Identifying Potential Lyme Disease Cases Using Self-Reported Worldwide Tweets: Deep Learning Modeling Approach Enhanced With Sentimental Words Through Emojis.

BACKGROUND: Lyme disease is among the most reported tick-borne diseases worldwide, making it a major ongoing public health concern. An effective Lyme disease case reporting system depends on timely diagnosis and reporting by health care professionals, and accurate laboratory testing and interpretation for clinical diagnosis validation. A lack of these can lead to delayed diagnosis and treatment, which can exacerbate the severity of Lyme disease symptoms. Therefore, there is a need to improve the monitoring of Lyme disease by using other data sources, such as web-based data. OBJECTIVE: We analyzed global Twitter data to understand its potential and limitations as a tool for Lyme disease surveillance. We propose a transformer-based classification system to identify potential Lyme disease cases using self-reported tweets. METHODS: Our initial sample included 20,000 tweets collected worldwide from a database of over 1.3 million Lyme disease tweets. After preprocessing and geolocating tweets, tweets in a subset of the initial sample were manually labeled as potential Lyme disease cases or non-Lyme disease cases using carefully selected keywords. Emojis were converted to sentiment words, which were then replaced in the tweets. This labeled tweet set was used for the training, validation, and performance testing of DistilBERT (distilled version of BERT [Bidirectional Encoder Representations from Transformers]), ALBERT (A Lite BERT), and BERTweet (BERT for English Tweets) classifiers. RESULTS: The empirical results showed that BERTweet was the best classifier among all evaluated models (average F1-score of 89.3%, classification accuracy of 90.0%, and precision of 97.1%). However, for recall, term frequency-inverse document frequency and k-nearest neighbors performed better (93.2% and 82.6%, respectively). On using emojis to enrich the tweet embeddings, BERTweet had an increased recall (8% increase), DistilBERT had an increased F1-score of 93.8% (4% increase) and classification accuracy of 94.1% (4% increase), and ALBERT had an increased F1-score of 93.1% (5% increase) and classification accuracy of 93.9% (5% increase). The general awareness of Lyme disease was high in the United States, the United Kingdom, Australia, and Canada, with self-reported potential cases of Lyme disease from these countries accounting for around 50% (9939/20,000) of the collected English-language tweets, whereas Lyme disease-related tweets were rare in countries from Africa and Asia. The most reported Lyme disease-related symptoms in the data were rash, fatigue, fever, and arthritis, while symptoms, such as lymphadenopathy, palpitations, swollen lymph nodes, neck stiffness, and arrythmia, were uncommon, in accordance with Lyme disease symptom frequency. CONCLUSIONS: The study highlights the robustness of BERTweet and DistilBERT as classifiers for potential cases of Lyme disease from self-reported data. The results demonstrated that emojis are effective for enrichment, thereby improving the accuracy of tweet embeddings and the performance of classifiers. Specifically, emojis reflecting sadness, empathy, and encouragement can reduce false negatives.

Non-face emojis in digital marketing: Effects, contingencies, and strategic recommendations.

Non-face (NF) emojis are increasingly used to complement or substitute words in digital marketing messages, yet the effects, mechanisms, and contingencies of this communication strategy remain underexplored. In a large-scale longitudinal study of Airbnb listings, we show that NF emojis (vs. simple text) lead to an increase in eWOM volume, an effect we replicate experimentally. This effect is qualified by important boundary conditions whose underlying mechanisms are investigated in two additional experimental studies. At the message level, using multiple substitutive (vs. complementary) NF emojis reduces message evaluations and eWOM volume due to reduced processing fluency. At the source level, seller quality further moderates the interaction between emoji function and emoji number: for premium sellers, using multiple NF emojis reduces message evaluations and eWOM volume irrespective of their function due to reduced perceptions of competence. We distill these findings into detailed managerial guidelines for using NF emojis in digital marketing. Supplementary Information: The online version contains supplementary material available at 10.1007/s11747-022-00917-z.

Putting your best face forward: How instructor emoji use influences students' impressions of credibility, immediacy, and liking.

