Accessible Social Media Research Articles

Suicide thoughts screening with social media using cat swarm-intelligent adaptive recurrent network

The research on detecting suicidal ideation through social media in early stages and faces several difficulties. Many persons with a propensity for suicide express their ideas and beliefs on social media. Numerous studies have found that accessible social media posts have useful criteria for rapidly identifying people thosewho are considering suicide. Finding and comprehending the risk factors and warning signals that may lead to suicide, is the most challenging aspect of suicide prevention. By automatically detecting the abrupt changes in a user behavior, this can be accomplished. Social media interactions can be used to gather textual and behavioral data using natural language processing (NLP) techniques. The framework can use this data to spot trends in social interactions that point to suicide intent. We can anticipate suicidal ideation using classification techniques based on deep learning. We can accomplish this by identifying these emotions in user postings using a combination of Cat Swarm-Intelligent Adaptive Recurrent Network (CSI-ARN) models. Adding extra training data and using an attention model to improve model performance can increase accuracy. This study examines social media comments for suicidal thoughts using a CSI-ARN model. The suggested model outperformed baseline models with 90.3% accuracy and 92.6% F1-score.

Persepsi Remaja Generasi Z Tentang Kesiapan Menikah Dan Keselarasan Kebijakan Pernikahan Authors

Generation Z teenagers are those born from 1995 to 2010 in the era of modern digitalization. Meanwhile, policy makers and implementers for generation Z teenagers in the pre-marital youth program are generations X and Y, those who live in the era of the digital revolution. These generations have different characters. The aim of this research is to determine the perspective of generation Z teenagers regarding marriage readiness with the alignment of marriage policies. This research method is a cross-sectional study with the subjects of generation Z teenagers, namely 360 students from the Faculty of Medicine, Brawijaya University, officers from the Office of Religious Affairs (KUA), health workers and sub-district officers. The research was carried out in the Lowokwaru area of Malang City. This research uses Google forms, interviews and observations. The results of this research showed that 50.00% of teenagers were not ready to marry. Pre-marital youth programs at the Department of Religion and Community Health Centers already exist but are not implemented well. The educational method used is still conventional, not using easily accessible social media. It is recommended that pre-marriage programs for generation Z teenagers can be synergistic between the Department of Religion and Community Health Centers. For further research, we can initiate website-based consultation and education applications for teenagers.

Exploring X: barriers to care for eosinophilic esophagitis.

Patients with chronic diseases have increasingly turned to social media to discuss symptoms and share the challenges they face with disease management. The primary aim of this study is to use naturally occurring data from X (formerly known as Twitter) to identify barriers to care faced by individuals affected by eosinophilic esophagitis (EoE). For this qualitative study, the X application programming interface with academic research access was used to search for posts that referenced EoE between 1 January 2019 and 10 August 2022. The posts were identified as being either related to barriers to care for EoE or not. Those related to barriers to care were further categorized by the type of barrier that was expressed. A total of 8636 EoE-related posts were annotated of which 12.1% were related to barriers to care in EoE. The themes that emerged about barriers to care included: dietary challenges, limited treatment options, lack of community support, lack of physician awareness of disease, misinformation, cost of care, lack of patient belief in disease or trust in physician, and limited access to care. Saturation of themes was achieved. This study highlights barriers to care in EoE using readily accessible social media data that is not derived from a curated research setting. Identifying these obstacles is key to improving care for this chronic disease.

Seq2Set2Seq: A Two-stage Disentangled Method for Reply Keyword Generation in Social Media

