Language In Social Media Research Articles

Comparison of wellbeing structures based on survey responses and social media language: A network analysis.

Wellbeing is predominantly measured through surveys but is increasingly measured by analysing individuals' language on social media platforms using social media text mining (SMTM). To investigate whether the structure of wellbeing is similar across both data collection methods, we compared networks derived from survey items and social media language features collected from the same participants. The dataset was split into an independent exploration (n = 1169) and a final subset (n = 1000). After estimating exploration networks, redundant survey items and language topics were eliminated. Final networks were then estimated using exploratory graph analysis (EGA). The networks of survey items and those from language topics were similar, both consisting of five wellbeing dimensions. The dimensions in the survey- and SMTM-based assessment of wellbeing showed convergent structures congruent with theories of wellbeing. Specific dimensions found in each network reflected the unique aspects of each type of data (survey and social media language). Networks derived from both language features and survey items show similar structures. Survey and SMTM methods may provide complementary methods to understand differences in human wellbeing.

Attitude towards Social Media and English Language Competency of Grade 11 Students of Surigao State College of Technology

Attitude towards Social Media and English Language Competency of Grade 11 Students of Surigao State College of Technology

Social Media Influenced Lexicons: A Child’s Vocabulary Production in Talk-In Interactions

Social media has become a prominent medium of communication and has been used by all generations, including the youngest members of society. It has emerged as a powerful communication medium that makes interactions rapid, simple, and sensible. Youngsters also use social media to have fun, form and maintain connections, share and discover hobbies, explore identities, and grow familial ties; it is a continuation of their in-person and offline encounters. There is an assumption that with their exposure to modern gadgets, internet connectivity, and various online networking sites, children's daily talk-in interactions are influenced by social media languages. Utilizing a qualitative-descriptive research design, conversation analysis, Vygotsky's theory of language development and an interactionism approach, the purpose of the study is to provide an elaborated academic account of a child’s vocabulary production in casual conversations and list down the emerging social-media-influenced lexicons generated from a child, which were classified according to six-word categories: slang, colloquialism, alphabetism, neologism, loan words, and pseudowords. Findings show that the trends in digital exchanges on social media platforms have prevalent occurrences in a child’s everyday language, where some words and phrases possess critical meanings, as the child’s denotations and social-media connotations have a contrastive nature. As children develop their productive lexical skills using social media, the study highlights Vygotsky’s assertion on the importance of a child’s "more knowledgeable other" in language acquisition, production, and development.

Social Media Influence on Pakistani Youth’s Linguistic Expressions: A Predictive Study of Resultant Changes

Social media has taken over our lives in this era of technology and globalization in many ways. Among many other impacts on the users, the language choices, and expressions, mostly preferred by youth, are manipulated and affected by such online platforms. With this in view, this research seeks to understand how social media has transformed the language expressions of young Pakistanis. It also focuses on the possible resultant changes in linguistic choices made by youth after being influenced by social media. Data was collected through previous papers to discover the research gaps, and an online survey/questionnaire was administered to fulfil this study's goal. Fifty participants were randomly selected from five educational institutions in Sialkot, Pakistan (Govt. College Women University, NISA College, University of Management and Technology, University of Central Punjab, and Govt. Murray Graduate College). The data was critically, qualitatively, and quantitatively evaluated and analyzed. Furthermore, the research findings have shown that social media language dominates youngsters' linguistic expressions in several ways. A shift could be observed from using the alphabet to signs and symbols impacting the youth's academic and formal linguistic expression in educational institutes.

Ragam Bahasa Slang Pada Kata “Well”

In the 21st century, there are many uses of new and foreign language terms, not even a few of these language terms have become normalized or normalized by the community for use in everyday life. The problem contained in this study is that the use of the slang term "well" is more dominantly used on social media, especially on social media tiktok and especially young people who tend to understand more about the term "well" slang. The purpose of this research is to find out why in the 21st century people, especially young people, are more interested in using the slang term "well" for everyday use and especially in social media tiktok. And also to invite or get used to using Indonesian more often . The method used in this research is qualitative data. The results of this study are to prove why the younger generation is more likely to use and understand more the Indonesian language in social media because Indonesian itself is an identity for citizenship. Based on the results of research that in the 21st century, people, especially the younger generation, are more comfortable and easier to understand the slang term "well".