This project explores the impacts of emojis on students' impressions when used in a course welcome email. We adopt a 4 × 3 factorial design to determine how different emojis (i.e., , , ) impact students' impressions of credibility, immediacy, and liking. Data from students (N = 368) indicates emoji choice does impact impressions. Consistently, instructors' emoji use resulted in decreased perceived competence and trustworthiness but increased perceived caring, immediacy, and liking. Findings have implications for instructors who engage in technologically-mediated out-of-class communication and want to strengthen early student-instructor relationships. Limitations and future directions are also discussed.

COVID-19 and the Gendered Use of Emojis on Twitter: Infodemiology Study.

BACKGROUND: The online discussion around the COVID-19 pandemic is multifaceted, and it is important to examine the different ways by which online users express themselves. Since emojis are used as effective vehicles to convey ideas and sentiments, they can offer important insight into the public's gendered discourses about the pandemic. OBJECTIVE: This study aims at exploring how people of different genders (eg, men, women, and sex and gender minorities) are discussed in relation to COVID-19 through the study of Twitter emojis. METHODS: We collected over 50 million tweets referencing the hashtags #Covid-19 and #Covid19 for a period of more than 2 months in early 2020. Using a mixed method, we extracted three data sets containing tweets that reference men, women, and sexual and gender minorities, and we then analyzed emoji use along each gender category. We identified five major themes in our analysis including morbidity fears, health concerns, employment and financial issues, praise for frontline workers, and unique gendered emoji use. The top 600 emojis were manually classified based on their sentiment, indicating how positive, negative, or neutral each emoji is and studying their use frequencies. RESULTS: The findings indicate that the majority of emojis are overwhelmingly positive in nature along the different genders, but sexual and gender minorities, and to a lesser extent women, are discussed more negatively than men. There were also many differences alongside discourses of men, women, and gender minorities when certain topics were discussed, such as death, financial and employment matters, gratitude, and health care, and several unique gendered emojis were used to express specific issues like community support. CONCLUSIONS: Emoji research can shed light on the gendered impacts of COVID-19, offering researchers an important source of information on health crises as they happen in real time.

Semantic and syntactic processing of emojis in sentential intermediate positions.

The current study investigated the neuro mechanisms of emoji processing as sentence predicate in written context. In the hybrid textuality which is more cognitively engaging, emojis in sentential intermediate positions were designed as either congruent or incongruent to the context. The results showed that incongruent words led to a robust N400 effect, while incongruent emojis only elicited the P600 effect. It implies that semantics and syntax of words can be separated while those of emojis seem to be integrated together. That is, when the meaning of the emoji is violated to the sentential context, its grammatical role cannot be well interpreted, especially when it is used as a key grammatical component in a sentence, such as the predicate. Thus, it shows that even though the meaning of emojis can be interpreted by readers, their syntactic and semantic functions cannot be clearly separated. In comparison with word processing, the larger amplitude with emojis in the time window of 350-500 ms shows more cognitive efforts in emoji semantic processing, possibly arising from the switch of modalities within the visual channel, that is, the multimodal cognitive load.

Is there an intergenerational discrepancy in the comprehension and aesthetic preference regarding emoji usage? Evidence from WeChat.

Emojis are widely used on social media, blogs, and instant messaging to express users' feelings. However, in everyday interactions, the same emoji often has different interpretations and aesthetic preferences among different age groups. This can lead to communication barriers and misunderstandings. Based on social identity theory, this study uses WeChat, a social platform popular in China, to analyze intergenerational differences in emoji understanding and preferences through a questionnaire survey. The results indicate: (1) There are significant intergenerational differences in the usage habits, interpretation, and aesthetic preferences of emojis. (2) Middle-aged and elderly tend to interpret goodbye emoji symbols as simple emotional expressions, such as "goodbye" or "see you later," while younger-age groups lean towards more complex emotions and social intentions, such as "speechlessness" and "end of friendship." (3) Younger-age groups use emojis frequently and with a wide variety, whereas middle-aged and elderly groups use emojis less frequently and with limited variety. Younger individuals' aesthetic preferences for emojis lean towards humor, conflict, and narrative, whereas middle-aged and elderly groups prefer emojis with bright colors and everyday greetings typical of their generation. Based on research findings, we believe that social identity theory provides a framework for understanding how individuals establish their identities through interactions with specific social groups. This study is beneficial for identifying the comprehension and aesthetic biases in emoji usage across generations, sheds light on the broader implications of social identity theory in digital communication contexts, and promotes friendly social interactions in real-time communication applications.