Social media produces large amounts of content every day. How to predict the potential influences of the contents from a social reply feedback perspective is a key issue that has not been explored. Thus, we propose a novel task named reply keyword prediction in social media, which aims to predict the keywords in the potential replies in as many aspects as possible. One prerequisite challenge is that the accessible social media datasets labeling such keywords remain absent. To solve this issue, we propose a new dataset, 1 to study the reply keyword prediction in social media. This task could be seen as a single-turn dialogue keyword prediction for open-domain dialogue system. However, existing methods for dialogue keyword prediction cannot be adopted directly, which has two main drawbacks. First, they do not provide an explicit mechanism to model topic complementarity between keywords which is crucial in social media to controllably model all aspects of replies. Second, the collocations of keywords are not explicitly modeled, which also makes it less controllable to optimize for fine-grained prediction since the context information is much less than that in dialogue. To address these issues, we propose a two-stage disentangled framework, which can optimize the complementarity and collocation explicitly in a disentangled fashion. In the first stage, we use a sequence-to-set paradigm via multi-label prediction and determinantal point processes, to generate a set of keyword seeds satisfying the complementarity. In the second stage, we adopt a set-to-sequence paradigm via seq2seq model with the keyword seeds guidance from the set, to generate the more-fine-grained keywords with collocation. Experiments show that this method can generate not only a more diverse set of keywords but also more relevant and consistent keywords. Furthermore, the keywords obtained based on this method can achieve better reply generation results in the retrieval-based system than others.

Michael Swan's Poems in Translation on Social Media – An Exercise in Rendering Poetic Images and Encouraging Translating Communities

Translating poetry is an exercise that stimulates both the cognitive and the emotional potentialities of students. Poetic texts are the essence of what poets thought and are therefore more difficult to decipher given the minimal linguistic input. The present study is the result of the work with two groups of students who had classes online during the coronavirus pandemic. Facebook as an accessible social media platform proved to be a great hub for launching the challenge of translating poetry and having students post their versions of translations. Their work was thus exposed to the assessment and appreciation of their fellow students who became thus part of a translating community. The poems chosen for this exercise in translation were selected from Michael Swan’s volume tiger dreams/ vise cu tigri POEMS/ POEME. The bilingual edition appeared at Niculescu Publishing House Romania and served as a consistent basis for the translation practice with the students from the “Alexandru Ioan Cuza” University of Iași who were specializing in Applied Linguistics - Translation and Interpreting. The resulting versions of the texts prove that language in poetry is pulsating with meaning anchored in the reality of the author’s imagination and in the translators’ efforts to mediate that reality and make it accessible to the contemporary public.

Social media usage in industrial markets: An examination of technopark companies in Turkey

This study examines the extent to which companies operating within the technology park, ranked in the top 3 in Turkey according to the performance index, utilise social media marketing. The research explores the level of their engagement, the platforms they leverage, and their relative activity across these platforms. Furthermore, a profile has been delineated specifically for companies in technology-intensive industrial markets. Out of the 1121 companies accessed on their websites, it was observed that 55% of them had added redirects to their social media accounts. Among the 615 companies with accessible social media accounts, it was noted that 102 of them had profiles on Facebook, Instagram, Linked In, YouTube, and X. On the other hand, it has been found that the percentages of companies sharing content on their social media accounts at least one year ago are noteworthy (Among firms using YouTube 33.3%, Facebook 5.9%, and X 33.7%). This study offers perspectives for academic circles and practitioners through analyses of the involvement levels of firms operating in a business-to-business context in social media marketing and the platforms they utilise.

Examining Social Media Policy and Records Management in Massachusetts Municipal Governments

ABSTRACTThis paper reports on an exploratory analysis of the social media policies of municipal governments in the Commonwealth of Massachusetts. With a strong Public Records law and language clearly indicating that social media posts are government records, Massachusetts provides a framing for research into municipal policy on social media use, retention, preservation, and access. Of the 351 municipalities in the Commonwealth, just 87 have publicly accessible Social Media policies. These policies indicate that municipal governments take their responsibilities around social media records management seriously, they do not offer many specifics around how they will engage directly with posts from privately‐owned social media platforms. Implications of these findings suggest that the digital preservation community must continue to develop tools and methods to preserve social media records the support broader efforts around government transparency and accountability, as well as advocate for platforms to include features to support responsible public sector social media use.

