A Cross-Corpus Deep Learning Approach to Social Media Emotion Classification

Emotion Detection refers to the identification of emotions from contextual data in the form of written text, such as comments, posts, reviews, publications, articles, recommendations, conversations, and so on. Because of the Internet's exponential uptake and the recent coronavirus outbreak, social media platforms have become a crucial means of sharing thoughts and ideas throughout the entire globe, creating rapid data growth through users' contributions on various platforms. The necessity to acquire knowledge of their behaviors is a matter of great concern for both internet safety and privacy. In this study, we categorize emotional sentiments using deep learning models along with hybrid approaches such as LSTM, Bi-LSTM, and CNN+LSTM. When compared to existing state-of-the-art methods, the experiments showed that the suggested strategy is more robust and achieves an expressively higher quality of emotion detection with an accuracy rate of 94.16%, including strong F1-scores on complex and difficult emotion categories such as Fear (93.85%) and Anger (94.66%) through CNN+LSTM. © 2022 IEEE.

Comparing Deep and Machine Learning Models for Sentiment and Emotion Classification from Vaccine #sideffects

The accelerated development of Covid-19 vaccines offered tremendous promise and hope, yet stirred significant trepidation and fear. These conflicting emotions motivated many to turn to social media to share their experiences and side effects during the process of getting vaccinated. This paper analyzes sentiment and emotions from tweets collected using the hashtag #sideffects during the early roll out of the Covid-19 vaccine. Each tweet was labeled according to its sentiment polarity (positive vs. negative), and was assigned one of four emotion labels (joy, gratitude, apprehension, and sadness). Exploratory analysis of the tweets through word cloud visualizations revealed that the negativity of emotions intensified with the severity of side effects. Word and numerical features extracted from the text of the tweets and metadata were used to train conventional machine learning and deep learning models. These models resulted in an accuracy of 81% for binary sentiment classification, and 71 % for multi-label emotion identification. The proposed framework, which yielded competitive performance, may be employed to gain insights into people's thoughts and feelings from vaccine-related conversations. These insights can be helpful in devising communication and education strategies to mitigate vaccine hesitancy. © 2022 IEEE.

Valence-arousal classification of emotion evoked by Chinese ancient-style music using 1D-CNN-BiLSTM model on EEG signals for college students.

During the COVID-19 pandemic, young people are using multimedia content more frequently to communicate with each other on Internet platforms. Among them, music, as psychological support for a lonely life in this special period, is a powerful tool for emotional self-regulation and getting rid of loneliness. More and more attention has been paid to the music recommender system based on emotion. In recent years, Chinese music has tended to be considered an independent genre. Chinese ancient-style music is one of the new folk music styles in Chinese music and is becoming more and more popular among young people. The complexity of Chinese-style music brings significant challenges to the quantitative calculation of music. To effectively solve the problem of emotion classification in music information search, emotion is often characterized by valence and arousal. This paper focuses on the valence and arousal classification of Chinese ancient-style music-evoked emotion. It proposes a hybrid one-dimensional convolutional neural network and bidirectional and unidirectional long short-term memory model (1D-CNN-BiLSTM). And a self-acquisition EEG dataset for Chinese college students was designed to classify music-induced emotion by valence-arousal based on EEG. In addition to that, the proposed 1D-CNN-BILSTM model verified the performance of public datasets DEAP and DREAMER, as well as the self-acquisition dataset DESC. The experimental results show that, compared with traditional LSTM and 1D-CNN-LSTM models, the proposed method has the highest accuracy in the valence classification task of music-induced emotion, reaching 94.85%, 98.41%, and 99.27%, respectively. The accuracy of the arousal classification task also gained 93.40%, 98.23%, and 99.20%, respectively. In addition, compared with the positive valence classification results of emotion, this method has obvious advantages in negative valence classification. This study provides a computational classification model for a music recommender system with emotion. It also provides some theoretical support for the brain-computer interactive (BCI) application products of Chinese ancient-style music which is popular among young people.