Emoji use in social media posts: relationships with personality traits and word usage.

Prior research has demonstrated relationships between personality traits of social media users and the language used in their posts. Few studies have examined whether there are relationships between personality traits of users and how they use emojis in their social media posts. Emojis are digital pictographs used to express ideas and emotions. There are thousands of emojis, which depict faces with expressions, objects, animals, and activities. We conducted a study with two samples (n = 76 and n = 245) in which we examined how emoji use on X (formerly Twitter) related to users' personality traits and language use in posts. Personality traits were assessed from participants in an online survey. With participants' consent, we analyzed word usage in posts. Word frequencies were calculated using the Linguistic Inquiry Word Count (LIWC). In both samples, the results showed that those who used the most emojis had the lowest levels of openness to experience. Emoji use was unrelated to the other personality traits. In sample 1, emoji use was also related to use of words related to family, positive emotion, and sadness and less frequent use of articles and words related to insight. In sample 2, more frequent use of emojis in posts was related to more frequent use of you pronouns, I pronouns, and more frequent use of negative function words and words related to time. The results support the view that social media users' characteristics may be gleaned from the content of their social media posts.

Are you really smiling? Display rules for emojis and the relationship between emotion management and psychological well-being.

Display rules specify socially appropriate facial expressions in a given situation. However, managing emotions for such a social adaption sometimes leads to deleterious psychological outcomes. Given that people nowadays rely on emojis to express emotions online, the present study investigated (1) whether display rules exist in emoji communications and (2) how emotion management using emojis is associated with psychological well-being. Prior studies have demonstrated the effects of context on the frequency of emoji use. However, the intensity and type of expression may differ, even if emojis are used at the same frequency. The current study thus investigated whether emotional expressions and the types of emojis used are adjusted to contexts similar to facial displays. As many as 1,289 Japanese participants typed emojis in response to Internet chats and reported the intensity of their emotional expressions. The contexts of the chats varied depending on the target of use, the emotional value of contexts, and private or public settings. The results showed that, similar to facial displays, individuals expressed emotions through emojis more with those closely related, more in positive contexts than in negative contexts, and more in private than in public contexts. When the expressions were intense, individuals used emojis consistent with the emotional value of the context. Upon attenuating the expressions, this study found that individuals tended to use euphemistic emojis and sent smiling emojis in negative contexts to manage the expressions. Moreover, expressing emotions with emojis was associated with subjective well-being, whereas managing emotions with emojis was weakly associated with depressive symptoms. Together, this study indicates the existence of display rules for emojis, calling for future research on the psychological impact of online emotion norms.

Speech acts and the communicative functions of emojis in LIHKG online discussion forum amid COVID-19.

Since the beginning of 2022, the Hong Kong government has imposed strict social distancing measures and changed its stance on various regional policies with the aim to contain the so-called 'fifth wave' of COVID-19. In these pandemic and 'infodemic' times filled with uncertainty and fear, Hong Kong netizens used local online discussion forums as a resource to establish an innovative form of 'helping network.' This study is based on 230 posts from a popular local online discussion forum 'LIHKG' in February 2022 when the pandemic was regarded as most critical by the Department of Health. Speech Acts theoretic approach was adopted to explore how forum users employed speech acts to perform various communicative practices such as expressing concerns, asking for information, and engaging with others in a CMC environment amid a global health crisis. Representatives were found to be the most dominant text-based speech acts, followed by directives, expressives and commissives. Speech acts provide forum users a context in which emoji usage occurs. Forum users not only make use of words to 'do' things in the online self-help forum, but they also employ emojis to either supplement or complement speech acts. This study also shows that emojis perform multiple functions in the discussion posts and argues that they do not merely function as emotion indicators of their textual company, but also carry significant pragmatic meanings by illustrating how they can also carry illocutionary force and in some cases, even alter the illocutionary force of their preceding texts. The findings of this study enhance our understanding of how forum users communicate via verbal and nonverbal means within the underexplored 'helping domain' of online discussion forums. It also suggests that online discussion forum interactions need to be approached differently than other better understood alternatives.

Stimulus data and experimental design for a self-paced reading study on emoji-word substitutions.