Consumer sentiment toward international activist advertising

Companies have been increasingly conveying activist advertising messages to international audiences in response to persisting social ills and unsustainable business practices. Given the ambiguity surrounding the effects of international advertising, this study aims to compare the response of local consumers to a multinational brand’s standardized activist advertising strategy with creative executions adapted to the national contexts of Greece and the USA. The selected brand originates from the USA. The paper used a systematic qualitative approach and sentiment analysis using Microsoft Excel and Azure Machine Learning add-in. Analysis conducted on 1,051 user comments in January 2023 regarding two publicly accessible social media posts of a multinational haircare brand showed both similarities and differences in consumer responses. 662 comments were in English and 389 comments were in Greek. The study’s dataset was anonymized entirely and de-identified. The results indicate that consumer sentiment was largely negative in both countries. Although the relative share of negative comments was significantly higher in the USA (96.7%) than in Greece (59.4%), both groups of consumers placed their emphasis on the same themes (e.g., children and products). Therefore, they have perceived the main message similarly, irrespective of the execution differences. Overall, the findings can be attributed to strategic and tactical issues of the activist advertising campaign, as well as to sociocultural particularities of the national context. In the case of international advertising, attempts to incorporate the brand’s stance on a controversial sociopolitical issue into its advertising strategy pose significant risks to business organizations.

Civic Life in the Digital Space of Pre-Service Teachers

This research investigates the profile and perceptions of respondents towards widely accessible social media platforms to identify key considerations in transforming online engagement into actual civic action. Quantitative in design, the survey of the descriptive method of research is used adopting the developed questions for the study of the United Nations Development Programme on young activists in 2021 to assess the digital engagement of 118 pre-service teachers randomly selected through the multistage sampling method. Utilizing descriptive statistics, social media platforms providing greater opportunities for self-expression such as Facebook and Tiktok are found frequently used for creating and sharing content related to education, and health. Respondents concurred on widespread disinformation online and the complementary nature of civic engagement. Despite the manifested lack of trust and reservations due to the risk of data surveillance and breach, the respondents consider social media platforms as enabling venues for civic engagement. Corresponding policies and programs that institute gender-inclusive, safe, and participatory venues in both digital and traditional forms are necessary means for supporting the youth as key players in nation-building.

Refining agent-based travel demand models using social media data

This work presents an approach for detecting localisable events from social media using machine learning techniques and how this information can be used in agent-based travel demand models. The approach allows for explicitly modelling irregular mobility patterns that emerge from incidences and events that gather more people as usual in certain locations, and thus, create deviating travel demands. The advantage of our approach is that it solely relies on publicly accessible social media data that can be analysed in real-time. The method is demonstrated along a case study on mapping the event-related mobility scene in Berlin (Germany).

Comparison of Literature Review, Social Media Listening, and Qualitative Interview Research Methods in Generating Patient-Reported Symptom and Functional Impact Concepts of Presbyopia.

To compare the insights obtained about the experience of individuals with presbyopia (age-related impaired near vision) across three different sources of qualitative data: a structured targeted literature review, a social media listening (SML) review, and qualitative concept elicitation (CE) interviews with individuals with presbyopia and healthcare professionals (HCPs). The number of concepts identified, depth of data, cost and time implications, and value of the patient insights generated were explored and compared for each method. Keywordsearches in bibliographic databases and review of abstracts identified 120 relevant publications; in-depth targeted literature review of the qualitative studies identified key symptoms/functioning concepts. SML was conducted using publicly accessible social media sources with focus on ophthalmologic diseases using a pre-defined search string. Relevant posts from individuals with presbyopia (n = 270) were analysed and key concepts identified. Semi-structured CE interviews were conducted with individuals with presbyopia (US n = 30, Germany n = 10, France n = 10), and HCPs (US = 3, France n = 2, Germany n = 1, Japan n = 1) who were experienced in treating presbyopia. Verbatim transcripts were coded using thematic analysis. A conceptual model summarised concepts identified across sources RESULTS: Out of the total of 158 concepts identified across the three sources, qualitative CE interviews yielded the highest number of concepts (n = 151/158, 96%), with SML yielding a third of the concepts (n = 51/158, 32%) and the literature review yielding the fewest concepts (n = 33/158, 21%). Qualitative CE interviews provided greater depth of data than SML and literature reviews. SML and literature reviews were less costly and quicker to run than qualitative CE interviews and also were less burdensome for participants. Qualitative CE interviews are considered the gold standard in providing greater depth of understanding of the patient experience, and more robust data. However, research requirements, budget, and available time should be considered when choosing the most appropriate research method. More time and cost-effective SML and literature review methods can be used to supplement qualitative CE interview data and provide early identification of measurement concepts. More research and regulatory guidance into less traditional qualitative methods, however, are needed to increase the value of SML and literature review data.