AI-based analysis of social media language predicts addiction treatment dropout at 90 days.

The reoccurrence of use (relapse) and treatment dropout is frequently observed in substance use disorder (SUD) treatment. In the current paper, we evaluated the predictive capability of an AI-based digital phenotype using the social media language of patients receiving treatment for substance use disorders (N = 269). We found that language phenotypes outperformed a standard intake psychometric assessment scale when predicting patients' 90-day treatment outcomes. We also use a modern deep learning-based AI model, Bidirectional Encoder Representations from Transformers (BERT) to generate risk scores using pre-treatment digital phenotype and intake clinic data to predict dropout probabilities. Nearly all individuals labeled as low-risk remained in treatment while those identified as high-risk dropped out (risk score for dropout AUC = 0.81; p < 0.001). The current study suggests the possibility of utilizing social media digital phenotypes as a new tool for intake risk assessment to identify individuals most at risk of treatment dropout and relapse.

Analysis of YouTube videos on hydrocephalus in the local language: matching content with the needs of caregivers.

Studies that evaluate YouTube videos on hydrocephalus often exclude non-English-language videos, even though hydrocephalus is more prevalent in low- and middle-income countries where English may not be widely understood. This study had two aims: to analyze the engagement, content, and quality of YouTube videos on hydrocephalus in the Filipino language, and to determine whether the videos' content matched the information needs of caregivers of children with hydrocephalus in the Philippines. The authors conducted an online survey among caregivers of patients with hydrocephalus, recruited through the Facebook page of the Hydrocephalus Foundation of the Philippines Inc. Data on demographics, social media use, and language and content preferences were collected. In parallel, the authors systematically evaluated the engagement and content of three groups of YouTube videos on hydrocephalus: 1) most viewed Filipino-language videos, 2) most viewed English-language videos, and 3) same-age English-language videos, matched to the first group based on upload date. The quality of the Filipino-language videos was assessed using the DISCERN criteria. Among 280 respondents, 91% watched videos on hydrocephalus online and 89% preferred videos in Filipino. Compared with same-age English videos, Filipino videos had greater engagement, indicated by a higher median number of likes (40 vs 8, p = 0.005) and comments (8.5 vs 1, p = 0.007). English and Filipino videos emphasized similar topics on hydrocephalus, but the latter were more likely to discuss treatment cost and to solicit donations. Caregivers were most interested in the long-term care of patients with hydrocephalus, discussed only in 10 of 72 videos (14%) overall. The mean DISCERN score for Filipino videos was 30.1 ± 7.7, indicating poor quality. There is a gap between the information needs of Filipino caregivers and the content of YouTube videos on hydrocephalus. Neurosurgeons can serve as creators, resource persons, or curators of content, ensuring that up-to-date, accurate, and credible health information on hydrocephalus is available to caregivers in their preferred language.

On the Culture of Speech of Social Networks

This article will focus on the culture of the language of social networks. Currently, starting from linguists to the intelligentsia in general, the alarm has begun to sound in the media regarding the language culture in social networks. After all, with intensive use of the social network, situations often arise on the Internet when the language culture is not supported. The article will focus on the culture of language in the social network, factors that negatively affect it, polite speech and contradictory concepts of verbal aggression (rudeness), trolling, cyberbullying. This article is devoted to the linguistic features of social network. These language features include the extensive use of foreign vocabulary and slang words. Both groups of words are actively used in forming a single phenomenon of communication. Like any language, the language of social media includes both literary vocabulary and limited areas of use: slang and jargon. The main difference is that the main part of foreign lexemes repeats new concepts that do not exist in the Kazakh and Russian languages. Most of the words that have become popular among Internet users are Americanisms. Analysis of the vocabulary of social networks shows that this process is only intensifying. The ways of manifestation of each of the listed features, the influence on language levels will be discussed. Scientific consideration of these issues will be reflected in the language practice of social networks.

