Number Of Tweets Research Articles

Whose tweets about obesity and weight loss gain the most attention: celebrities, political, or medical authorities?

X (formerly Twitter) is a unique social medium where many famous people and health institutions post and interact with casual users. We aimed to explore reactions to tweets about obesity and weight loss from accounts representing celebrities, politicians, sportsmen, and health authorities. We collected tweets from n = 2444 X profiles representing seven categories: celebrities, politicians, sportsmen, medical specialists, medical journals, medical universities, and health institutions. We retrieved tweets from the accounts and selected tweets about, e.g., obesity, overweight, body mass index, and weight loss. We conducted sentiment analysis, descriptive statistics, and multivariable quantile regression modeling. In quantile regression models, each tau represents a decile from 0.1 to 0.9 of the dependent variable (number of likes or retweets). Therefore, a tau value of 0.5 represents the 5th decile, the 50th percentile, and the median of the dependent variable. The final dataset consisted of n = 8989 tweets. Achieving a large number of likes (taus 0.7, 0.8, and 0.9) was positively associated with posts written by celebrities, politicians, medical journals, and universities, while it was negatively associated with tweets authored by health institutions or medical specialists. In the case of a significant number of retweets, a positive association was observed for all account types, except for health institutions, for which the relationship was negative. These relationships were independent of verification status, the number of followers, tweet length, and sentiment. Tweets concerning obesity and weight loss originating from accounts representing health institutions garnered fewer likes and retweets compared to other types of accounts, including non-medical ones. A limitation of the study is the relatively small number of tweets emanating from non-medical accounts. A X informational campaign about obesity should engage non-medical accounts with many followers to reach as many users as possible.

What Are the Most Popular Articles in Urogynecology and Who Is Disseminating Them

Importance This research describes which articles published in Urogynecology are garnering the most attention online. Understanding which articles are having the largest impact in the online community has become increasingly important due to the exponential increase in the use of social media on the internet. Objective The Altmetric Attention Score (AAS) is a quantitative and qualitative measure of the articles’ online attention in social media and news outlets, blogs, and reference managers. The aim of this study was to provide an analysis of those accessing and sharing the 100 most popular articles published in Urogynecology. Study Design This was a retrospective descriptive analysis. Using Dimensions, a “linked research knowledge system,” data about each article’s demographics on Twitter and other media sources was extracted from each of the articles within Urogynecology with the highest AAS. No articles were excluded. The articles were categorized by topic and metrics of online sharing were compared among categories. Results Fifteen categories were created. Sexual health and education articles had the highest average Altmetric scores per article and reached the highest impressions per article and had the highest average follower count per Twitter user. On average, social justice in medicine had the highest number of tweets per article. Tweets were most often composed by members of the public (58%) compared with health care practitioners (14%), researchers (13%), and science communicators (12%). Conclusions Sexual health and education articles had the highest average AAS and impressions on Twitter. We observed a difference in which articles are being shared most among the general public and health care professionals. The general public comprised a majority of those sharing articles online regardless of category. Additionally, there may be a disparity in research, its funding, and online scientific communications within the field of urogynecology.