Multi-label Emotion Classification of COVID-19 Tweets with Deep Learning and Topic Modelling

The COVID-19 pandemic has become one of the severe diseases in recent years. As it majorly affects the common livelihood of people across the universe, it is essential for administrators and healthcare professionals to be aware of the views of the community so as to monitor the severity of the spread of the outbreak. The public opinions are been shared enormously in microblogging media like twitter and is considered as one of the popular sources to collect public opinions in any topic like politics, sports, entertainment etc., This work presents a combination of Intensity Based Emotion Classification Convolution Neural Network (IBEC-CNN) model and Non-negative Matrix Factorization (NMF) for detecting and analyzing the different topics discussed in the COVID-19 tweets as well the intensity of the emotional content of those tweets. The topics were identified using NMF and the emotions are classified using pretrained IBEC-CNN, based on predefined intensity scores. The research aimed at identifying the emotions in the Indian tweets related to COVID-19 and producing a list of topics discussed by the users during the COVID-19 pandemic. Using the Twitter Application Programming Interface (Twitter API), huge numbers of COVID-19 tweets are retrieved during January and July 2020. The extracted tweets are analyzed for emotions fear, joy, sadness and trust with proposed Intensity Based Emotion Classification Convolution Neural Network (IBEC-CNN) model which is pretrained. The classified tweets are given an intensity score varies from 1 to 3, with 1 being low intensity for the emotion, 2 being the moderate and 3 being the high intensity. To identify the topics in the tweets and the themes of those topics, Non-negative Matrix Factorization (NMF) has been employed. Analysis of emotions of COVID-19 tweets has identified, that the count of positive tweets is more than that of count of negative tweets during the period considered and the negative tweets related to COVID-19 is less than 5%. Also, more than 75% negative tweets expressed sadness, fear are of low intensity. A qualitative analysis has also been conducted and the topics detected are grouped into themes such as economic impacts, case reports, treatments, entertainment and vaccination. The results of analysis show that the issues related to the pandemic are expressed different emotions in twitter which helps in interpreting the public insights during the pandemic and these results are beneficial for planning the dissemination of factual health statistics to build the trust of the people. The performance comparison shows that the proposed IBEC-CNN model outperforms the conventional models and achieved 83.71% accuracy. The % of COVID-19 tweets that discussed the different topics vary from 7.45% to 26.43% on topics economy, Statistics on cases, Government/Politics, Entertainment, Lockdown, Treatments and Virtual Events. The least number of tweets discussed on politics/government on the other hand the tweets discussed most about treatments. © 2023 CRL Publishing. All rights reserved.

Emotion classification through text with proposed hybrid learning emotion model

Natural language processing (NLP) and artificial intelligence (AI) are important to enrich human-computer communication. The NLP is widely applied in various domains such as e-commerce, health, social media sentiment, etc. There has been an increasing need to deliver classes online since the COVID-19 pandemic, and various efforts and tools have been explored to improve students' online studies. Students usually communicate with instructors and ask questions through text messages in online classes;Hence, NLP could be used to identify students' emotions to improve the online learning experience. The current emotion classification works focused on the seven (7) universal emotions: anger, contempt, disgust, enjoyment, fear, sadness, and surprise. There is a lack of studies specializing in learning emotion classification. This research proposes a hybrid learning emotion model to predict students' emotions through text messages. Emotions can affect the learner at different stages of the learning process. Understanding the student's emotions is important because it will impact their attention, motivation, and self-regulated learning ability. The proposed hybrid learning emotion model is designed to classify four types of learning emotions: engagement, confusion, boredom, and hopefulness. In this research, the text messages from the student were collected based on the proposed hybrid learning emotion models, and the multinomial Naïve Bayes approach was used to predict the learning emotion. © VDE VERLAG GMBH.

Emodynamics: Detecting and Characterizing Pandemic Sentiment Change Points on Danish Twitter

In this paper, we present the results of an initial experiment using emotion classifications as the basis for studying information dynamics in social media ('emodynamics'). To do this, we used Bert Emotion [18] to assign probability scores for eight different emotions to each text in a time series of 43 million Danish tweets from 2019-2022. We find that variance in the information signals novelty and resonance reliably identify seasonal shifts in posting behavior, particularly around the Christmas holiday season, whereas variance in the distribution of emotion scores corresponds to more local events such as major inflection points in the Covid-19 pandemic in Denmark. This work in progress suggests that emotion scores are a useful tool for diagnosing shifts in the baseline information state of social media platforms such as Twitter, and for understanding how social media systems respond to both predictable and unexpected external events. © 2022 Copyright for this paper by its authors.

