation of a training sample is shown, which will ensure high-quality training of the neural network model.

IMPACT OF FLOODING ON AIRPORTS USING REMOTE SENSING AND GIS TECHNIQUES

Floods are considered one of the worst weather-related natural disasters. They are sudden and highly unexpected following brief period of heavy rain. Egypt is subjected to flash floods, their impact vast areas causing serious damages with thousands of human injuries, economic losses and heavy damage to man-made features. According to the importance and criticality of severe rains that may lead to floods that make us thinking about making flood management to avoid risks resulting from it. Flood management is an approach that is virtually unknown in Egypt and has not been widely discussed despite the growing problem of widespread flood damage in recent years. This study aims to evaluate the comprehensive of flash flooding occurrences, impacts, and possible mitigation on the Airports. In this study, Alexandria (Borg El-Arab district) was selected for flash flooding vulnerability assessment, because it is a coastal city and exposed to heavy rains for long periods causing floods, especially Borg El-Arab international airport, it’s about 49 km away from Alexandria city in the southwestern direction, and it is 14 km away from the new city of Borg El Arab in the eastern direction. It was established to relieve Alexandria International Airport, the area of ​​the airport is about 43,669 square meters, the airport served about 189,064 passengers and this number is expected to rise especially after the opening of the new terminal, Runway and other buildings in the airport. Using digital elevation model (DEM) implemented into a Geographic Information System (GIS), the climate maps and metalogical data of this study can help initiating appropriate measures to mitigate the probable hazards in the area. During this research review the impact of floods, how they predict their occurrence to the Disaster Risk Reduction and avoid of danger impacts on vital areas in cities through surveying techniques. how to protect the assets and infrastructure of the airport by predicting the crisis appropriate to mitigate the probable hazards in the airport. يعتبر النقل الجوي من أفضل وسائل السفر ولکن أصبح غير موثوق به بسبب عوامل کثيرة , تم اختيار الإسکندرية لتقييم مدى تعرضها للفيضانات ، لأنها مدينة ساحلية ومعرضة للأمطار الغزيرة. تم استخدام نظم المعلومات الجغرافية (GIS) وعمل التحليلات لتقييم مخاطر الفيضانات وتم عمل نمذجة للفيضانات من خلال الاستشعار عن بعد ، و بيانات الأرصاد الجوية التى تساعد على إنشاء نظام إنذار مبکر وتهدف الدراسة إلى التنبؤ بحدوث الفيضانات و التحکم في المخاطر الناتجة عنها باستخدام تقنية تحليل متعددة المعايير من خلال دراسة الخرائط المناخية و عمل أنظمة حماية و تجميع لمياه الامطار بحيث لا تؤثر على البنية التحتية في المطار. وقد تم عمل دراسة شاملة للفيضانات في مطار برج العرب وتوفير نظام محاکاة ديناميکي لتحديد أماکن ومستويات السيول , القضاء على التعديات و إزالة العوائق في الوديان وعمل حملات توعية عن مخاطر السيول وکيفية التعامل معها .

Cross-Cultural and Cultural-Specific Production and Perception of Facial Expressions of Emotion in the Wild

Automatic recognition of emotion from facial expressions is an intense area of research, with a potentially long list of important application. Yet, the study of emotion requires knowing which facial expressions are used within and across cultures in the wild, not in controlled lab conditions; but such studies do not exist. Which and how many cross-cultural and cultural-specific facial expressions do people commonly use? And, what affect variables does each expression communicate to observers? If we are to design technology that understands the emotion of users, we need answers to these two fundamental questions. In this paper, we present the first large-scale study of the production and visual perception of facial expressions of emotion in the wild. We find that of the 16,384 possible facial configurations that people can theoretically produce, only 35 are successfully used to transmit emotive information across cultures, and only 8 within a smaller number of cultures. Crucially, we find that visual analysis of cross-cultural expressions yields consistent perception of emotion categories and valence, but not arousal. In contrast, visual analysis of cultural-specific expressions yields consistent perception of valence and arousal, but not of emotion categories. Additionally, we find that the number of expressions used to communicate each emotion is also different, e.g., 17 expressions transmit happiness, but only 1 is used to convey disgust.

