Emotional Comments Research Articles

Sense or Sensibility? Netizens’ Choice of Social Media Comments in an Authoritarian Regime

Abstract While the Internet in China is subjected to heavy state regulations, Chinese netizens can still access online comments that deviate from official discourse on many issues. To prevent online discussions from getting out of hand, the Chinese government uses soft propaganda such as online comments to channel public opinions. Which type of online comments appeal to Chinese netizens? Using a survey experimental design, we examine the appeal of 4 distinct types of online comments on certain policies. We find that our survey respondents spend significantly more time in consuming emotional comments that deviate from official discourse. When it comes to the effect on attitude, however, we find that deviating-emotional comments are no more persuasive than deviating-informational comments. Our results call into question the effectiveness of China’s state propaganda in channeling online public opinions while highlighting the importance of alternative information in shaping public opinions in an authoritarian context.

An empirical study on how emotion affects the probability of replies based BERT

The rapid development of the internet, social media, and online forums have become crucial platforms for people to express their views and emotions. Comments are not only a way for users to express their opinions but also play a vital role in promoting discussions and interactions between users, significantly influencing public opinion. This paper aims to explore the impact of emotions on the likelihood of comments receiving replies, deepening the understanding of the role of emotional factors in interactions on social media and online forums. Through large-scale model training and pipeline parallel computation, this paper employs the Bidirectional Encoder Representations from Transformers (BERT) model for learning and prediction, enhancing accuracy and efficiency. The experimental results show that the response rate of negative emotional comments is about 27%, while the response rate of positive emotional comments is about 18%. It means that the comments with negative emotions are more likely to receive replies than those with positive emotions.

Evolving cycles and self-organised criticality in social dynamics

In many complex systems, self-organised criticality (SOC) provides a mechanism for the diversity of spatiotemporal scales that optimises the system’s response to omnipresent driving forces. Signatures of SOC are increasingly more evidenced in collective social behaviours. However, the spontaneous occurrence of critical states and their role in maintaining the system’s functional properties still need to be better understood; the reason can be related to the complexity of human interactions and the ubiquitous presence of cycles in social dynamics. In this work, we shed new light on these issues based on a critical survey and the extensive data analysis of online social dynamics. Firstly, we highlight prominent features of human activity patterns, conditioned by circadian cycles and content-related interactions, that can affect the course of the dynamics from the elemental to the global scale. We then analyse the prototypal time series of emotion-driven communications in the online social network MySpace to demonstrate the coexistence of SOC states with the modulated cyclical trends. Precisely, we determine avalanches of emotional comments exhibiting multifractal scaling, scale-invariant inter-avalanching behaviours and temporal correlations coexist with the cyclical trends of broad singularity spectra. We demonstrate that similar multi-harmonic cycles occur in entirely different datasets, particularly the negative emotion-driven Diggs and the infection-rate data from recent epidemics. Our results reveal the dynamical regime where the modulated cycles coexist with self-organised critical states; in contrast, in the cycles-dominated regime, exemplified by the infection time series, the nature of collective dynamics remains hidden behind the cycle modulation.

A Deep Learning Framework for News Readers' Emotion Prediction Based on Features From News Article and Pseudo Comments.

With the rapid development of the Internet, readers tend to share their views and emotions about news events. Predicting these emotions provides a vital role in social media applications (e.g., sentiment retrieval, opinion summary, and election prediction). However, news articles usually consist of objective texts that lack emotion words, making emotion prediction challenging. From prior studies, we know that comments that come directly from readers are full of emotions. Therefore, in this article, we propose a deep learning framework that first merges article and comment information to predict readers' emotions. At the same time, in the prediction process, we design a pseudo comment representation for unpublished news articles by the comments of published news. In addition, a better model is required to encode articles that contain implicit emotions. To solve this problem, we propose a block emotion attention network (BEAN) to encode news articles better. It includes an emotion attention mechanism and a hierarchical structure to capture emotion words and generate structural information during encoding. Experiments performed on three public datasets show that BEAN achieves the state-of-the-art average Pearson (AP) and accuracy (Acc@1). Moreover, results on four self-collected datasets show that both the introduction of emotional comments and BEAN in our framework improve the ability to predict readers' emotions.