RSCOEWR: Radical-Based Sentiment Classification of Online Education Website Reviews

Online education is becoming more and more popular with the development of the Internet. In particular, due to the COVID-19 pandemic, many countries around the world are increasing the popularity of online education, which makes the research on sentiment classification of course reviews of online education websites an important research direction in natural language processing tasks. Traditional sentiment classification models are mostly based on English. Unlike English, Chinese characters are based on pictograms. Radicals of Chinese characters can also express certain semantics, and characters with the same radical often have similar meanings. Therefore, RSCOEWR, a word-level and radical-level based sentiment classification model for course reviews of Chinese online education websites is proposed, which solves the problem of data sparsity of reviews by feature extraction of multiple dimensions. In addition, a deep learning model based on CNN, BILSTM, BIGRU and Attention is constructed to solve the problem of high dimension and assigning the same attention to context of traditional sentiment classification model. Extensive comparative experiment results show that RSCOEWR outperforms the state-of-the-art sentiment classification models, and the experimental results on public Chinese sentiment classification datasets prove the generalization ability of RSCOEWR.

A comparison of humans and machine learning classifiers categorizing emotion from faces with different coverings

Partial face coverings such as sunglasses and face masks unintentionally obscure facial expressions, causing a loss of accuracy when humans and computer systems attempt to categorise emotion. With the rise of soft computing techniques interacting with humans, it is important to know not just their accuracy, but also the confusion errors being made—do humans make less random/damaging errors than soft computing? We analyzed the impact of sunglasses and different face masks on the ability to categorize emotional facial expressions in humans and computer systems. Computer systems, represented by VGG19, ResNet50, and InceptionV3 deep learning algorithms, and humans assessed images of people with varying emotional facial expressions and with four different types of coverings, i.e. unmasked, with a mask covering the lower face, a partial mask with transparent mouth window, and with sunglasses. The first contribution of this work is that computer systems were found to be better classifiers (98.48%) than humans (82.72%) for faces without covering (>15% difference). This difference is due to the significantly lower accuracy in categorizing anger, disgust, and fear expressions by humans (p′s<.001). However, the most novel aspect of the work is identifying how soft computing systems make different mistakes to humans on the same data. Humans mainly confuse unclear expressions as neutral emotion, which minimizes affective effects. Conversely, soft techniques often confuse unclear expressions as other emotion categories, which could lead to opposing decisions being made, e.g. a robot categorizing a fearful user as happy. Importantly, the variation in the misclassification can be adjusted by variations in the balance of categories in the training set.

Building and Testing Fine-Grained Dataset of COVID-19 Tweets for Worry Prediction

The COVID-19 outbreak has resulted in the loss of human life worldwide and has increased worry concerning life, public health, the economy, and the future. With lockdown and social distancing measures in place, people turned to social media such as Twitter to share their feelings and concerns about the pandemic. Several studies have focused on analyzing Twitter users’ sentiments and emotions. However, little work has focused on worry detection at a fine-grained level due to the lack of adequate datasets. Worry emotion is associated with notions such as anxiety, fear, and nervousness. In this study, we built a dataset for worry emotion classification called “WorryCov”. It is a relatively large dataset derived from Twitter concerning worry about COVID-19. The data were annotated into three levels (“no-worry”, “worry”, and “high-worry”). Using the annotated dataset, we investigated the performance of different machine learning algorithms (ML), including multinomial Naïve Bayes (MNB), support vector machine (SVM), logistic regression (LR), and random forests (RF). The results show that LR was the optimal approach, with an accuracy of 75%. Furthermore, the results indicate that the proposed model could be used by psychologists and researchers to predict Twitter users’ worry levels during COVID-19 or similar crises. © 2022, International Journal of Advanced Computer Science and Applications. All Rights Reserved.

Sentimental Analysis on Online Education Using Machine Learning Models

Sentimental analysis is a simple natural language processing technique for classifying and identifying the sentiments and views represented in a source text. Corona pandemic has shifted the focus of education from traditional classrooms to online classes. Students’ mental and psychological states alter as a result of this transition. Sentimental study of the opinions of online education students can aid in understanding the students’ learning conditions. During the corona pandemic, only, students enrolled in online classes were surveyed. Only, students who are in college for pre-graduation, graduation, or post-graduation were used in this study. To grasp the pupils’ feelings, machine learning models were developed. Using the dataset, we were able to identify and visualize the students’ feelings. Students’ favorable, negative, and neutral opinions can be successfully classified using machine learning algorithms. The Naive Bayes method is the most accurate method identified. Logistic regression, support vector machine, decision tree, and random forest these algorithms also gave comparatively good accuracy. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Optimal Compact Network for Micro-Expression Analysis System.