Categorizing E-cigarette-related tweets using BERT topic modeling

BackgroundSocial media platforms are critical channels for promoting e-cigarettes, particularly among youth, making analysis of their vast and diverse content essential for public health interventions. Prevalence rates of e-cigarette use are high and evidence suggests that social media are popular forums that promote e-cigarette use through direct and indirect marketing techniques. The volume and diverse nature of e-cigarette-related information on social media is challenging and may obfuscate public health prevention messaging. Traditional hand-coding methods are labor-intensive and limit scalability. In contrast, unsupervised machine learning approaches, such as topic modeling, allow for efficient analysis of large datasets, uncovering patterns and trends that manual methods cannot achieve at scale. The present study focused on ascertaining the extent to which themes and topics in tweets related to e-cigarettes can be successfully rendered into useful homogenous units using machine learning. A better understanding of current depictions and discussions around e-cigarette products and use on social media can inform public health counter messaging and policy interventions. MethodsWe used topic modeling (BERTopic) to iteratively derive vape-related tweet clusters and calculate the importance of particular words to these groupings. We conducted a qualitative content analysis to study clustered tweets. We also sought to determine the geographic locations of e-cigarette conversations using automated geoparsing methods, which translate toponyms in textual data into geographic identifiers, to attempt to infer the location of tweets. ResultsWe were able to successfully identify >100,000 tweets in broad thematic categories in English and Spanish. Our correlation and inter-topic map analysis of the machine-derived topics, which examines the relationships between topics, indicated that most of the topics were unique (correlation value < 0.5) and did not overlap with each other. We identified six topics: Flavors and Disposable Vapes, Cannabis, Vape Shops and Refillable Vapes, Vape Culture, Anti-vaping and Quitting, and Spanish Tweets and Vaping Nicotine. Further analysis of these topics using qualitative methods identified themes within each topic. For example, Category 6 (Spanish Tweets and Vaping Nicotine) included four topics focused on the health risks of vaping, personal motivations for vaping, and the regulation of vaping products. Using geoparsing, which automatically detects location information, we found that the United States had the highest number of tweets related to vaping. Discussion/conclusionResults underscore the possibility of leveraging BERTopic modeling to reduce large quantities of data to comprehensively describe and categorize myriad e-cigarette related messages to which social media users are exposed. This data reduction approach can be applied to various social media platforms to describe and categorize e-cigarette posts and thereby triangulate and validate findings. Thematic content analysis of the topics identified through this technique requires supervision and human inputs. Our approach provides a comprehensive understanding of the evolving e-cigarette discourse, informing public health counter-messaging and policy interventions. Moreover, findings support the need for regulation, such as reducing appealing flavors and suggest that social media can be used effectively to support public health messaging (i.e., quitting messages).

Social media and health care: a cross-sectional analysis of X (Twitter) posts using the NodeXL platform

Introduction. The landscape of healthcare and medical education is rapidly evolving, driven by the popularity of social media platforms like Facebook, WeChat, and X (Twitter). These platforms have transformed healthcare communication, enabling trainees, medical students, and practitioners to enhance learning and clinical practice. Educators leverage social media to simplify complex medical concepts, fostering continuous learning and professional development. Despite their benefits, social media, notably X (Twitter), boasting over 186 million active users, are susceptible to misinformation, underscoring the importance of verifying data accuracy and identifying influential medical sources. This study aims to identify the most influential sources of health information through X (Twitter) analysis using the NodeXL tool. Methods. Employing a cross-sectional design, this study utilized the NodeXL platform for social media analysis. NodeXL facilitated the identification of prevalent topics in public health discussions on X (Twitter). Influencers, users, and prominent healthcare providers were categorized to assess the credibility of their information. Data collection extended up to March 1, 2024. Results. Analysis revealed that the #hospital hashtag garnered the highest number of tweets among popular healthcare hashtags (6,438 tweets, with 84% being unique). Conversely, #medicalcare and #medicine had the lowest citation counts (58 and 116 respectively). @MahaHealthIE emerged as the most famous account using the #healthservices hashtag. Notable influencers with the #hospital hashtag included YouTube, Narendra Modi, and Al Jazeera English. @GreenSwelfares led in using the #medicalcare hashtag, while YouTube and the World Health Organization (@WHO) were prominent among accounts using #medicine. Conclusion. This study underscores the significance of monitoring social media and tracking key influencers periodically. However, the study's limitation lies in its snapshot nature, failing to capture the dynamic shifts in influencer popularity trends over time.

Public Perception of the Tobacco 21 Amendment on Twitter in the United States: Observational Study.