This data paper presents the experimental design and stimuli from an online self-paced reading study on the processing of emojis substituting lexically ambiguous nouns. We recorded reading times for the target ambiguous nouns and for emojis depicting either the intended target referent or a contextually inappropriate homophonous noun. Furthermore, we recorded comprehension accuracy, demographics and a self-assessment of the participants' emoji usage frequency. The data includes all stimuli used, the raw data, the full JavaScript code for the online experiment, as well as Python and R code for the data analysis. We believe that our dataset may give important insights related to the comprehension mechanisms involved in the cognitive processing of emojis. For interpretation and discussion of the experiment, please see the original article entitled "The processing of emoji-word substitutions: A self-paced-reading study".

Age Differences in the Interpretation of Facial Emojis: Classification on the Arousal-Valence Space.

Emojis are universal tools that are frequently used to express people's emotional states throughout daily communications. They are often applied in various fields of research, such as consumer surveys, as indicators of users' emotional states. Further analyses of emoji interpretation among people with age are required to ensure the validity of emojis as a metric in such fields of research, thereby reducing misunderstandings. However, details regarding the effect of age on both arousal and valence, as they pertain to the interpretation of emojis, remain unclear. Therefore, in this study, we investigate the effects of the interpretation of facial emojis on the arousal-valence space among people of varying age groups. We conducted an online survey involving 2,000 participants, whereby we employed a nine-point scale to evaluate the valence and arousal levels associated with 74 facial emojis. Based on the two axes of valence and arousal among the age groups involved in this study, emojis are categorized into six similar clusters. For the two negative clusters, i.e., strongly negative and moderately negative sentiments, the group involving middle-aged participants showed significantly higher levels of arousal compared to the group involving young participants. Additionally, not all emojis classified into the aforementioned negative clusters indicate age difference. Based on these results, this study recommends using emojis with no age-related effects on the negative clusters as indices for evaluating human emotions.

Emotional violation of faces, emojis, and words: Evidence from N400.

Human social interactions depend on the construction of emotional meaning. The present study used event-related potentials to investigate the neural features of emotional violation processing in facial expressions, emojis, and emotion words. Behavioral results showed emotion congruency effects among facial expressions, emojis, and emotion words. Emotional violations resulted in a longer response time than emotion congruent conditions in happy context conditions. Responses to angry faces were slower in angry sentences than in happy sentences. As expected, the classic N400 effect was obtained for the emotional violations among facial expressions, emojis, and emotion words. Emotional violations resulted in more negative-going N400 amplitudes. Moreover, the N400 effects elicited by facial expressions and emojis were significantly smaller than emotion words, and there were no significant differences in N400 effects between facial expressions and emojis. The findings suggest that the emotional violation processing of facial expressions, emojis, and emotion words could be reflected in an electrophysiological index of semantic processing, and that emotional violation elicited higher levels of semantic retrieval. In addition, there were differences between nonverbal and verbal information processing in emotional violation, while the emotional violation of words induced greater semantic retrieval demands than facial expressions and emojis.

The role of personality traits and engagement factors towards the use of paid stickers in personal communication messages.

Background: The research investigated the personality traits and engagement factors that influence the use of paid stickers in personal communication. The study was driven by the increasing significance of stickers such as emoticons and emojis in online dialogues. The study was hinged on the Theory of the big five personality traits; neuroticism, extraversion, openness to experience, agreeableness and conscientiousness. The study tested seven hypotheses to ascertain the effect of personality traits and engagement factors towards the utilization of paid stickers in personal communication. Methods: The research applied the quantitative survey research design, where primary data was collected from respondents that had experience in using emojis and emoticons in their communications. The data was collected from respondents in Bangkok, Thailand using a structured questionnaire between May 14, 2022, and May 31, 2022.    Results: The results from 391 respondents indicated that conscientiousness, extraversion, openness, and neuroticism influence perceived enjoyment, while perceived enjoyment and perceived ease of use have a significant and positive influence on the intention to use paid stickers. Two elements of engagement, interactive engagement, and personal engagement were used to assess the influence of engagement parameters on the behavioral intention to use paid stickers. The intention to employ paid stickers in personal messages was found to be strongly and favorably influenced by these two engagement characteristics. Conclusions: The study recommends that the creators of stickers, emoticons, and emojis should consider user personality features, sticker engagement, sticker simplicity of use, and the personal delight of users in the creative and communication process. The study concludes that perceived enjoyment and perceived ease of use have a large and favorable impact on the use of paid stickers. The study's main limitation was that it focused on one area of social media. This must be taken into account when applying the findings.