Micro-expression analysis is the study of subtle and fleeting facial expressions that convey genuine human emotions. Since such expressions cannot be controlled, many believe that it is an excellent way to reveal a human's inner thoughts. Analyzing micro-expressions manually is a very time-consuming and complicated task, hence many researchers have incorporated deep learning techniques to produce a more efficient analysis system. However, the insufficient amount of micro-expression data has limited the network's ability to be fully optimized, as overfitting is likely to occur if a deeper network is utilized. In this paper, a complete deep learning-based micro-expression analysis system is introduced that covers the two main components of a general automated system: spotting and recognition, with also an additional element of synthetic data augmentation. For the spotting part, an optimized continuous labeling scheme is introduced to spot the apex frame in a video. Once the apex frames have been recognized, they are passed to the generative adversarial network to produce an additional set of augmented apex frames. Meanwhile, for the recognition part, a novel convolutional neural network, coined as Optimal Compact Network (OC-Net), is introduced for the purpose of emotion recognition. The proposed system achieved the best F1-score of 0.69 in categorizing the emotions with the highest accuracy of 79.14%. In addition, the generated synthetic data used in the training phase also contributed to performance improvement of at least 0.61% for all tested networks. Therefore, the proposed optimized and compact deep learning system is suitable for mobile-based micro-expression analysis to detect the genuine human emotions.

Merging Datasets for Emotion Analysis

Context. Applying sentiment analysis is in general a laborious task. Furthermore, if we add the task of getting a good quality dataset with balanced distribution and enough samples, the job becomes more complicated. Objective. We want to find out whether merging compatible datasets improves emotion analysis based on machine learning (ML) techniques, compared to the original, individual datasets. Method. We obtained two datasets with Covid-19-related tweets written in Spanish, and then built from them two new datasets combining the original ones with different consolidation of balance. We analyzed the results according to precision, recall, F1-score and accuracy. Results. The results obtained show that merging two datasets can improve the performance of ML models, particularly the F1-score, when the merging process follows a strategy that optimizes the balance of the resulting dataset. Conclusions. Merging two datasets can improve the performance of ML models for emotion analysis, whilst saving resources for labeling training data. This might be especially useful for several software engineering activities that leverage on ML-based emotion analysis techniques.

Application of Bayesian Network Reasoning Algorithm in Emotion Classification

In the early stage of covid-19 disease transmission, it is easy to lead to public panic and dissatisfaction without timely information feedback. In order to solve this problem, this paper constructs an emotion classification and prediction algorithm based on Bayesian network reasoning by analyzing the variable elimination algorithm, connection tree reasoning algorithm and Gibbs sampling algorithm in Bayesian network reasoning algorithm. The algorithm can quickly identify the emotions of Internet users from the communication with low computational resources, and provide reference for the relevant departments to formulate the correct public opinion guidance strategy. © 2021 IEEE.

Social sentiment analyzer for online post of the COVID-19 Pandemic based on Neural network

In order to explore the emotions of people during this pandemic by using the Baidu Post Bar, we propose a neural network to classify text based on emotions. The data for training the proposed model and performing experiments is obtained from various online forums. The results of the proposed model are compared with other models presented in literature. The experimental results show that the proposed CNN_BiLSTM model has good results in classifying the data samples and it satisfies the requirements of emotion classification of forum Chinese texts. The proposed method accurately classifies the emotion of each sentence and provides necessary technical support for subsequent emotion analysis. © 2022 IEEE.

Music Recommendation Systum Based on Emotion

With the onset of lockdown in the COVID-19 scenario, people were forced to confine themselves within the four walls of their rooms which in the meantime invited mood disorders like depression, anxiety etc. Music has proven to be a potential empathetic companion in this tough time for all. The proposed emotion-based music recommendation system uses aser emotion as an input to recommend songs that are-ascertained using faciai expression or using direct inputs from the user. The model uses a Random Forest classifier and XGBoost algorithm to identify the song's emotion considering various features like instruineiitainess, energy, acoustics, liveness, etc, and lyrical similarity among songs with the help of Term-Frequency times Inverse Document-Frequency (TF-IBF). The results of comprehensive experiments on reai data confirm the accuracy of the proposed emotion classification system that can be integrated into any recommendation engine. © 2021 IEEE.

Optimism and pessimism analysis using deep learning on COVID-19 related twitter conversations.