Following the signing of the Tobacco 21 Amendment (T21) in December 2019 to raise the minimum legal age for the sale of tobacco products from 18 to 21 years in the United States, there is a need to monitor public responses and potential unintended consequences. Social media platforms, such as Twitter (subsequently rebranded as X), can provide rich data on public perceptions. This study contributes to the literature using Twitter data to assess the knowledge and beliefs of T21. Twitter data were collected from November 2019 to February 2021 using the Twitter streaming application programming interface with keywords related to vaping or e-cigarettes, such as "vape," "ecig," etc. The temporal trend of the T21 discussion on Twitter was examined using the mean number of daily T21-related tweets. Inductive methods were used to manually code the tweets into different sentiment groups (positive, neutral, and negative) based on the attitude expressed toward the policy by 3 coders with high interrater reliability. Topics discussed were examined within each sentiment group through theme analyses. Among the collected 3197 tweets, 2169 tweets were related to T21, of which 444 tweets (20.5%) showed a positive attitude, 736 (33.9%) showed a negative attitude, and 989 (45.6%) showed a neutral attitude. The temporal trend showed a clear peak in the number of tweets around January 2020, following the enactment of this legislation. For positive tweets, the most frequent topics were "avoidance of further regulation" (120/444, 27%), "Enforce T21" (110/444, 24.8%), and "health benefits" (81/444, 18.2%). For negative tweets, the most frequent topics were "general disagreement or frustration" (207/736, 28.1%) and "will still use tobacco" (188/736, 25.5%). Neutral tweets were primarily "public service announcements (PSA) or news posts" (782/989, 79.1%). Overall, we find that one-third of tweets displayed a negative attitude toward T21 during the study period. Many were frustrated with T21 and reported that underage consumers could still obtain products. Social media data provide a timely opportunity to monitor public perceptions and responses to regulatory actions. Continued monitoring can inform enforcement efforts and potential unintended consequences of T21.

Stroke recovery—what are people talking about on Twitter? A content analysis

Purpose Prioritisation exercises seek out what matters to key stakeholders to inform the planning of research. Social media platforms are potentially useful data sources. The aim was to examine the content of tweets, short messages containing text and pictures, to ascertain the priorities of Twitter users regarding stroke recovery. Materials and methods Content analysis of Twitter was conducted. An electronic search used the identifiers: #strokesurvivor and #strokerecovery. Tweets spanning four weeks from January 2021 were analysed. Results There were 1361 tweets extracted and 486 analysed following exclusion of duplicates and unrelated material. Six themes were uncovered (n = number of tweets): maintaining motivation and positivity (153); sharing of resources (146); raising awareness of stroke (74); symptomatic aspects of recovery (39); experience of rehabilitation (63); and concerns about Covid-19 (17). Conclusions Despite the brevity of tweets, a rich picture arose. A key limitation was lack of biographical data about Twitter users. Recommendations about topics requiring attention from stroke researchers, clinicians and policy makers are: management of psychological problems; public perception of stroke; rehabilitation considerations including treatment burden, person-centred care and equality of care; symptom management including fatigue and aphasia. Findings can be used to supplement and validate other priority-setting exercises.

Public Perceptions of the Food and Drug Administration's Regulatory Authority Over Synthetic Nicotine on Twitter: Observational Study.