Jinxed byIncantation? Contemporary Chinese Netizens’ Reactions to a Horror Film

AbstractIncantationis a horror film released in the Republic of China (Taiwan) in March 2022, which is inspired by a real-life story and features a woman’s rescue of her six-year-old daughter after the latter is cursed by an abhorrent deity with occult powers. This film is adulated as one of the scariest Taiwanese films and attained prodigious commercial success. Nonetheless, in mainland China,Incantationis regarded as more of a contentious film than a fearsome one: audiences’ prevalent feedback is that they feel jinxed and offended, as indicated by their complaints on social media platforms as well as reviewing and question-and-answer websites. The primary reason lies in that the film’s heroine breaks the fourth wall and addresses audiences directly, which is further intensified by the film’s mockumentary shooting style and found-footage technique. In this research, I explore the rationale behind Chinese audiences’ negative and emotional comments onIncantationfrom a viewer’s perspective, by means of investigating their self-initiated comments and user-generated responses in China’s cyberspace, focusing on feedback posted on Weibo, Douban and Zhihu. Data cumulated from these sources manifest Chinese netizens’ mindset concerning contentious religious/supernatural discourse in cyberspace as well as their rationality towards superstitious constructs.

Influence of Emotional Factors (Positive, Negative) on the Usefulness of Product Reviews Based on Big Data

In the era of prosperous online shopping, product reviews play a decisive role in users’ decision to purchase products. At the same time, it can also help businesses understand the corresponding deficiencies, to make targeted improvements. However, users’ comments are full of emotional colors, and these comments with strong emotional tendencies have a greater impact on consumers than ordinary comments, especially those with negative emotions. At present, most text sentiment analysis is oriented at the chapter and sentence level, and there are few sentiment analysis refined to product-specific attributes. Based on this, this paper is aimed at exploring the influencing factors of the emotional tendency of product reviews, analyzing a large number of reviews of a certain mobile phone product, and extracting the keywords of the influencing factors. This article summarizes six key influencing factors. Through the constructed conceptual model of emotional tendencies, it is concluded that the impact of negative emotional comments on consumption is much greater than that of positive emotional comments. Then, there is a further conceptual model of negative affective tendencies. This paper explores the causes of the influencing factors of negative affective tendencies. In this paper, the influencing factors of negative emotional tendencies are subdivided into 10 secondary factors. Through the reliability test, all secondary factors are above 87%. Then, after scoring the negative comment text code, a regression analysis was performed, and it was found that 10 secondary factors were significant, and the corresponding regression model was obtained.

Customer Perceived Risk Measurement with NLP Method in Electric Vehicles Consumption Market: Empirical Study from China

In recent years, as people’s awareness of energy conservation, environmental protection, and sustainable development has increased, discussions related to electric vehicles (EVs) have aroused public debate on social media. At some point, most consumers face the possible risks of EVs—a critical psychological perception that invariably affects sales of EVs in the consumption market. This paper chooses to deconstruct customers’ perceived risk from third-party comment data in social media, which has better coverage and objectivity than questionnaire surveys. In order to analyze a large amount of unstructured text comment data, the natural language processing (NLP) method based on machine learning was applied in this paper. The measurement results show 15 abstracts in five consumer perceived risks to EVs. Among them, the largest number of comments is that of “Technology Maturity” (A13) which reached 25,329, and which belongs to the “Performance Risk” (PR1) dimension, indicating that customers are most concerned about the performance risk of EVs. Then, in the “Social Risk” (PR5) dimension, the abstract “Social Needs” (A51) received only 3224 comments and “Preference and Trust Rank” (A52) reached 22,324 comments; this noticeable gap indicated the changes in how consumers perceived EVs social risks. Moreover, each dimension’s emotion analysis results showed that negative emotions are more than 40%, exceeding neutral or positive emotions. Importantly, customers have the strongest negative emotions about the “Time Risk” (PR4), accounting for 54%. On a finer scale, the top three negative emotions are “Charging Time” (A42), “EV Charging Facilities” (A41), and “Maintenance of Value” (A33). Another interesting result is that “Social Needs” (A51)’s positive emotional comments were larger than negative emotional comments. The paper provides substantial evidence for perceived risk theory research by new data and methods. It can provide a novel tool for multi-dimensional and fine-granular capture customers’ perceived risks and negative emotions. Thus, it has the potential to help government and enterprises to adjust promotional strategies in a timely manner to reduce higher perceived risks and emotions, accelerating the sustainable development of EVs’ consumption market in China.