This paper proposes a new deep learning approach to better understand how optimistic and pessimistic feelings are conveyed in Twitter conversations about COVID-19. A pre-trained transformer embedding is used to extract the semantic features and several network architectures are compared. Model performance is evaluated on two new, publicly available Twitter corpora of crisis-related posts. The best performing pessimism and optimism detection models are based on bidirectional long- and short-term memory networks. Experimental results on four periods of the COVID-19 pandemic show how the proposed approach can model optimism and pessimism in the context of a health crisis. There is a total of 150,503 tweets and 51,319 unique users. Conversations are characterised in terms of emotional signals and shifts to unravel empathy and support mechanisms. Conversations with stronger pessimistic signals denoted little emotional shift (i.e. 62.21% of these conversations experienced almost no change in emotion). In turn, only 10.42% of the conversations laying more on the optimistic side maintained the mood. User emotional volatility is further linked with social influence.

Topics, Sentiments, and Emotions Triggered by COVID-19-Related Tweets from IRAN and Turkey Official News Agencies.

There is no doubt that the COVID-19 epidemic posed the most significant challenge to all governments globally since January 2020. People have to readapt after the epidemic to daily life with the absence of an effective vaccine for a long time. The epidemic has led to society division and uncertainty. With such issues, governments have to take efficient procedures to fight the epidemic. In this paper, we analyze and discuss two official news agencies' tweets of Iran and Turkey by using sentiment- and semantic analysis-based unsupervised learning approaches. The main topics, sentiments, and emotions that accompanied the agencies' tweets are identified and compared. The results are analyzed from the perspective of psychology, sociology, and communication.

Comparison of CNN Architecture for Thermal Face Emotion Classification

After the corona pandemic, people's feelings of depression are increasing in most countries. Emotion recognition is an essential technology for the increasing demand for non-face-to-face medical services to reduce the risk of infection. A skin temperature pattern can be used as one of the indicators indicating the emotional state. In this paper, the self-constructed thermal image DB was applied to the existing CNN architecture for facial expression classification and performance evaluation was performed. As a result, it was confirmed that the network in which several kernels are applied in parallel in order to extract various features has good performance. © 2021 IEEE.

Emotion Classification of COVID-19 Chinese Microblogs based on the Emotion Category Description

Emotion classification of COVID-19 Chinese microblogs helps analyze the public opinion triggered by COVID-19. Existing methods only consider the features of the microblog itself, without combining the semantics of emotion categories for modeling. Emotion classification of microblogs is a process of reading the content of microblogs and combining the semantics of emotion categories to understand whether it contains a certain emotion. Inspired by this, we propose an emotion classification model based on the emotion category description for COVID-19 Chinese microblogs. Firstly, we expand all emotion categories into formalized category descriptions. Secondly, based on the idea of question answering, we construct a question for each microblog in the form of 'What is the emotion expressed in the text XT and regard all category descriptions as candidate answers. Finally, we construct a question-and-answer pair and use it as the input of the BERT model to complete emotion classification. By integrating rich contextual and category semantics, the model can better understand the emotion of microblogs. Experiments on the COVID-19 Chinese microblog dataset show that our approach outperforms many existing emotion classification methods, including the BERT baseline. © 2021 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License

How does "A Bit of Everything American" state feel about COVID-19? A quantitative Twitter analysis of the pandemic in Ohio.

COVID-19 has proven itself to be one of the most important events of the last two centuries. This defining moment in our lives has created wide-ranging discussions in many segments of our societies, both politically and socially. Over time, the pandemic has been associated with many social and political topics, as well as sentiments and emotions. Twitter offers a platform to understand these effects. The primary objective of this study is to capture the awareness and sentiment about COVID-19-related issues and to find how they relate to the number of cases and deaths in a representative region of the United States. The study uses a unique dataset consisting of over 46 million tweets from over 91,000 users in 88 counties of the state of Ohio, a state-of-the-art deep learning model to measure and detect awareness and emotions. The data collected is analyzed using OLS regression and System-GMM dynamic panel. Findings indicate that the pandemic has drastically changed the perception of the Republican party in the society. Individual motivations are strongly influenced by ideological choices and this ultimately affects individual pandemic-related outcomes. The paper contributes to the literature by expanding the knowledge on COVID-19 (i), offering a representative result for the United States by focusing on an "average" state like Ohio (ii), and incorporating the sentiment and emotions into the calculation of awareness (iii).