Emotion Recognizing Virtual Assistant

Virtual Assistants are the most effective product of AI which makes people’s life easier. They are used in many machines. With AI many other technologies are also born like emotion recognition. This paper presents the AI with the feature of emotion recognition. This AI will complete the task by considering the emotion of user. As so as it takes the command it will analyze the task but before it perform it will recognize the emotion of user and then according to it, it will proceed for task completion. We have used Python language with machine learning algorithm. It is very effective to detect the emotions and avoid any problems. It will provide closer interaction with user like friend.

Audio-visual Emotion Regulation System Based on TGAM Module

Based on the TGAM PCB module, a system of emotion control using audio-visual feedback is designed. TGAM collects EEG information through the electrode in contact with the forehead skin. The system analyzes the user's emotion through the STM32F103ZET6 of the main control chip, and finally controls the control end of the system to regulate the user's emotion. It can be seen from the test results that the system can precisely recognize the user's emotions, and at the same time effectively adjust the user's emotions from both audio-visual aspects. The system has high recognition accuracy and good adjustment effect.

Approach or avoid? The dualistic effects of envy on social media users’ behavioral intention

People express themselves through posts or selfies with brands and activities on social networking sites (SNSs) such as Facebook and Instagram. This user-generated content provides adequate social information that may elicit the emotions of users who are exposed to such content on these online platforms. Although academic researchers have focused on factors affecting users’ emotions on SNSs, how users reconcile both positive and negative emotions to their attitude and behavior in triadic interactions remains unclear. The current study attempted to answer this research question through the lens of social comparison theory by investigating the effects of tie strength and focus of attention as two forces eliciting online social comparisons on emotional consequences measured through pleasure and envy. Moreover, the dualistic effects of the two distinct types of envy, namely benign and malicious, and the effect of pleasure on users’ approach and avoidance behavior were explored and hypothesized. The results indicated that strong ties triggered more benign envy compared with malicious envy. Furthermore, benign envy positively affected brand attitude and SNS avoidance in terms of exhaustion, whereas malicious envy negatively influenced brand attitude and increased the likelihood of SNS avoidance in terms of both exhaustion and discontinuance.

Why Does Explainability Matter in News Analytic Systems? Proposing Explainable Analytic Journalism

ABSTRACT As the use of algorithms has emerged in journalism, analytic/algorithmic journalism (AJ) has seen rapid development in major news organizations. Despite this surging trend, little is known about the role and the effects of explainability on the process by which people perceive and make sense of trust in an algorithm-driven AI system. While AJ has greatly benefited from increasingly sophisticated algorithm technologies, AJ suffers from a lack of transparency and understandability for readers. We identify explainability as a heuristic cue of an algorithm and conceptualizes it in relation to trust by testing how it affects user emotion with AJ. Our experiments show that the addition of interpretable explanations leads to enhanced trust in the context of AJ and readers' trust hinges upon the perceived normative values that are used to assess algorithmic qualities. Explanations of why certain news articles are recommended give users emotional assurance and affirmation. Mediation analyses show that explanatory cues play a mediating role between trust and performance expectancy. The results have implications for the inclusion of explanatory cues in AJ, which help to increase credibility and help users to assess AJ value.

Assembly Assistance System with Decision Trees and Ensemble Learning.

This paper presents different prediction methods based on decision tree and ensemble learning to suggest possible next assembly steps. The predictor is designed to be a component of a sensor-based assembly assistance system whose goal is to provide support via adaptive instructions, considering the assembly progress and, in the future, the estimation of user emotions during training. The assembly assistance station supports inexperienced manufacturing workers, but it can be useful in assisting experienced workers, too. The proposed predictors are evaluated on the data collected in experiments involving both trainees and manufacturing workers, as well as on a mixed dataset, and are compared with other existing predictors. The novelty of the paper is the decision tree-based prediction of the assembly states, in contrast with the previous algorithms which are stochastic-based or neural. The results show that ensemble learning with decision tree components is best suited for adaptive assembly support systems.

IoTouch: whole-body tactile sensing technology toward the tele-touch

In the era of social distancing, humans tend to interact more with digital edges/devices and robotic avatar. Users mostly interact with cyber-physical systems through audiovisual devices, while tangible interfaces are limited to touch panels. Touch perception not only brings sense of physical contact, texture; but also conveys the intention and emotion of users. Here, we introduce a novel soft tangible device, called IoTouch, as a combination of soft robotics and deep learning, that can act as both robotic skin or haptic sensing interface. The technique aims to implementation of touch sensing with a vision-based approach. We showcase on barrel shape (ellipsoid with two flattened ends) of the IoTouch, where a dataset of tactile images was collected through an autonomous process, in order to train a network for recognition of physical contact states (contact location, contact depth). A Finite Element Method model of the barrel skin was also setup for data acquisition of skin's deformation. The proposed method can detect multiple contacts simultaneously on the entire area of the barrel skin. Obtained result promises a platform for creation of robotic avatars that can sense diverse states of physical touch, through which the users' experience and communication of haptics can be enhanced.