The problem of varying annotations to identify abusive language in social media content

Abstract With the increase of user-generated content on social media, the detection of abusive language has become crucial and is therefore reflected in several shared tasks that have been performed in recent years. The development of automatic detection systems is desirable, and the classification of abusive social media content can be solved with the help of machine learning. The basis for successful development of machine learning models is the availability of consistently labeled training data. But a diversity of terms and definitions of abusive language is a crucial barrier. In this work, we analyze a total of nine datasets—five English and four German datasets—designed for detecting abusive online content. We provide a detailed description of the datasets, that is, for which tasks the dataset was created, how the data were collected, and its annotation guidelines. Our analysis shows that there is no standard definition of abusive language, which often leads to inconsistent annotations. As a consequence, it is difficult to draw cross-domain conclusions, share datasets, or use models for other abusive social media language tasks. Furthermore, our manual inspection of a random sample of each dataset revealed controversial examples. We highlight challenges in data annotation by discussing those examples, and present common problems in the annotation process, such as contradictory annotations and missing context information. Finally, to complement our theoretical work, we conduct generalization experiments on three German datasets.

Cognitive Linguistics Explains What Happened to the Russian Tank

Usage-based models that underlie cognitive approach to language and grammar imply investigation of language as a dynamic tool used in interpersonal communication rather than as an abstract system of signs. Hence the linguists’ interest in the language of social and mass media, with its focus upon real current situations and events. One of such events, reported by journalists and widely commented upon, was an incident that occurred in Ukraine shortly after the Russian invasion of 24 February 2022. In one of the villages in the battle zone a group of Ukrainian civilians seized a tank from the Russian army. In the internet, the news soon became a hit and was translated into several languages.Focusing upon Polish, the analysis presented in the paper will show the relation between the form of those messages and their epistemological value. In the case study I will use the concept of the linguistic worldview combined with that of conceptual integration, thus substantiating the claim that theoretical framework offered by Cognitive Linguistics can be profitably used to describe, to optimize and to operationalize acts of linguistic communication.

Opioid death projections with AI-based forecasts using social media language

Targeting of location-specific aid for the U.S. opioid epidemic is difficult due to our inability to accurately predict changes in opioid mortality across heterogeneous communities. AI-based language analyses, having recently shown promise in cross-sectional (between-community) well-being assessments, may offer a way to more accurately longitudinally predict community-level overdose mortality. Here, we develop and evaluate, TrOP (Transformer for Opiod Prediction), a model for community-specific trend projection that uses community-specific social media language along with past opioid-related mortality data to predict future changes in opioid-related deaths. TOP builds on recent advances in sequence modeling, namely transformer networks, to use changes in yearly language on Twitter and past mortality to project the following year’s mortality rates by county. Trained over five years and evaluated over the next two years TrOP demonstrated state-of-the-art accuracy in predicting future county-specific opioid trends. A model built using linear auto-regression and traditional socioeconomic data gave 7% error (MAPE) or within 2.93 deaths per 100,000 people on average; our proposed architecture was able to forecast yearly death rates with less than half that error: 3% MAPE and within 1.15 per 100,000 people.

The language of social media contests: A lexical analysis of contests across social platforms

Contests play an important role in social media content created and facilitated by users generally, and by brands and marketers specifically, in the drive for continued communicative engagement and online participation. This study assesses the language of social media contests by capturing more than 30,000 social media posts relating to contests, and performing a lexical analysis on them to identify major linguistic themes. The findings reveal a mixture of persuasive language tropes, gratitude linkages and platform-specific behaviour across social media contest posts. Implications include the utilisation of social contest language for brand strategy.

What’s so Social about Facebook? Distant Reading of Swedish Local Government Facebook Pages, 2010-2017

ABSTRACT Social media, particularly its more social aspects, can be challenging for organizations. In this article local governments’ communication on Facebook is used as a case study and analyzed through a mixed methods approach, utilizing distant and close readings of 50,000 Facebook posts from 23 Swedish local governments. The aim is to investigate patterns in both content and style with a particular focus on social interaction, drawing on a neo-institutional approach and the idea that communication can play an explicit social function. The findings suggest that local governments used Facebook mainly to inform citizens, whereas dialogue and discussion were directed elsewhere. When local governments translate social media into practice, it seems to be done in line with established channels and ways of communicating. These findings underline the need to understand local governments’ use of social media in relation to concepts such as openness and control, where attempts are made to control an uncontrollable online environment. Another key finding is that local governments seemed to post when there was very little or nothing to say; they posted about the mundane, trivial, and ordinary. These findings indicate an adaptation of the language and discourse of social media which contrasts with bureaucratic language.