We can work it out: faculty interpretation of student evaluations of teaching

ABSTRACT Despite previous literature strongly criticising the use of student evaluations of teaching (SETs), it is unlikely that the frequency of SETs will be decreased for university instructors. However, little attention has been given to how we can make SETs work as a tool for improving teaching effectiveness. This research explores how faculty members of a large professional master’s programme in Brazil interpret the results of their SETs. The findings show that qualitative questions combined with quantitative scores are effective in improving classes. It also shows that faculty critically assess students’ feedback by disregarding emotional positive and negative comments and looking for suggestions in comments. Instructors with lower scores have difficulty interpreting feedback and tend to attribute their performance to nonresponse bias. This research contributes to the SET literature by showing that a combination of qualitative and quantitative questions can be effective in improving teaching quality but that some instructors may need support in interpreting SET results to change their teaching.

Modeling Dynamics of Online Short Video Popularity Based on Douyin Platform

This article analyzes the evolution mode of video view counts of nearly 1 000 short videos from “Douyin” platform. According to the statistical law, it is found that there are two time-varying patterns of cumulative short video view counts, namely single gradient and multi-gradient propagation modes. In order to explore the reasons for different propagation modes, this article analyzes the correlation among user’s liking behavior, the emotional tendency of comments and the view counts. It is found that the user's liking behavior will lead to further dissemination of short videos, and the higher the proportion of negative emotional comments is, the larger the view counts of short videos are. Finally, based on the two main spreading ways-passive viewing from recommendation of “Douyin” and active viewing from fans, and taking into account the feature that liking promotes the view counts, this article constructs an online short video liking-spreading dynamics model, which reproduces the evolution patterns of view counts of online short videos well, and the influence of different parameters on the evolution patterns of view counts are explored through the model simulation. In a word, this article reveals the spreading mechanism of online short videos and provides theoretical support for making more effective strategies for information promotion or control.

The effect of online reviews on restaurant visit intentions: applying signaling and involvement theories

Purpose The purpose of this study is to investigate the effect of online reviews on consumers’ intention to visit restaurants, with the moderating role of involvement. Design/methodology/approach The research framework was built on signaling theory, message appeals and involvement theory. To test the proposed framework, three experiments were conducted online with real customer samples. T-tests, ANOVA and SPSS PROCESS macro were used for data analysis. Findings The results revealed that online reviews with higher online ratings and emotional appeal led to higher restaurant visit intention. Review appeal significantly moderated the effect of online ratings on restaurant visit intention. Customers with low restaurant involvement were more impacted by emotional comments than by functional comments. Research limitations/implications The present study extends our knowledge on the effects of online reviews moderated by levels of customer involvement. By combining signaling theory with involvement theory, it adds value to the literature on customer online behavior, especially in the foodservice context. The present study has limitations that might provide opportunities for future research. It used evaluations (TripAdvisor scores) and only positive reviews (texts), so customers’ intentions considering negative reviews could not be examined. The level of hedonism concerning consumption in restaurants and prior knowledge regarding restaurant reviews was not controlled for. It is possible that the level of hedonism perceived and prior review knowledge may moderate the customers’ intention to visit the restaurant. Practical implications The present study shows the importance of online comments for the promotion of restaurants that have low evaluation scores. It is essential that restaurant owners and managers encourage potential customers by using comments to elaborate on their marketing strategies and promotion. At the same time, they should invite customers to share their emotional experiences, and not just their views on service efficiency (a functional aspect). During the COVID-19 pandemic, the use of the internet and mobile devices has become more prominent. Managers could therefore use emotional messages on the restaurant’s website or apps to attract customers with low restaurant involvement. Also, a system to identify the involvement of customers with restaurants could be implemented online or on mobile devices to present specific messages. The present study also recommends the use of online tools as virtual tours, photographs taken from different angles, smiling faces, floor plans and sittings and pre-determined emotional expressions. Also, the restaurant could promote lives on cooking different dishes to motive customer’s interaction and comments. These would help to increase customers’ visit intentions. Originality/value This study extends knowledge about the effect of restaurant online reviews (both ratings and appeals) moderated by the level of customer involvement. The present study also adds value to the customer online behavior literature showing that customers with low involvement are more sensitive to emotional content as they use the affective route to process information rather than the central route.