The Omnibus Budget Bill, known as H. R. 2471, passed through Congress on March 10, 2022, and was eventually signed by President Biden on March 15, 2022. This bill amended the Federal Food, Drug, and Cosmetic Act granting the Food and Drug Administration (FDA) regulatory authority over synthetic nicotine. This study aims to examine the public perceptions of the Omnibus Bill that regulates synthetic nicotine products as tobacco products on Twitter (rebranded as X). Through the X streaming application programming interface, we collected and identified 964 tweets related to the Omnibus Bill on synthetic nicotine between March 8, 2022, and April 13, 2022. The longitudinal trend was used to examine the discussions related to the bill over time. An inductive method was used for the content analysis of related tweets. By hand-coding 200 randomly selected tweets by 2 human coders respectively with high interrater reliability, the codebook was developed for relevance, major topics, and attitude to the bill, which was used to single-code the rest of the tweets. Between March 8, 2022, and April 13, 2022, we identified 964 tweets related to the Omnibus Bill regulating synthetic nicotine. Our longitudinal trend analysis showed a spike in the number of tweets related to the bill during the immediate period following the bill's introduction, with roughly half of the tweets identified being posted between March 8 and 11, 2022. A majority of the tweets (497/964, 51.56%) had a negative sentiment toward the bill, while a much smaller percentage of tweets (164/964, 17.01%) had a positive sentiment toward the bill. Around 31.43% (303/964) of all tweets were categorized as objective news or questions about the bill. The most popular topic for opposing the bill was users believing that this bill would lead users back to smoking (145/497, 29.18%), followed by negative implications for small vape businesses (122/497, 24.55%) and government or FDA mistrust (94/497, 18.91%). The most popular topic for supporting the bill was that this bill would take a dangerous tobacco product targeted at teens off the market (94/164, 57.32%). We observed a more negative sentiment toward the bill on X, largely due to users believing it would lead users back to smoking and negatively impact small vape businesses. This study provides insight into public perceptions and discussions of this bill on X and adds valuable information for future regulations on alternative nicotine products.

The Societal Impact of the Papers Published in Blended Learning in Medicine on Social Network Sites: An Altmetrics Study.

Nowadays, blended learning in medicine (BLM) has gained the attention of most experts as an invaluable approach to improving the quality of medical education. The level of attention to articles in this field on social networks is substantial. This study aimed to study the effectiveness of published articles in blended learning, indexed in Scopus and Web of Science databases between 2013 and 2022, from an altmetrics perspective. The research is descriptive-analytical, with a scientometrics approach (using the Altmetrics index). The population includes all the articles on blended learning in medicine, indexed in Scopus and Web of Science databases, two well-known citation databases worldwide. Data were extracted using the Altmetrics bookmarklet tool and analyzed with descriptive statistics methods in Excel software. Out of 1327 articles, 136 articles (10.25%) did not have a digital object identifier (DOI) or PMID number. Mendeley, X (previously Twitter), and Dimensions were the most widely used social networks in blended learning. The United States, the United Kingdom, and Australia had the highest number of tweets in blended learning in medicine. The number of articles with altmetrics indicators, categorized by publication year, demonstrates an improvement in the familiarity and use of social media by blended learning researchers in medicine. Blended learning researchers are advised to carefully select reputable journals - preferably with DOI - to increase the visibility and attention to their articles on social media.

Feasibility of big data analytics in disaster psychiatry: Impact of Seoul Itaewon tragedy on sentiment distribution on Twitter

Numerous studies have highlighted the significant impact of disasters on mental health, often leading to psychiatric disorders among affected individuals. Timely identification of disaster-related mental health problems is crucial to prevent long-term negative consequences and improve individual and community resilience. To address the limitations of prior research that has focused solely on isolated incidents, we analyzed the impact of a recurring Halloween event in Itaewon, South Korea, which culminated tragically in a crowd crush incident in 2022. We conducted sentiment analysis on big data from Korean Twitter to gauge the impact of this disaster on public sentiment. We collected tweets 2 weeks before and after the annual festival from 2020 to 2022, allowing for the consideration of variability across years and days before the disaster. Using a pre-trained RoBERTa neural network model fine-tuned with public sentiment datasets, we categorized tweets into seven pre-defined emotional categories: Anger, sadness, happiness, disgust, fear, surprise, and neutrality. These sentiments were then analyzed as daily time-series data. The overall tweet volume across all sentiment categories increased, particularly showing an increase in the number of tweets indicating “Sadness” in 2022 compared with that in previous years. Post-disaster, a substantial increase was noted in the proportion of tweets expressing “Sadness” and “Fear.” This trend was confirmed by Seasonal Autoregressive Integrated Moving Average with Exogenous Regressor models. Notably, there was an increase in the number of tweets expressing all sentiments, including “Happy.” However, significant changes in proportions were observed only in tweets categorized as expressing “Sadness” [0.046 (95% CI: 0.024–0.068, P < 0.0001)] and “Fear” [0.033 (95% CI: 0.014–0.051, P < 0.0001)]. Our study demonstrates the feasibility of using sentiment data from social media, combined with sentiment classification, to assess distinct public mental health features following disasters. This approach provides valuable insights into the emotional impact of each event.