A novel LSTM–CNN–grid search-based deep neural network for sentiment analysis

As the number of users getting acquainted with the Internet is escalating rapidly, there is more user-generated content on the web. Comprehending hidden opinions, sentiments, and emotions in emails, tweets, reviews, and comments is a challenge and equally crucial for social media monitoring, brand monitoring, customer services, and market research. Sentiment analysis determines the emotional tone behind a series of words may essentially be used to understand the attitude, opinions, and emotions of users. We propose a novel long short-term memory (LSTM)–convolutional neural networks (CNN)–grid search-based deep neural network model for sentiment analysis. The study considers baseline algorithms like convolutional neural networks, K-nearest neighbor, LSTM, neural networks, LSTM–CNN, and CNN–LSTM which have been evaluated using accuracy, precision, sensitivity, specificity, and F-1 score, on multiple datasets. Our results show that the proposed model based on hyperparameter optimization outperforms other baseline models with an overall accuracy greater than 96%.

Emotion Based Smart Music Player

Every individual human might have completely different faces; however, their expressions tell us the same story and it notably plays a significant role in extraction of an individual’s emotions and behavior. Music is the purest form of art and a medium of expression, which is known to have a greater connection with a person’s emotions. It has a novel ability to lift one’s mood. This project system focuses on building an efficient music player which works on emotion of user using facial recognition techniques. The facial features extracted will generate a system thereby reducing the effort and time involved in doing it manually. Facial data is captured by employing a camera. The emotion module makes use of deep learning techniques to spot the exact mood relative to that expression. The accuracy of mood detection module in the system for real time footage is above 80%; while for static pictures it is 95 to one hundred percent. Therefore, it brings out higher accuracy relating to time and performance.

Measuring sentiments and attitude of people toward self-drive rental car services in Bangalore City, India

ABSTRACT This paper explores the emotions of self-drive rental car users in India on social-media platform using sentiment analysis and estimates the relationship between socio-demographic factors and factors influencing the decision of renting a car. An ordered logit model is used to determine the factors which are affecting individuals’ demographic characteristics to rent from a self-drive rental car service. A total of six models are computed for each of the influencing factors. The results suggest that there is a positive image of self-drive rental car service as perceived from social media platform and in the 18-25 years age group. Private employees are significantly affected by quality of car and ease to hire facility offered by this service. It is also estimated that time flexibility is the most influencing factor considered while renting a car. The outcomes of this study may aid these service providers in strategic planning and policy framework.

Predicting Election Results from Twitter Using Machine Learning Algorithms

Introduction: In the present scenario, the social media network plays a significant role in sharing information between individuals. This incorporates information about news and events that are presently occurring in the worldwide. Anticipating election results is presently turning into a fascinating research topic through social media. In this article, we proposed a strategy to anticipate election results by consolidating sub-event discovery and sentimental analysis in micro-blogs to break down as well as imagine political inclinations uncovered by those social media users. Methods: This approach discovers and investigates sentimental data from micro-blogs to anticipate the popularity of contestants. In general, many organizations and media houses conduct a pre-poll review and obtain expert’s perspectives to anticipate the result of the election, but for our model, we use Twitter data to predict the result of an election by gathering information from Twitter and evaluate it to anticipate the result of the election by analyzing the sentiment of twitter information about the contestants. Results: The number of seats won by the first, second, and third party in AP Assembly Election 2019 has been determined by utilizing Positive Sentiment Scores (PSS’s) of the parties. The actual results of the election and our predicted values of the proposed model are compared, and the outcomes are very close to actual results. We utilized machine learning-based sentimental analysis to discover user emotions in tweets, anticipate sentiment score, and then convert this sentiment score to parties' seat score. Comprehensive experiments are conducted to check out the performance of our model based on a Twitter dataset. Conclusions: Our outcomes state that the proposed model can precisely forecast the election results with accuracy (94.2 %) over the given baselines. The experimental outcomes are very closer to actual election results and contrasted with conventional strategies utilized by various survey agencies for exit polls and approval of results demonstrated that social media data can foresee with better exactness. Discussion: In the future, we might want to expand this work into different areas and nations of the reality where Twitter is picking up prevalence as a political battling tool, and where politicians and individuals are turning towards micro-blogs for political communication and data. We would likewise expand this research into various fields other than general elections and from politicians to state organizations.