Entity-level sentiment prediction in Danmaku video interaction

Sentiment analysis in Danmaku video interaction aims at measuring public mood in respect of the video, which is helpful for the potential applications in behavioral science. Once these sentiments are discovered, this feedback can help video creators improve the video quality and greatly enhance online users’ watching experience. Predicting these entity-level sentiments is challenging because there is no publicly available dataset about entity-level sentiment analysis of Danmaku-enabled video comments. Furthermore, the targeted entity with skewed unbalance distribution in real-world scenarios, making the task more challenging, especially when the target entity only has positive (negative) emotional comments. In this case, applying previous aspect-level sentiment analysis models directly will introduce entity bias. In this paper, we propose a large-scale Chinese video comments dataset containing time-sync Danmaku comments and traditional video comments, targeting multiple entities and sentiments associated with each entity from popular video websites. We also propose a framework of entity-level sentiment analysis with two de-biasing models: hard-masking de-bias model and soft-masking de-bias model. This framework is defined by parallel neural networks to learn the representation of comments sentences. Based on the representations, our model learns a masking strategy for entity words to avoid overfitting and mitigate the bias. Our experiments on Danmaku-enabled video datasets show that the soft-masking model significantly outperforms comparable baselines, with a relative F1-score improvement of 9.33% compared to AEN-BERT and a relative F1-score improvement of 45.77% compared to Td-LSTM. Furthermore, experiments on different distribution bias of entity demonstrate that our proposed model can achieve competitive performances. The findings of this research have implications for measuring public sentiment for entities mentioned in a specific video domain. It can also be used as a benchmark dataset for aspect entity sentiment detection methods.

Is BTS Different? Shared Episodes on SNS as a Good Indicator for Celebrity Endorsed Ad Effects

This study examines the effects of celebrity endorsed advertising from a new perspective of the prior research that emphasizes the matchup between the brand and the celebrity. Due to the recent sharing experiences of the celebrity and their fans on SNS, it is hypothesized that the shared stories would impact viewers’ responses that are often expressed in their likes, dislikes, shares and comments on SNS. In this study, the episodic type of advertising is hypothesized to have more favorable and active responses from viewers than the typical celebrity image-focused ads would have. By crawling and analyzing viewers’ responses on YouTube toward 12 BTS endorsed ads, the hypotheses are confirmed as higher ratio of likes, lower ratio of dislikes and significantly higher ratio of comments over both total views and total likes were found. For the rationale behind, total 1800 comments were categorized into 4 major content types such as attached, experiential, empathic and self-related ones that are all considered as important factors influencing the strong ad effect. The results showed that the episodic ads have marginally more emotional comments than the celeb image ads. The difference was only found in experiential and empathic responses but not in self-related responses. Contrary to the hypothesis, the comments expressing attachment were found more for the celebrity image-focused ads than the episodic ones. It does not seem to suggest that the celebrity image focused ads are better to capture viewers’ attachment towards the celebrity and the ad endorsed, but that the episodic ads draw viewers into relatively deeper level of attachment such as empathy by perceiving the authenticity of the celebrity and the brand. In conclusion, the shared stories on SNS can be a factor in the match-up theory on celebrity endorsed ad effects.

Is BTS Different? Shared Episodes on SNS as a Good Indicator for Celebrity Endorsed Ad Effects

This study examines the effects of celebrity endorsed advertising from a new perspective of the prior research that emphasizes the matchup between the brand and the celebrity. Due to the recent sharing experiences of the celebrity and their fans on SNS, it is hypothesized that the shared stories would impact viewers’ responses that are often expressed in their likes, dislikes, shares and comments on SNS. In this study, the episodic type of advertising is hypothesized to have more favorable and active responses from viewers than the typical celebrity image-focused ads would have. By crawling and analyzing viewers’ responses on YouTube toward 12 BTS endorsed ads, the hypotheses are confirmed as higher ratio of likes, lower ratio of dislikes and significantly higher ratio of comments over both total views and total likes were found. For the rationale behind, total 1800 comments were categorized into 4 major content types such as attached, experiential, empathic and self-related ones that are all considered as important factors influencing the strong ad effect. The results showed that the episodic ads have marginally more emotional comments than the celeb image ads. The difference was only found in experiential and empathic responses but not in self-related responses. Contrary to the hypothesis, the comments expressing attachment were found more for the celebrity image-focused ads than the episodic ones. It does not seem to suggest that the celebrity image focused ads are better to capture viewers’ attachment towards the celebrity and the ad endorsed, but that the episodic ads draw viewers into relatively deeper level of attachment such as empathy by perceiving the authenticity of the celebrity and the brand. In conclusion, the shared stories on SNS can be a factor in the match-up theory on celebrity endorsed ad effects.

