Korean Language NLP Model Based Emotional Analysis of LGBTQ Social Media Communities

Sexual minorities are increasingly gaining social visibility and legal rights guarantees at the constitutional level across much of the world, from South America, the United States, and Europe to Japan, Taiwan, and Thailand. At the same time, the COVID-19 pandemic has brought on significant mental health challenges for the public due to accompanying social and economic impact and measures, most of them adverse. Given pre-existing studies highlighting the minority demographic's vulnerability to depression and other mental health symptoms, and the increasing availability of accessible NLP tools, datasets, and models, this paper uses an emotional classification model to analyze emotional trends in queer communities on social media. Using KoBERT with a pre-labelled dataset containing some forty thousand scraped social media posts labelled with emotions, patterns of emotional expression on Twitter in the queer community is revealed. Resulting data provided a validation of the viability of this method of analyzing trends in negative and positive emotional expression as well as the impact COVID-19 had on online queer communities in early 2020 but revealed limitations. © 2023 IEEE.

Evolution of Public Opinion on COVID-19 Based on Microblog Visualization

In January 2020, the outbreak of COVID in China attracted widespread attention and discussion on social media. Evolution of public opinion can help us understand users' hot topics and the evolution rule among these topics. Therefore, a public opinion evolution model based on microblog data is proposed in this paper. Firstly, a web crawler is used to obtain microblog data. Then the idea of sentiment analysis and topic extraction in order is used to analyze, and divide the stages through the emotional conflict evolution diagram. Finally, fine-grained emotion visualization is carried out for the hot topics in each stage, the evolution rule of public opinion on COVID-19 is summarized, and the effectiveness and scientificity of the method are also verified. © 2022 ACM.

Real-Time Emotional Analysis from A Live Webcam Using Deep Learning

In the Covid-19 age, we are becoming increasingly reliant on virtual interactions like as Zoom and Google meetings / Teams chat. The videos received from live webcamera in virtual interactions become great source for researchers to understand the human emotions. Due to the numerous applications in human-computer interaction, analysis of emotion from facial expressions has piqued the interest of the newest research community (HCI). The primary objective of this study is to assess various emotions using unique facial expressions captured via a live web camera. Traditional approaches (Conventional FER) rely on manual feature extraction before classifying the emotional state, whereas Deep Learning, Convolutional Neural Networks, and Transfer Learning are now widely used for emotional classification due to their advanced feature extraction mechanisms from images. In this implementation, we will use the most advanced deep learning models, MTCNN and VGG-16, to extract features and classify seven distinct emotions based on their facial landmarks in live video. Using the FER2013 standard dataset, we achieved a maximum accuracy of 97.23 percent for training and 60.2 percent for validation for emotion classification. © 2022 IEEE.

Analysis of public sentiment tendency in COVID-19 period based on GA-BiLSTM

As the Internet becomes the main source of information for the public, grasping the emotional polarity of online public opinion is particularly important for relevant departments to supervise online public opinion. In order to more accurately determine the emotional polarity of public opinion in the epidemic, this paper proposes a public sentiment analysis model based on Word2vec, genetic algorithm and Bi-directional Long Short-Term Memory (Bi-LSTM) algorithm. The Word2vec model converts the comment text into an n-dimensional vector, uses the Bi-LSTM algorithm to analyze the sentiment polarity, and uses the genetic algorithm to analyze the number of Bi-LSTM layers and the number of fully connected layers and the number of neurons in each layer of Bi-LSTM optimization. The experimental results show that the accuracy of the above model is compared with the accuracy of the Word2vec model and the LSTM model separately, and the accuracy is increased by 11.0% and 7.7%, respectively. © 2022 ACM.