The power of social media: broader Twitter outreach and higher Altmetric scores significantly amplify neurosurgical citation reach.

The authors sought to quantify the role of social media-related academic activity through use of the Altmetric score (a composite score based on social media attention from a variety of sources) and investigate its potential impact on the number of citations received at 3 years postpublication (articles published between January 2019 and December 2019). Articles published in the top 12 neurosurgical journals according to Google Scholar (based on 5-year Web of Science impact factors, 2017-2021) were identified. Data collected included days since publication, Altmetric scores, and total number of tweets (posts), and 3-year citations were obtained from Google Scholar. A multiple linear regression model was created that featured a blocking method to stratify confounding variables from most to least contributing. Furthermore, the data were dichotomized by publications with ≥ 10 citations (top 25th percentile) and those with < 10 to analyze the impact of the score on total number of citations received at 3 years, using an independent-samples Mann-Whitney U-test. Among 6721 included articles, the mean Altmetric score was 3.76 ± 15.69 and the mean number of citations received was 9.61 ± 22.16. When accounting for relevant control variables, the Altmetric score was a significant predictor of the total number of citations accumulated at 3 years (variability of 10.17%). On statistical testing, the Altmetric score was significantly higher in publications with ≥ 10 citations (p < 0.001). The authors report a strong, statistically significant correlation between the Altmetric score and the number of citations received. To their knowledge, this is the first study to demonstrate the impact of social media academic activity on neurosurgery article citation dissemination, potentially influencing resident medical education.

ExaAUAC: Arabic Twitter user age prediction corpus based on language and metadata features

Twitter is a rich resource for analyzing the contents of social media and extracting the age groups of users can be beneficial for recommender systems, marketing and advertising. Age detection task is an aspect of demographic information of users. In this study a large-scale corpus of Arabic Twitter users including 181k user profiles with diverse age groups consisting of −18, 18–24, 25–34, 35–49, 50–64, +65 is presented. The corpus is created by four methods: (1) collecting publicly available birthday announcement tweets using the Twitter Search application programming interface, (2) augmenting data, (3) fetching verified accounts, and (4) manual annotation. To have a best age detection model on the presented corpus, different evaluations are tested to find the model with highest accuracy and efficiency. Number of tweets, regression vs. classification, using metadata of users and tweets, using LSTM+CNN model vs. BERT are some parts of examinations done. Presented methodology is based on language and metadata features and final model is fine-tuned with BERT on 70k users and evaluated on 8200 manually annotated users. We show that our best model, compared with LSTM+CNN model and BERT-based similar model yields an improvement of up to 9% in F1-score and increment of 5% in accuracy, respectively. The model achieved macro-averaged F1-score of 44 on six age groups, and F1-score of 58 on three age groups of −25, 25–34, +35. The link of our proposed data is provided here: www.github.com/exaco/ExaAUAC.