Emotion detection on Myanmar texts

At this age, World Wide Web is growing faster. Many companies have built and launch social media networks. People so widely use social media to get the latest news, to express their emotions or moods, to communicate with their friends and so on. Emotions of social media users are needed to analyze in order to apply in many areas. Many researchers do research on emotion detection using different techniques with their languages. Currently, there are no emotion detection systems for Myanmar (Burmese) language. So, this paper describes the emotion detection system for Myanmar language. This system uses our pre-constructed M-Lexicon, a Myanmar word-emotion lexicon, in the detection process. This system detects six basic emotions such as happiness, sadness, anger, fear, surprise, and disgust. In order to determine certain emotion from the text, we also apply rule-based decision making on sentence nature. We use Facebook users’ status, which has been written in Myanmar words. Emotions of user groups are also summarized in this system. Our approach achieves 86% accuracy for emotion detection in Myanmar texts.

USER EXPECTATIONS ON SMART TV; AN EMPIRIC STUDY ON USER EMOTIONS TOWARDS SMART TV

As a result of the introduction of new technologies in consumer electronics, analog TV shifted from a mere viewing experience to a personalized digital TV experience where users are encouraged to interact. The application of these new technologies not only create changes in physical appearance and adding more functionalities to TVs but it also shifts user expectations, which are mainly emotionally driven. The initial attempt of this study is to determine which emotions are involved in smart TV preference and why those particular emotions are aroused. In other words, this study aims to discover the link among contents, activities and user interaction as well as the relationship between triggered emotions and user expectations. By doing so, it analyses user emotions and expectations towards a dream TV. The primary data is collected towards semi-structured in-depth interviews. The results show that Smartness, High quality, Personalization, Functionality and Appearance are the key features that meet the expectations towards TV experience. User-friendliness, compatibleness, enjoyableness, awareness, novel-interactions, self-defense smart software and voice remote are the consequent expectations. All these expectations arise from different underlying emotional tendencies. With its initial attempt to propose guidelines for designers, this study suggests that for designing a smart TV that meets user expectations, its design should enable smart interaction that simplifies managing task (Smartness), high quality of picture and sound to enable innovative continuous experience (High quality), supporting not missing any content of interest and filter unwanted ones (Personalization), utilize all kinds of usage comfortably (Functionality), and should have an aesthetic look, even seamless design that fits any possible environment (Appearance).

Research on the Design of Virtual Experiment Platform of Product Appearance Structure Based on Emotion Measurement

This paper mainly studied the influence of the design of virtual experiment platform on the users' emotional state and learning achievements, and explored the relationship between the three. The routine methods of emotion elicitation and measurement were studied. The emotion of users was elicited by different interaction design and visual design, and the emotion state of users was measured by SAM. Through the experiment, we got the conclusion that the design change will affect the emotion, and the emotion valence and the learning achievement are positively related, and provide the theoretical basis for the subsequent platform design.

Modeling of Recommendation System Based on Emotional Information and Collaborative Filtering.

Emotion information represents a user’s current emotional state and can be used in a variety of applications, such as cultural content services that recommend music according to user emotional states and user emotion monitoring. To increase user satisfaction, recommendation methods must understand and reflect user characteristics and circumstances, such as individual preferences and emotions. However, most recommendation methods do not reflect such characteristics accurately and are unable to increase user satisfaction. In this paper, six human emotions (neutral, happy, sad, angry, surprised, and bored) are broadly defined to consider user speech emotion information and recommend matching content. The “genetic algorithms as a feature selection method” (GAFS) algorithm was used to classify normalized speech according to speech emotion information. We used a support vector machine (SVM) algorithm and selected an optimal kernel function for recognizing the six target emotions. Performance evaluation results for each kernel function revealed that the radial basis function (RBF) kernel function yielded the highest emotion recognition accuracy of 86.98%. Additionally, content data (images and music) were classified based on emotion information using factor analysis, correspondence analysis, and Euclidean distance. Finally, speech information that was classified based on emotions and emotion information that was recognized through a collaborative filtering technique were used to predict user emotional preferences and recommend content that matched user emotions in a mobile application.