Sentiment Analysis of Weather-Related Tweets from Cities within Hot Climates

Abstract Evidence exists that exposure to weather hazards, particularly in cities subject to heat island and climate change impacts, strongly affects individuals’ physical and mental health. Personal exposure to and sentiments about warm conditions can currently be expressed on social media, and recent research noted that the geotagged, time-stamped, and accessible social media databases can potentially be indicative of the public mood and health for a region. This study attempts to understand the relationships between weather and social media sentiments via Twitter and weather data from 2012 to 2019 for two cities in hot climates: Singapore and Phoenix, Arizona. We first detected weather-related tweets, and subsequently extracted keywords describing weather sensations. Furthermore, we analyzed frequencies of most used words describing weather sensations and created graphs of commonly occurring bigrams to understand connections between them. We further explored the annual trends between keywords describing heat and heat-related thermal discomfort and temperature profiles for two cities. Results showed significant relationships between frequency of heat-related tweets and temperature. For Twitter users exposed to no strong temperature seasonality, we noticed an overall negative cluster around hot sensations. Seasonal variability was more apparent in Phoenix, with more positive weather-related sentiments during the cooler months. This demonstrates the viability of Twitter data as a rapid indicator for periods of higher heat experienced by public and greater negative sentiment toward the weather, and its potential for effective tracking of real-time urban heat stress. Significance Statement Social media such as Twitter allow individuals to broadcast their opinions in real time, including perceptions and sensations related to weather events. Evidence from two cities exposed to hot weather—one equatorial and one desert subtropical—indicates that tweets were sensitive to seasonal temperature differences even within a small range. For Twitter users exposed to no strong temperature seasonality, generally negative sentiments to hot weather were seen year-round. In Phoenix with more pronounced seasonality, tweets were more positive in sentiment during the cooler months. This result shows promise for the medium as a rapid real-time indicator—or a snapshot—for societal sentiment to weather events.

Semiotic Analysis Of Wardah Beauty Moves You Ads Through Youtube Media


 This study discusses the Semiotic Analysis of Wardah Beauty Moves You advertisements which aired through the Wardah Beauty YouTube channel published since October 2021 with a duration of 60 seconds. With the development of technology, YouTube has become one of the most practical and easily accessible social media, so that it becomes the most popular site and is watched by thousands of people every day. The advertisement emphasizes that women's beauty can be a driving force for change that can have an impact and benefit on the environment. This study aims to determine the representation of symbols and meanings of beauty in Wardah Beauty Moves You advertisement, using a qualitative approach with virtual ethnographic methods. Researchers analyzed advertisements by collecting data from YouTube and then taking pictures of several scenes related to the meaning of beauty in the advertisement. The results of this study indicate that the representation of the symbol of beauty in the advertisement is showing Dewi Sandra as Wardah's brand ambassador who can represent the beauty of Indonesian women. The meaning of women's beauty is that they are capable of driving change according to the ad's tagline, namely #BeautyMovesYou. The beauty of women shown in advertisements is not monotonous in terms of beauty standards for Indonesian women in general, namely having white skin and long straight hair. However, the advertisement wants to show that in fact beauty is not only physical beauty. The meaning of beauty varies depending on the perspective of people.

Co-Development of a Web Application (COVID-19 Social Site) for Long-Term Care Workers ("Something for Us"): User-Centered Design and Participatory Research Study.