Using relational learning in exploring the effectiveness of using hashtags in future topics and user relations in X

This research has a research object, namely relational learning with a mathematical modeling approach from graph queries for exploring future topics and user relationships. The problem in this research is the large and varied number of tweets that are produced every day, where each use of hashtags always increases, which has an impact on the accumulation of data that needs to be processed to obtain information because users on social media X can interact to influence trends so as to solve the problem. This requires the application of relational learning by utilizing graph query mathematical models. The results obtained from this research are in the form of a model that can produce predictions of future topics and see user relationships based on interactions on social media with relationships between entities at interconnected nodes. In applying relational learning with mathematical models utilizing graph queries there will be a process of examining the relationships between entities, content and communication interactions in accordance with the definitions and theorems that have been described to observe each node. In relational learning, there will be each node according to the entity used, then the mathematical model with graph queries will connect all the entities to form a graph that can be used as a model for predicting future topics and relationships between users. This research is research with a level of novelty in applying graphical queries to mathematical models to predict future topics and applying relational learning to user relationships so that it can add information related to future communication. Graph queries aim to model a node between relations in the data so that it can represent a relationship between variables

Nutrients and Foods Recommended for Blood Pressure Control on Twitter in Japan: Content Analysis.

Management and prevention of hypertension are important public health issues. Healthy dietary habits are one of the modifiable factors. As Twitter (subsequently rebranded X) is a digital platform that can influence public eating behavior, there is a knowledge gap regarding the information about foods and nutrients recommended for blood pressure control and who disseminates them on Twitter. This study aimed to investigate the nature of the information people are exposed to on Twitter regarding nutrients and foods for blood pressure control. A total of 147,898 Japanese tweets were extracted from January 1, 2022, to December 31, 2022. The final sample of 2347 tweets with at least 1 retweet was manually coded into categories of food groups, nutrients, user characteristics, and themes. The number and percentage of tweets, retweets, and themes in each category were calculated. Of the 2347 tweets, 80% (n=1877) of tweets mentioned foods, which were categorized into 17 different food groups. Seasonings and spices, including salt, were most frequently mentioned (1356/1877, 72.2%). This was followed by vegetable and fruit groups. The 15 kinds of nutrients were mentioned in 1566 tweets, with sodium being the largest proportion at 83.1% (n=1301), followed by potassium at 8.4% (n=132). There was misinformation regarding salt intake for hypertension, accounting for 40.8% (n=531) of tweets referring to salt, including recommendations for salt intake to lower blood pressure. In total, 75% (n=21) of tweets from "doctors" mentioned salt reduction is effective for hypertension control, while 31.1% (n=74) of tweets from "health, losing weight, and beauty-related users," 25.9% (n=429) of tweets from "general public," and 23.5% (n=4) tweets from "dietitian or registered dietitian" denied salt reduction for hypertension. The antisalt reduction tweets accounted for 31.5% (n=106) of the most disseminated tweets related to nutrients and foods for blood pressure control. The large number of tweets in this study indicates a high interest in nutrients and foods for blood pressure control. Misinformation asserting antisalt reduction was posted primarily by the general public and self-proclaimed health experts. The number of tweets from nutritionists, registered dietitians, and doctors who were expected to correct misinformation and promote salt reduction was relatively low, and their messages were not always positive toward salt reduction. There is a need for communication strategies to combat misinformation, promote correct information on salt reduction, and train health care professionals to effectively communicate evidence-based information on this topic.

Twitter Sentiment Analysis Using Machine Learning

In an age of social media, online forums, and chats, cyberbullying is a prevalent issue. On Twitter (now X), approximately 500 million tweets are shared per day (Antonakaki et.al., 2021). It is the job of the moderators to ensure these tweets follow standard community guidelines. However, the sheer number of tweets makes it difficult to sort manually and ensure they are following protocol. Sentiment analysis and machine learning algorithms can be used to classify these texts automatically as positive or negative. Normally, these machine learning models are much more efficient and may provide higher accuracy rates in identifying hate speech in Twitter. In this paper, we are exploring the use of five classical machine learning algorithms to classify Twitter hate speech as neutral, racist, or sexist. Model performance was compared after using raw tweet data versus pre-processed tweets through data cleanup. Furthermore, we highlight two methods to deal with imbalanced datasets to improve the prediction rates. Overall, we were able to achieve a 96% accuracy in correctly classifying tweets into the different labels.