A Study on Emotional Analysis Focusing on Onomatopoeia Used on SNS for the COVID-19

COVID-19 has dramatically changed the social situation in Japan. Along with the change in the real society, COVID-19 also changes the usage of social media. This study reports on findings from an analysis of onomatopoeia appears in posts on social media regarding COVID-19 to see how it has affected people's emotion. We analyzed the frequency of appearance of onomatopoeias expressing specific emotions according to the time variation, the relation between major events such as the declaration of state of emergency, and changes of co-occurrence words for the onomatopoeias. As a result of analysis, we found that the frequencies and degree of variation of onomatopoeias that belong to the same emotion group are complexly associated. The analysis results on co-occurrence words and frequency shift by events suggest that the cause of the change in emotion was different even for the onomatopoeia expressing the same emotion. The long-term emotional changes marked the peak in June 2020 during the second COVID-19 outbreak in Japan, rather than the first outbreak occurred in April 2020. At this time, as the number of infected people increased, the frequency of the use of the onomatopoeias also tended to increase. From the first case of COVID-19 in Japan (Jan 2019) to the second outbreak (Jun 2020), "anger "and "fear"were dominant emotions then they change to "peace of mind"during the second peak to the third outbreak (Nov 2020), and finally become "disgust". © 2021 ACM.

Research on public emotional polarization and public opinion evolution of OTC and learning during the COVID-19 epidemic: taking the topic of OTC on Zhihu as an example

Purpose>The outbreak and continuation of COVID-19 have spawned the transformation of traditional teaching models to a certain extent. The Chinese Ministry of Education’s guidance on “keep learning and teaching during class suspension” has made OTC and learning (OTC) become routinized, and the public’s emotional attitudes toward OTC have also evolved over time. The purpose of this study is to segment the emotional text data and introduce it into the topic model to reveal the evolution process and stage characteristics of public emotional polarity and public opinion of OTC topics during public health emergencies in the context of social media participation. The research has important guiding significance for the development of OTC and can influence and improve the efficiency and effect of OTC to a certain extent. The analysis of online public opinion can provide suggestions for the government and media to guide the trend of public opinion and optimize the OTC model.Design/methodology/approach>This paper takes the topic of “OTC” on Zhihu during the COVID-19 epidemic as an example, combined with the characteristics of public opinion changes, chooses Boson emotional dictionary and time series analysis method to build an OTC network public opinion theme evolution analysis framework that integrates emotional analysis and topic mining. Finally, an empirical analysis of the dynamic evolution of the communication network for each stage of the life cycle of a specific topic is realized.Findings>This paper draws the following conclusions: (1) Through the emotional value table and the change trend chart of the number of comments, the analysis found that the number of positive comments is greater than the number of negative comments, which can be inferred that the public gradually accepts “OTC” and presents a positive emotional state. (2) By observing the changing trend of the average daily emotional value of the public, it is found that the overall emotional value shows a stable development trend after a large fluctuation. From the actual emotional value and the fitted emotional value curve, it can be seen that the overall curve fit is good, so ARIMA (12, 1, 6) can accurately predict the dynamic trend of the daily average emotional value in this paper. Therefore, based on the above-mentioned public opinion, emotional analysis research, relevant countermeasures and suggestions are put forward, which is conducive to guiding the development direction of public opinion in a positive way.Originality/value>Taking the topic of “OTC” in Zhihu as an example, this paper combines Boson emotional dictionary and time series to conduct a series of research analyses. Boson emotional dictionary can analyze the public’s emotional tendency, and time series can well analyze the intrinsic structure and complex features of the data to predict the future values. The combination of the two research methods allows for an adequate and unique study of public emotional polarization and the evolution of public opinion.