Enhancing EFL Learners' Self-Efficacy Beliefs of Learning English with Emoji Feedbacks in CALL: Why and How.

Encouraging feedback positively affects learners' self-efficacy; in language learning, self-efficacy predicts language learner performance and behavior. Our research involved three studies to expand knowledge about why and how we can enhance English as a Foreign Language (EFL) learners' self-efficacy beliefs in online settings. In Study 1, based on an online survey with 310 participants, we ascertained the extent to which EFL learners with greater self-efficacy tend to challenge themselves by learning content that requires a proficiency level that is higher than their current proficiency. In Study 2, we recruited 120 EFL learners; the results indicate that positive feedback via emojis embedded in online courses could significantly boost EFL learners' self-efficacy beliefs about learning English. Study 3 involved 35 participants and extended the understanding provided by the first two studies, showing that EFL learners not only like to use emojis for computer-mediated communication (CMC), but also prefer to receive them as feedback. This research adds to knowledge on "why" and "how" we can enhance EFL learners' self-efficacy beliefs in online contexts. We systematically provide empirical evidence regarding the aforementioned issues and demonstrate that positive feedback through emojis has great potential to enhance EFL learners' self-efficacy, even when such feedback is subliminal.

The Multidimensional Lexicon of Emojis: A New Tool to Assess the Emotional Content of Emojis.

Emerging studies suggest that emojis can make important contributions to the emotional content and meaning of digital messages. Yet researchers currently lack adequate tools to incorporate emojis into their analyses. To address this gap, we used over 3 million Twitter posts from a period of 17 months and emotion ratings provided by 2,230 human raters to develop and validate the Multidimensional Lexicon of Emojis (MLE). This new lexicon consists of 359 common emojis rated on ten emotion and sentiment dimensions. The MLE is an open-access tool that holds promise for those interested in conducting a comprehensive analysis of the emotional content of digital communication that incorporates emojis and goes beyond the dimensions of negativity and positivity.

An integrated instrumental and sensory techniques for assessing liking, softness and emotional related of gluten-free bread based on blended rice and bean flour.

Despite recent scientific advances and the growth of the gluten-free market, important issues such as the improvement of the sensory and nutritional quality of gluten-free bread (GFB) still need to be addressed. Therefore, the aim of the present study was to integrate instrumental and sensory techniques for assessing liking, softness, and emotions related to GFB based on rice flour (RF) and bean flour (BF). Results shows that common BF increases the ash, protein, and dietary fiber content of bread. The RF and BF blend improves dough thermomechanical properties, bread volume, instrumental texture properties and acceptability, as well as being the formulation indicated by consumers as presenting ideal softness, all of which subsequently correlated with positive food-related emotions, based on a facial emojis list. Thus, a RF and BF blend is a valuable ingredient producing nutrient-dense and acceptable GFB, which is important for consumers who choose or must adhere to a gluten-free diet. This research highlights promising predictors able to correlate dough parameters, as well as physical properties of bread with the sensory quality of GFB; this could be helpful to food scientists and producers to conduct extensive sensory and consumer research regarding both commercial and experimental GFB to establish whether those products meet consumer expectations, showing the relevance of continuing studies.

COVID-19 vaccine hesitancy: The effects of combining direct and indirect online opinion cues on psychological reactance to health campaigns.

This study aims to examine whether and how user-generated comments and reaction emojis on COVID-19 vaccine-promoting Facebook posts induce psychological reactance to posts and vaccine hesitancy in audiences of the posts. An online experiment including 465 American adults showed that, compared with COVID-19 vaccine promotion posts accompanied by pro-vaccine comments, those accompanied by anti-vaccine comments provoked greater reactance in audiences through the mediating effects of bandwagon perception and the presumed influence of the posts on others. Greater reactance, in turn, increased audiences' COVID-19 vaccine hesitancy. Additionally, reaction emojis altered the comments' effects such that pro-vaccine comments triggered less reactance than anti-vaccine comments when the pro-vaccine comments were accompanied by agreement emojis (i.e., "like" and "love"); whereas there was no significant difference between pro-vaccine comments and anti-vaccine comments in reactance when the pro-vaccine comments were accompanied by rejection emojis (i.e., "angry" and "sad"). Furthermore, audiences' pre-existing attitudes did not affect the effects of opinion cues on their' reactance and vaccine hesitancy.