Sentiment Analysis of COVID-19 Tweets using Neural Network in Pakistan

Covid-19 is a respiratory infectious disease that spreads from person to person. World Health Organization declared it a pandemic in March 2020. Social distancing and lockdowns during the pandemic affected the lives, sentiments, and mental health of people. They are mentally, physically, and emotionally disturbed. It was observed that the verification of the very first Covid case increased the precariousness and fear in Pakistan because people had no information about the state policies. In this paper, Covid-related tweets from Pakistan for the year 2021 are collected. Pakistan faced two Covid waves in 2021. Dataset is preprocessed and a neural network-based model is applied to analyze the sentiment of the tweet. Sentiments of people are analyzed separately for each Covid wave, moreover, a comparative analysis is presented to discuss the change in people's sentiments with the passage of time. Results show a reduction in the number of tweets from third to fourth wave. Moreover, the %decrease in negative and positive sentiments are 6 and 1 respectively which show that by the passage of time, people started living with the environment and time healed the wounds of fears and uncertainty in their lives.

Analyzing social media reactions to the FTX crisis: Unraveling the spillover effect on crypto markets

AbstractIn this study, we analyzed social media conversations during the unfolding of the FTX crisis, the biggest cryptocurrency scandal in United States history. Drawing on the accessibility‐diagnosticity framework, we examined the negative spillover effect of the crisis using a natural language processing approach. We specifically assessed whether there was a negative spillover from FTX to other crypto entities with different levels of diagnostic attribute similarity. We collected a large corpus of Twitter conversations related to the FTX collapse in 2022 and used the association rule analysis to determine the association between FTX and other crypto entities. Our analysis revealed that the number of tweets mentioning FTX and other crypto entities changed in line with a series of real‐world events during the FTX crisis. The negative spillover of the FTX crisis occurred primarily during the first 10 days as the FTX scandal unfolded. The results indicated that the FTX crisis spilled over to highly accessible and diagnostic crypto entities, such as Binance, Bitcoin, and the cryptocurrency industry in general. On the other hand, less accessible and less diagnostic crypto entities/currencies like Ethereum and Coinbase did not experience negative spillover from the scandal.

Evaluating NMT using the non-inferiority principle

Abstract The aim of this article is to propose a new neural machine translation (NMT) evaluation method based on the non-inferiority principle. In order to do that, we evaluate raw machine translation (MT) in terms of naturalness, which for this research is defined as not just the lack of fluency errors but also meeting the linguistic expectations of Galician end users when reading original texts in Galician. Our main objective is, in the first place, to validate the new methodology presented in our previous study by evaluating an NMT engine from Spanish into Galician for the social media domain that was retrained with a new Twitter corpus. This new methodology and NMT engine were applied after analyzing the conclusions of a pilot survey conducted among Twitter users to evaluate their perception of tweets translated from Spanish into Galician with our NMT engine created with a corpus of tweets. As in our preliminary study, our aim is to propose a robust quality approximation method based on the reception parameters of end users’ perceptions. This new survey was conducted in December of 2022 with the participation of 228 Galician-speaking Twitter users. Among the main changes proposed are the inclusion of more information about the participant profile, so the non-inferiority principle can be also evaluated according to these parameters; the inclusion of a new typology of tweets, the threads; the provision of context by means of presenting the tweets in their original display as shown in the Twitter app; a change in the number of tweets evaluated and the number of different questionnaires; the change in the distribution of the questionnaires; and the inclusion of an error classification human evaluation conducted by professional linguists to correlate the findings. We will present the steps carried out following the conclusions of the pilot study, describe the new study’s design, analyze the new findings, and present the final conclusions regarding the engine and the evaluation method based on the non-inferiority principle. Finally, we will also provide some examples of the use of this new methodology in the translation industry.

Public perception of psychiatry, psychology and mental health professionals: a 15-year analysis.