Automatic Intelligent Movie Sentiment Analysis Model Creation for Box Office Prediction using Multiview Light Semi Supervised Convolution Neural Network

With the rapid growth of e-commerce, online product and service monitoring is becoming more and more established as an important source of information for both sellers and customers. Emotional surveys and comments for online review analysis are gaining more and more attention as such studies help use information from online reviews for potential economic impacts. Twitter is a widely used social networking site and a trusted source of public opinion. The success of the film can be predicted by analyzing the tweets and researching the impact of the film. This report discusses the application of emotional analysis and in-depth machine learning methods to understand the relationship between online movie reviews, and this story is used to generate revenue at the movie box office. In this paper, this work present a Intelligent Extensive Information Rich Transfer Network (IEIRTN). It is modeled with information from sentences (i.e., reviews) and aspects simultaneously. First, IEIRTN extract all aspects of the sentence. After obtaining the aspects, it utilize all data in the source domain and the target domain for training Multiview Light Semi Supervised Convolution Neural Network (MLSSCNN) classifier. To understand the predictive performance of this approach several performance metrics are used. The experimental result shows that the MLSSCNN offers a superior predictive effect than other classifier.

Research on Users’ Emotion in the Later Period of the Inversion of public opinion--Taking the case of Wang Fengya as an example

Online public opinion reversal events occur frequently. The emotional characteristics and reasons of users in the later period of online public opinion reversal events are still not clear. Therefore, it is necessary to analyze the user emotions in the later period of the online public opinion reversal event, so as to help strengthen the supervision of public opinions and avoid the negative impact on the society in the process of public opinion reversal as far as possible. In this paper, Wang Fengya’s public opinion reversal event was taken as an example. Python crawler was used to capture the user comment data of the later period of this network public opinion reversal event. Combined with BosonNLP emotion dictionary, HowNet emotion dictionary and the characteristics of data capture, a custom emotion dictionary was constructed to realize the emotion analysis based on the custom emotion dictionary. In the later period of the reversal of public opinion on the Internet, user emotion has the characteristics of scattered user group structure, extreme and irrational emotion, and a high proportion of negative emotional comments. This is related to China’s economic development, the composition of Weibo network users and the diversity of media communication means.

Affective and physiological reactivity to emotional comments in individuals at elevated risk for psychosis

BackgroundIndividuals with schizophrenia are at increased risk of relapse when they live in highly critical (i.e., high expressed emotion; EE) family environments. It remains less clear, however, how individuals at elevated risk for a psychotic disorder react to the social stress of EE. Here we examined whether individuals at elevated risk for developing schizophrenia report greater subjective changes in affect and have increased physiological reactivity after hearing critical, praising and neutral comments. MethodMeasures of heart rate, heart rate variability, skin conductance, and self-reported affective ratings were used to assess differential responses to EE-type stimuli in 38 individuals at elevated-risk for psychosis and 38 low-risk controls. ResultsThe elevated-risk group and low-risk controls, did not differ in their initial affective and physiological reactivity to criticism. However, during the recovery period following the criticism, the elevated-risk group demonstrated greater heart rate activation. They also showed more sensitivity to praise. Although elevated-risk participants initially had higher baseline levels of negative affect and heart rate, following praise, these levels reduced and became indistinguishable from the levels of low-risk controls. ConclusionsThese findings suggest that at-risk individuals may have more difficulty recovering from criticism than their self-report data might suggest. They may also derive physiological and affective benefits from praise. Important clinical implications of these findings are discussed.