Sensing Psychological Well-being Using Social Media Language: Prediction Model Development Study.

Positive mental health is arguably increasingly important and can be revealed, to some extent, in terms of psychological well-being (PWB). However, PWB is difficult to assess in real time on a large scale. The popularity and proliferation of social media make it possible to sense and monitor online users' PWB in a nonintrusive way, and the objective of this study is to test the effectiveness of using social media language expression as a predictor of PWB. This study aims to investigate the predictive power of social media corresponding to ground truth well-being data in a psychological way. We recruited 1427 participants. Their well-being was evaluated using 6 dimensions of PWB. Their posts on social media were collected, and 6 psychological lexicons were used to extract linguistic features. A multiobjective prediction model was then built with the extracted linguistic features as input and PWB as the output. Further, the validity of the prediction model was confirmed by evaluating the model's discriminant validity, convergent validity, and criterion validity. The reliability of the model was also confirmed by evaluating the split-half reliability. The correlation coefficients between the predicted PWB scores of social media users and the actual scores obtained using the linguistic prediction model of this study were between 0.49 and 0.54 (P<.001), which means that the model had good criterion validity. In terms of the model's structural validity, it exhibited excellent convergent validity but less than satisfactory discriminant validity. The results also suggested that our model had good split-half reliability levels for every dimension (ranging from 0.65 to 0.85; P<.001). By confirming the availability and stability of the linguistic prediction model, this study verified the predictability of social media corresponding to ground truth well-being data from the perspective of PWB. Our study has positive implications for the use of social media to predict mental health in nonprofessional settings such as self-testing or a large-scale user study.

Digital Technologies, Social Media, Global and Local Languages in Southeast Asia

This article aligns with the theme, “Overcoming Adversity, Embracing Change: Addressing Challenges in Language and Culture in Asia”, and with the call for papers for this conference. It takes an optimistic but critical stand on questions of digital technologies, including social media in multilingual societies. The telephone, radio, television and more recently the internet were all in their turn (wrongly) seen as heralding the demise of normal face-to-face communication, and as threatening the continued existence of minority indigenous languages in multilingual nations. But the Chinese traditional saying, “A crisis is an opportunity riding a dangerous wind”, remains relevant in the pandemic and post-pandemic era. Technologies are not in themselves language-specific, nor are they necessarily biased towards powerful, global languages. Social media platforms such as WhatsApp, Instagram and others do not force users to shift towards Spanish, Mandarin, Arabic or English. I discuss examples of mixed language use in Southeast Asian social media contexts, taking up the point raised by Deterding (2020, 175) in his article based on his keynote presentation at the previous conference in this series: “perhaps trying to analyse the different languages in Brunei as distinct entities is flawed. In the modern globalised world, languages no longer belong in distinct boxes that can be neatly labelled”. The key argument is that the mixing of local vernacular and powerful global languages does not necessarily signal an impending language shift. On the contrary, such hybrid discoursal practices in social media may be viewed as a minority language maintenance and survival strategy.

Social Media Language Offers Insights Into Cognitive and Social Processes: a Review and Agenda for the Future

Social Media Language Offers Insights Into Cognitive and Social Processes: a Review and Agenda for the Future

Uncovering Factors Influencing Millennials’ Use of Non-Standard Words in Twitter

Social media communication has its own language features and one aspect is modified spelling of standard words. Social media users use shortened words with full awareness of the meanings, and new non-standard words are constantly added to the repertoire of social media language. A pertinent question is whether social media users learn these non-standard words to use or whether they also contribute to the vocabulary used in social media communication. The study examined Malaysian millennials’ use of non-standard words in Twitter and their reasons for shortening words. For the non-standard words, data were collected from 200 active Twitter users whereas data on reasons for shortening words were collected from 30 users. The results showed that the Malaysian millennials frequently used non-standard spelling of words. The three top words were “ni” (this), “nak” (want), and X (negation). The main reasons for the Twitter users to shorten words were the 280-character limit per tweet, user convenience, and characteristics of words. The Twitter users felt free to create new spellings of standard words at times for fun, but most of the time, they use the common non-standard words. The Malaysian millennials reported that they were inclined to shorten long and complex words, and words with many vowels. The study suggests that Twitter users balance between speed in communication and preservation of meaning when using non-standard words. Keywords: Social media, Twitter, non-standard words, word formation processes, shortening of words.