X (previously known as "Twitter") serves as a platform for open discussions on mental health, providing an avenue for scrutinizing public perspectives regarding psychiatry, psychology and their associated professionals. To analyze the conversations happening on X about psychiatrists, psychologists, and their respective disciplines to understand how the public perception of these professionals and specialties has evolved over the last 15 years. We collected and analyzed all tweets posted in English or Spanish between 2007 and 2023 referring to psychiatry, psychology, neurology, mental health, psychiatrist, psychologist, or neurologist using advance topic modelling and sentiment analysis. A total of 403,767 tweets were analyzed, 155,217 (38%) were in English and 248,550 (62%) in Spanish. Tweets about mental health and mental health professionals and disciplines showed a consistent volume between 2011 and 2016, followed by a gradual increase from 2016 through 2022. The proportion of tweets discussing mental health doubled from 2016 to 2022, increasing from 20% to 67% in Spanish and from 15% to 45% in English. Several differences were observed on the volume of tweets overtime depending on the language they were written. Users associated each term with varied topics, such as seeking for help and recommendation for therapy, self-help resources, medication and side effects, suicide prevention, mental health in times of crisis, among others. The number of tweets mentioning these topics increased by 5-10% from 2016 to 2022, indicating a growing interest among the population. Emotional analysis showed most of the topics were associated with fear and anger. The increasing trend in discussions about mental health and the related professionals and disciplines over time may signify an elevated collective awareness of mental health. Gaining insights into the topics around these matters and user's corresponding emotions towards them presents an opportunity to combat the stigma surrounding mental health more effectively.

MAPPING OF SENTIMENT ANALYSIS ON FOOD SECURITY AMONG MALAYSIANS USING SOCIAL MEDIA ANALYTICS

The study investigates the spatial distribution of sentiment in food securityrelated tweets among Malaysians, aiming to identify hotspots of positive, negative, and neutral sentiments. Note that data collection involved gathering 2,218 tweets on basic necessity products from January 2019 to August 2022, capturing the impact of the COVID-19 pandemic. Pre-processing and content analysis techniques identified the main themes in the tweets, while sentiment analysis categorised them using Valance Aware Dictionary and Sentiment Reasoner (VADER). ArcGIS and hotspot analysis visualised and analysed tweet density. Regional trends were observed, with the East Coast states and certain West Coast states having the highest number of tweets. Urban areas expressed concerns about food security and living costs due to urbanisation and limited agricultural land. Here, sentiment visualisation revealed negative sentiments prevalent in developed cities (46.8%) and positive (33.9%) or neutral (19.4%) sentiments in suburban areas. This study emphasises the growing use of social media platforms and the integration of social media data in spatial analysis, highlighting the importance of uncovering hidden patterns for increased social awareness and meaningful dialogue. Understanding the sentiments expressed by Malaysians on social media regarding rising food prices can provide valuable insights for policymakers and stakeholders to address these challenges effectively.

Feeling analysis on allergen immunotherapy on Twitter using an unsupervised machine learning model

Analyze feelings about allergen-specific immunotherapy on Twitter using the VADER model VADER (Valence Aware Dictionary and sEntiment Reasoner) model. tweets related to specific allergen immunotherapy were obtained through the Twitter Application Programming Interface (API). The keywords "allergy shot" were used between January 1, 2012, and December 31, 2022. The data was processed by removing URLs, usernames, hashtags, multiple spaces, and duplicate tweets. Subsequently, a sentiment analysis was performed using the VADER model. A total of 34,711 tweets were retrieved, of which 1928 were eliminated. Of the remaining 32,783 tweets, 32.41% expressed a negative sentiment, 31.11% expressed a neutral sentiment, and 36.47% expressed a positive sentiment, with an average polarity of 0.02751 (neutral) over the 11-year period. The average polarity of tweets about allergen-specific immunotherapy is neutral over the 11 years analyzed. There was an annual increase in the average polarity over the years, with 2017, 2018, and 2022 having positive polarity averages. Additionally, the number of tweets decreased over time.