Attachment, mentalisation and expressed emotion in carers of people with long-term mental health difficulties

BackgroundExpressed emotion (EE) is a global index of familial emotional climate, which is comprised of emotional over-involvement (EOI) and critical comments (CC)/hostility. Although EE is an established predictor of negative outcomes for both people with long-term mental health difficulties and their family carers, its psychological underpinnings remain relatively poorly understood. This paper examined associations between attachment, mentalisation ability and aspects of EE.MethodsCarers of people with long-term mental health difficulties (n = 106) completed measures of adult attachment (the Experiences in Close Relationships-Short Form questionnaire), mentalisation (the Reading the Mind in the Eyes Test and the Emotional Self-Efficacy Scale) and EE (the Family Questionnaire). Data were analysed using hierarchical multiple regression.ResultsAttachment avoidance and facets of mentalisation were directly and uniquely positively associated with CC/hostility, with attachment avoidance and other-directed emotional self-efficacy (one facet of mentalisation) each significantly predicting CC/hostility scores after controlling for the effects of EOI and demographic variables. However, no associations were observed between EOI, attachment anxiety and mentalisation. Furthermore, no indirect effects from attachment to EE via mentalisation was found.ConclusionsAlthough it would be premature to propose firm clinical implications based on these findings, data indicate that it may be beneficial for clinicians to consider attachment and mentalisation in their conceptualisation of carers’ criticism and hostility. However, further research is needed to clarify the magnitude of these associations and their direction of effect before firm conclusions can be drawn.

Influencing Factors OTA Hotel Online Comments Usefulness-Based on Research of Text Analysis

Based on the OTA hotel online reviews as the research object,using the data mining and Text analysis technology to the empirical analysis of the factors that affect online comments usefulness,and building OTA hotel online comments usefulness influence factors model,and application in China in 2015 various types of OTA online hotel original comments validated data analysis,the results show that the comment of timeliness,score,comments of the emotional negative reviews and comments of the length of online reviews useful have a significant impact,and commnets on the number of positive reviews and comments in a emotional had no significant effect of online comments usefulness.For the comments readers for the automated recommendation systems provides the beneficial enlightenment

Using Go-Alongs for exploring immigrant entrepreneurs’ native customers

The purpose of this article is to evaluate the methodological practice of Go-Alongs for exploring immigrant entrepreneurs’ native customers, a barely developed subfield within immigrant business research. Through accompanying individuals on outings in their familiar environments, Go-Alongs as a qualitative data collection method are used to gain access to practices, experiences and interpretations of individuals in their everyday routines. Drawing on current qualitative research on native customers in immigrant grocery shops in Vienna, the article demonstrates how Go-Alongs can be used for exploring consumption practices and patterns of interethnic interaction in this specific setting. What becomes apparent is that Go-Alongs provide an opportunity to gain access to reflexive aspects of lived experience in situ, in the present case expressed by spontaneous and emotional comments when the shop, ethnic products or interethnic interactions are commented on and evaluated. Moreover, Go-Alongs allow insights into modes of self-expression. However, Go-Alongs have limitations as they cannot capture consumption practices beyond the limited time and space of shopping. Furthermore, they do not fully provide access to narratives and discourses; therefore, Go-Alongs are most useful in combination with in-depth interviews.

Timisoara 1989: Dead People, Revolution and Murderers

The deficient manner in which the international press recounted the Revolution of Timişoara in December 1989 established a depreciative framework of reference, particularly in the context of a lack of investigations, some of which would have been necessary. The negative perception was also fuelled by the amount of emotional comments made by various influential public figures. The official Romanian press did not make any reference to the number of victims and even minimized the extent of destructions in the city. This served a manipulative purpose, so that news of the insurgence would not get out. Foreign journalists could not enter Romania earlier than December 22, at approximately 1 p.m., when the borders were reopened. Until then, they relied on the bits of information that they got hold of from unreliable sources, such as Romanian, or, particularly, foreign citizens, who were able to leave Romania, or on scarce information provided by telephone and on communications between some states’ diplomatic staffs and their ministries. The process of launching and spreading rumours was also impressive, and after two days and two nights of waiting in border crossing points, the journalists who arrived in Timişoara and in other cities believed that the previously gained equivocal information was being confirmed. This allowed the emergence of the enormous confusion between the horrific dead in the Paupers Cemetery and the true victims of the Revolution.