Social Media and COVID -19 Pandemic: Accelerating the Learning of English as a Foreign Language (EFL)

COVID-19 began in China (2019) and spread to other nations and become a world pandemic (2020). The news media and social media platforms have played an important role in information dissemination about the Coronavirus throughout the world. During COVID-19 Pandemic, social media has become a key tool for enhancing social networking and information sharing via the web. As more people turn to the internet for health information, social media platforms are helping to spread life-saving precautions that individuals, families, and communities may take to reduce their chance of contracting the virus. Language learners are linked to interactive social media platforms in Social Media Language Learning. The goal of this study was to look at the role of social media during COVID in foreign language acquisition. The participants in this study were Saudi Arabian college students. The study’s sample comprised 200 (n=200) college students, and the social media platforms investigated included Facebook, Instagram, Twitter, LinkedIn, Youtube, WhatsApp, Telegram, Snapchat and other platforms. Questionnaires were used to collect the data. The results indicated that the students used various social media platforms in order to get the appropriate information about the virus which indirectly helped and motivated them to learn a new language. These learners lack the self-motivation needed to use social media to develop their English language abilities. The study discovered that adopting online social media during a pandemic for English language learning had a significant impact on interactions with peers and teachers.

Synthesis of Affective Expressions and Artificial Intelligence to Discover Mental Distress in Online Community.

Looking at the rapidity the social media has gained ascendancy in the society, coupled with considerable shortage of addressing the health of the social media users, there is a pressing need for employing mechanized systems to help identify individuals at risk. In this study, we investigated potential of people's social media language in order to predict their vulnerability towards the future episode of mental distress. This work aims to (a) explore the most frequent affective expressions used by online users which reflect their mental health condition and (b) develop predictive models to detect users with risk of psychological distress. In this paper, dominant sentiment extraction techniques were employed to quantify the affective expressions and classify and predict the incident of psychological distress. We trained a set of seven supervised machine learning classifiers on logs crowd-sourced from 2500 Indian Social Networking Sites (SNS) users and validated with 3149 tweets collected from Indian Twitter. We test the model on these two different SNS datasets with different scales and ground truth labeling method and discuss the relationship between key factors and mental health. Performance of classifiers is evaluated at all classification thresholds; accuracy, precision, recall, F1-score. and experimental results show a better traction of accuracies ranging from ~ 82 to ~ 99% as compared to the models of relevant existing studies. Thus, this paper presents a mechanized decision support system to detect users' susceptibility towards mental distress and provides several evidences that it can be utilized as an efficient tool to preserve the psychological health of the social media users.

Addressing religious hate online: from taxonomy creation to automated detection.

Abusive language in online social media is a pervasive and harmful phenomenon which calls for automatic computational approaches to be successfully contained. Previous studies have introduced corpora and natural language processing approaches for specific kinds of online abuse, mainly focusing on misogyny and racism. A current underexplored area in this context is religious hate, for which efforts in data and methods to date have been rather scattered. This is exacerbated by different annotation schemes that available datasets use, which inevitably lead to poor repurposing of data in wider contexts. Furthermore, religious hate is very much dependent on country-specific factors, including the presence and visibility of religious minorities, societal issues, historical background, and current political decisions. Motivated by the lack of annotated data specifically tailoring religion and the poor interoperability of current datasets, in this article we propose a fine-grained labeling scheme for religious hate speech detection. Such scheme lies on a wider and highly-interoperable taxonomy of abusive language, and covers the three main monotheistic religions: Judaism, Christianity and Islam. Moreover, we introduce a Twitter dataset in two languages-English and Italian-that has been annotated following the proposed annotation scheme. We experiment with several classification algorithms on the annotated dataset, from traditional machine learning classifiers to recent transformer-based language models, assessing the difficulty of two tasks: abusive language detection and religious hate speech detection. Finally, we investigate the cross-lingual transferability of multilingual models on the tasks, shedding light on the viability of repurposing our dataset for religious hate speech detection on low-resource languages. We release the annotated data and publicly distribute the code for our classification experiments at https://github.com/dhfbk/religious-hate-speech.