Emojis and Emoticons in Health Care and Dermatology Communication: Narrative Review.

Background: Emoticons and emojis have become staple additions to modern-day communication. These graphical icons are now embedded in daily society through the various forms of popular social media and through users' personal electronic conversations. With ever-increasing use and inclusivity, exploration of the possible health care and dermatology applications of these tools is imperative. Objective: The goal of this narrative review was to provide and evaluate an up-to-date literature survey examining the utility of emoticons and emojis in medicine. Special attention was paid to their existing and potential uses in the field of dermatology, especially during the COVID-19 pandemic. Methods: A PubMed search of peer-reviewed publications was performed in mid-2021 to collect articles with emoticon or emoji keywords in combination with other health care-relevant or dermatology-relevant keywords. Screening of publications and described studies was performed by the authors with education and research experience in health care, dermatology, social media, and electronic communication trends. Selected articles were grouped based on common subjects for qualitative analysis and presentation for in-depth discussion. Results: From this extensive search, researchers were able to identify a wide variety of publications detailing the use of emoticons and emojis in general health care, pediatric health care, public health, and dermatology. Key subject areas that emerged from the investigation included the ability of emoticons and emojis to improve communication within pediatric health care, enhance mood and psychological assessment or mental health screening in adults, develop interventions to improve patient medication adherence, complement novel means of public health and COVID-19 surveillance, and bolster dermatology-specific applications. Conclusions: This review illuminated the repurposing of emojis and emoticons for a myriad of advantageous functions in health care and public health, with applications studied in many populations and situations. Dermatology-specific uses were relatively sparse in the literature, highlighting potential opportunities for growth in future studies and practices. The importance of diversity and inclusivity has extended to emojis, with the recent introduction of skin color customization and new emojis better representing the comprehensive spectrum of users' experiences. A continuously evolving and technology-driven population creates a unique niche for emoticons and emojis to ease worldwide communication and understanding, transcending the barriers of age, language, and background. We encourage future studies and innovations to better understand and expand their utility.

Sentiment Analysis in Social Media Data for Depression Detection Using Artificial Intelligence: A Review.

Sentiment analysis is an emerging trend nowadays to understand people's sentiments in multiple situations in their quotidian life. Social media data would be utilized for the entire process ie the analysis and classification processes and it consists of text data and emoticons, emojis, etc. Many experiments were conducted in the antecedent studies utilizing Binary and Ternary Classification whereas Multi-class Classification gives more precise and precise Classification. In Multi-class Classification, the data would be divided into multiple sub-classes predicated on the polarities. Machine Learning and Deep Learning Techniques would be utilized for the classification process. Utilizing Social media, sentiment levels can be monitored or analysed. This paper shows a review of the sentiment analysis on Social media data for apprehensiveness or dejection detection utilizing various artificial intelligence techniques. In the survey, it was optically canvassed that social media data which consists of texts,emoticons and emojis were utilized for the sentiment identification utilizing various artificial intelligence techniques. Multi Class Classification with Deep Learning Algorithm shows higher precision value during the sentiment analysis.

Going virtual in the early years: 30-month-old toddlers recognize commonly used emojis.

People nowadays do not only display facial expressions in face to face communication but also in on-line communication using graphical symbols named emojis. The present study explored 30-month-old toddlers' ability to recognize emojis that represented six basic human emotions. In the study, 38 toddlers first saw scenarios that elicited different emotions in an actor and were asked to visually identify the matching emoji in the presence of a distractor. Eye-tracking results showed that toddlers could correctly identify the emoji that represented the emotion in each scenario. Toddlers then heard different emotion words and were again found to be able to identify the matching emoji. These findings provide preliminary evidence that the ability to recognize and understand the emotional value of emotion symbols in the virtual world emerges early in development.