BackgroundImproving confidence in and uptake of COVID-19 vaccines and boosters among long-term care workers (LTCWs) is a crucial public health goal, given their role in the care of elderly people and people at risk. While difficult to reach with workplace communication interventions, most LTCWs regularly use social media and smartphones. Various social media interventions have improved attitudes and uptake for other vaccines and hold promise for the LTCW population.ObjectiveWe aimed to develop a curated social web application (interactive website) to increase COVID-19 vaccine confidence (a 3-arm randomized trial is underway).MethodsFollowing user-centric design and participatory research approaches, we undertook the following 3 steps: (1) content identification, (2) platform development, and (3) community building. A LTCW and stakeholder advisory group provided iterative input. For content identification (step 1), we identified topics of concern about COVID-19 vaccines via desktop research (published literature, public opinion polls, and social media monitoring), refined by interviewing and polling LTCWs. We also conducted a national online panel survey. We curated and fact-checked posts from popular social media platforms that addressed the identified concerns. During platform development (step 2), we solicited preferences for design and functionality via interviews and user experience testing with LTCWs. We also identified best practices for online community building (step 3).ResultsIn the interviews (n=9), we identified 3 themes: (1) LTCWs are proud of their work but feel undervalued; (2) LTCWs have varying levels of trust in COVID-19–related information; and (3) LTCWs would welcome a curated COVID-19 resource that is easy to understand and use-"something for us". Through desktop research, LTCW interviews, and our national online panel survey (n=592) we found that participants are interested in information about COVID-19 in general, vaccine benefits, vaccine risks, and vaccine development. Content identification resulted in 434 posts addressing these topic areas, with 209 uploaded to the final web application. Our LTCW poll (n=8) revealed preferences for personal stories and video content. The platform we developed is an accessible WordPress-based social media web application, refined through formal (n=3) and informal user experience testing. Users can sort posts by topic or subtopic and react to or comment on posts. To build an online community, we recruited 3 LTCW “community ambassadors” and instructed them to encourage discussion, acknowledge concerns, and offer factual information on COVID-19 vaccines. We also set “community standards” for the web application.ConclusionsAn iterative, user-centric, participatory approach led to the launch of an accessible social media web application with curated content for COVID-19 vaccines targeting LTCWs in the United States. Through our trial, we will determine if this approach successfully improves vaccine confidence. If so, a similar social media resource could be used to develop curated social media interventions in other populations and with other public health goals.

Analyzing Public Concerns Over COVID-19 Variants Using Social Media

SARS-CoV-2, or more popularly known COVID-19 has claimed more than 5.5 million lives since it has been declared as a global pandemic. Similar to other viruses, COVID-19 is also undergoing several mutations and has many variants like Alpha, Beta, Gamma, Delta, Omicron and others. With so many variants, social media users are confused and posting their frustrations and angers with Tweets or Posts in public social media platforms. These publicly accessible social media posts provide a wealth of information for a social scientist or political leader or a strategic decision maker. This study demonstrates a feasible approach to extract meaningful critical information from social media posts. By programmatically accessing Twitter database from 11th January 2022 till 20th January 2022, we retrieved almost 9 K Tweet messages on 6 different keywords like “COVID Variants”, “Omicron”, “Alpha Variant”, “Beta Variant”, “Gamma Variant” and “Delta Variant”. Results were compared against metrics like users, posts, engagement, and influence. Omicron was found to be the most popular topic compared to other variants with an influence score of 70.2 million and 2.1 K posts during the monitored period. The most popular sources for influences on COVID-19 Variant related posts were found to be @reuters with 24.2M, @forbes with 17.4M, @timesofindia with 14.2M and @inquirerdotnet with 3.4 followers. This study also found out that the most popular Tweet languages were English followed by French and Dutch. Lastly, this study ranked user mentions, word frequency (with word cloud) and hashtags for COVID-19 Variant related twitter posts during the monitored timeframe.

How Non-profit Art Spaces in Hanoi, Vietnam, used Facebook to Communicate, Exhibit and Promote Art and Culture During the Closure of Physical Spaces