Social Relations Under the Covid-19 Epidemic: Government Policies, Media Statements and Public Moods

In the face of public emergencies, how to better manage public opinion and maintain social stability is an important research content. Based on the background of the new epidemic in 2020, this paper explores how social emotions are transmitted among the government, the media and the public under public emergencies. Through natural language processing technology, this paper analyzes the relevant policies and media opinions of China, Britain and the United States under the new epidemic situation, and uses mf-dcca model to test the internal cross correlation. The results of the experiment unexpectedly found that a country’s government policy and the country’s media have a high degree of consistency in emotional orientation, and when the country’s social mood has abnormal fluctuations, the media will make adverse emotional statements, thus hedging the impact of some extreme policies on the society. From the perspective of emotion, this study provides a further theoretical basis for the relationship between the government and the public, proposes another control role of the media in emergencies, and discusses the relevant methods of media hedging government policies in the impact of social emotions. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Development of Recommendation System in e-Commerce using Emotional Analysis and Machine Learning Methods

The article identifies the theoretical aspects of e-commerce as an economic category, the problems of the current state of the e-commerce market related to the COVID-19 pandemic, consumer distrust and less functionality in the choice of clothing units. The aim of the article is the generalization, development and implementation of an expert system that will increase the functionality and efficiency of e- business. Research methods are mathematical apparatus for solving classification problems, regression, discrete methods, artificial neural networks, decision trees and other machine learning algorithms for solving classification problems, statistical methods and tools for data processing and analysis, data visualization tools. The problems of developing an expert system to increase the functionality of e-commerce were solved using R and Python programming languages, data processing and analysis. Practical significance of the research is to identify and use an effective algorithm for emotional analysis of the text, improve the method of collaborative filtering and develop an information system to provide recommendations to customers. As a result, the functionality and efficiency of e-commerce will increase. The obtained research results can be used as a methodological reference by software developers during the design and development of recommendation systems. © 2021 IEEE.

Research on public emotional polarization and public opinion evolution of OTC and learning during the COVID-19 epidemic: taking the topic of OTC on Zhihu as an example

Purpose The outbreak and continuation of COVID-19 have spawned the transformation of traditional teaching models to a certain extent. The Chinese Ministry of Education's guidance on "keep learning and teaching during class suspension" has made OTC and learning (OTC) become routinized, and the public's emotional attitudes toward OTC have also evolved over time. The purpose of this study is to segment the emotional text data and introduce it into the topic model to reveal the evolution process and stage characteristics of public emotional polarity and public opinion of OTC topics during public health emergencies in the context of social media participation. The research has important guiding significance for the development of OTC and can influence and improve the efficiency and effect of OTC to a certain extent. The analysis of online public opinion can provide suggestions for the government and media to guide the trend of public opinion and optimize the OTC model. Design/methodology/approach This paper takes the topic of "OTC" on Zhihu during the COVID-19 epidemic as an example, combined with the characteristics of public opinion changes, chooses Boson emotional dictionary and time series analysis method to build an OTC network public opinion theme evolution analysis framework that integrates emotional analysis and topic mining. Finally, an empirical analysis of the dynamic evolution of the communication network for each stage of the life cycle of a specific topic is realized. Findings This paper draws the following conclusions: (1) Through the emotional value table and the change trend chart of the number of comments, the analysis found that the number of positive comments is greater than the number of negative comments, which can be inferred that the public gradually accepts "OTC" and presents a positive emotional state. (2) By observing the changing trend of the average daily emotional value of the public, it is found that the overall emotional value shows a stable development trend after a large fluctuation. From the actual emotional value and the fitted emotional value curve, it can be seen that the overall curve fit is good, so ARIMA (12, 1, 6) can accurately predict the dynamic trend of the daily average emotional value in this paper. Therefore, based on the above-mentioned public opinion, emotional analysis research, relevant countermeasures and suggestions are put forward, which is conducive to guiding the development direction of public opinion in a positive way. Originality/value Taking the topic of "OTC" in Zhihu as an example, this paper combines Boson emotional dictionary and time series to conduct a series of research analyses. Boson emotional dictionary can analyze the public's emotional tendency, and time series can well analyze the intrinsic structure and complex features of the data to predict the future values. The combination of the two research methods allows for an adequate and unique study of public emotional polarization and the evolution of public opinion.

Emotional Analysis of Twitter Posts During the First Phase of the COVID-19 Pandemic in Greece: Infoveillance Study.

BACKGROUND: The effectiveness of public health measures depends upon a community's compliance as well as on its positive or negative emotions. OBJECTIVE: The purpose of this study was to perform an analysis of the expressed emotions in English tweets by Greek Twitter users during the first phase of the COVID-19 pandemic in Greece. METHODS: The period of this study was from January 25, 2020 to June 30, 2020. Data collection was performed by using appropriate search words with the filter-streaming application programming interface of Twitter. The emotional analysis of the tweets that satisfied the inclusion criteria was achieved using a deep learning approach that performs better by utilizing recurrent neural networks on sequences of characters. Emotional epidemiology tools such as the 6 basic emotions, that is, joy, sadness, disgust, fear, surprise, and anger based on the Paul Ekman classification were adopted. RESULTS: The most frequent emotion that was detected in the tweets was "surprise" at the emerging contagion, while the imposed isolation resulted mostly in "anger" (odds ratio 2.108, 95% CI 0.986-4.506). Although the Greeks felt rather safe during the first phase of the COVID-19 pandemic, their positive and negative emotions reflected a masked "flight or fight" or "fear versus anger" response to the contagion. CONCLUSIONS: The findings of our study show that emotional analysis emerges as a valid tool for epidemiology evaluations, design, and public health strategy and surveillance.

Emotional Attitudes of Chinese Citizens on Social Distancing During the COVID-19 Outbreak: Analysis of Social Media Data.

BACKGROUND: Wuhan, China, the epicenter of the COVID-19 pandemic, imposed citywide lockdown measures on January 23, 2020. Neighboring cities in Hubei Province followed suit with the government enforcing social distancing measures to restrict the spread of the disease throughout the province. Few studies have examined the emotional attitudes of citizens as expressed on social media toward the imposed social distancing measures and the factors that affected their emotions. OBJECTIVE: The aim of this study was twofold. First, we aimed to detect the emotional attitudes of different groups of users on Sina Weibo toward the social distancing measures imposed by the People's Government of Hubei Province. Second, the influencing factors of their emotions, as well as the impact of the imposed measures on users' emotions, was studied. METHODS: Sina Weibo, one of China's largest social media platforms, was chosen as the primary data source. The time span of selected data was from January 21, 2020, to March 24, 2020, while analysis was completed in late June 2020. Bi-directional long short-term memory (Bi-LSTM) was used to analyze users' emotions, while logistic regression analysis was employed to explore the influence of explanatory variables on users' emotions, such as age and spatial location. Further, the moderating effects of social distancing measures on the relationship between user characteristics and users' emotions were assessed by observing the interaction effects between the measures and explanatory variables. RESULTS: Based on the 63,169 comments obtained, we identified six topics of discussion-(1) delaying the resumption of work and school, (2) travel restrictions, (3) traffic restrictions, (4) extending the Lunar New Year holiday, (5) closing public spaces, and (6) community containment. There was no multicollinearity in the data during statistical analysis; the Hosmer-Lemeshow goodness-of-fit was 0.24 (χ28=10.34, P>.24). The main emotions shown by citizens were negative, including anger and fear. Users located in Hubei Province showed the highest amount of negative emotions in Mainland China. There are statistically significant differences in the distribution of emotional polarity between social distancing measures (χ220=19,084.73, P<.001), as well as emotional polarity between genders (χ24=1784.59, P<.001) and emotional polarity between spatial locations (χ24=1659.67, P<.001). Compared with other types of social distancing measures, the measures of delaying the resumption of work and school or travel restrictions mainly had a positive moderating effect on public emotion, while traffic restrictions or community containment had a negative moderating effect on public emotion. CONCLUSIONS: Findings provide a reference point for the adoption of epidemic prevention and control measures, and are considered helpful for government agencies to take timely actions to alleviate negative emotions during public health emergencies.