The Covid-19 Pandemic has changed the nature and importance of arts communication, exhibition and promotion via social media. However, moving fully online has highlighted global inequalities in digital inclusion and access, with inherent biases towards content from the West and larger cultural institutions with sufficient technical, human and financial resources in order to survive through the Covid-19 Pandemic. This paper investigates how non-profit art spaces in Hanoi, Vietnam, developed their use of Facebook for effective communication, exhibition and promotion of Vietnamese art and culture during the first closure of physical premises. With the shift of all work online due to Covid-19 Pandemic social distancing measures, Facebook provided non-profit art spaces with a viable digital solution at a time of increased pressure to connect with the audience. Facebook provided a way to overcome challenges faced by non-profit art spaces with lack of financial, human and technical resources, by providing a free and widely accessible social media platform. The current study draws upon a digital ethnography of Facebook posts over 2 months and 50 semi-structured interviews with cultural professionals in Hanoi. The findings highlight changes in the use of Facebook, the digital strategies that were created for working fully online, and how art spaces maintained connection with the audience during the closure of physical premises between March and April 2020. This study identifies changes in social media usage patterns in three main ways: 1) the introduction of using Facebook for digital exhibition and holding live events, 2) changes in type of promotional content, and 3) changes in communication style with the introduction of an effective rhetoric of care. Together, the findings highlight changes in the nature and importance of arts communication, exhibition and promotion via social media in the cultural sector due the Covid-19 Pandemic. Developments over this time could help provide a sustainable solution to overcome challenges faced in the cultural sector in Vietnam and overcome global inequalities in access and inclusion online.

Violence against healthcare workers during coronavirus (COVID-19) pandemic in Egypt: a cross-sectional study

BackgroundHealthcare workers are on the front lines of COVID-19 and are subject to risks. A rise in the cases of violence and aggressiveness against HCWs has been observed worldwide, adding to the already existing burnout. The purpose of this research is to determine the prevalence of workplace violence, its risk variables, and the pattern of violence directed towards healthcare workers in the context of COVID-19 pandemic. The research used a cross-sectional analytic design. Purposive sampling was utilized to identify research participants using an online survey. Form’s link was distributed to accessible social media groups such as Facebook and WhatsApp from July 2020 to the end of October 2020. A self-administered structured survey was adapted from the World Health Organization survey questionnaire about violence in healthcare settings. The Google Form’s link was distributed to the social media groups until the total sample of 405 was collected.ResultsDuring the COVID-19 pandemic, workplace violence against Egyptian healthcare workers was prevalent (63.2%). The most prevailing type of violence among the exposed participants was verbal violence (87.9%). Violence is more common in the (< 40 years old) age group (80.9% of exposed healthcare workers). Violence was more statistically significant against females (60.5% of the exposed healthcare workers) (p-value = 0.023). Regarding the work specialty, violence was more committed against physicians (84.3% of exposed healthcare workers) than nurses (12.8% of exposed healthcare workers). The primary perpetrators of violence were the patient’s family (74.6%). The majority of the exposed HCWs (96%) reported no physical injury from the violent event, and 71.5% deemed the violent incident preventable. The majority (90.6%) of HCWs exposed to violent incidents declared non-reporting.ConclusionsEffective risk communication at all levels of society is critical for reducing fear, stigma, and ultimately workplace violence, as recent assaults on healthcare institutions demonstrate. To reduce violence and safeguard the safety of the medical profession, the government, health policymakers, media organizations, and community engagement groups must collaborate for healthcare workers’ safety.

A Survey of YouTube Videos as a Source of Useful/Unuseful Information in the Field of the Prevention and Management of Burn Injuries: A Cross-sectional Analysis of the English Language Content.

The study was designed on whether YouTube videos are useful as an information resource in the field of burn injury prevention and management. Current literature on the educational content and quality of burn-related first-aid videos on YouTube was reported as inadequate and inaccurate. However, the quality of YouTube videos on various medical and clinical topics has been the subject of many previous studies, and there has been increasing evidence that the content ratio of usefulness was higher than that of nonuseful. While hours and even minutes in burn injuries are as precious as gold in terms of outcomes, it would be a significant loss not to use the most popular and easily accessible free social media platform of our time as a tool that can contribute to the prevention of burns and raise awareness. Analysis was conducted with the remaining 96 videos from 240 videos obtained from YouTube, according to possible search terms and exclusion of videos according to predetermined criteria. The Global Quality Score (GQS) and modified DISCERN (m.DISCERN) tools were used to assess the quality and reliability of the videos. Viewer engagement metrics and video properties were also investigated according to the usefulness criteria (eg, video length, duration on YouTube, topic contents, source uploads, reliability, and quality). Finally, it was revealed that nearly 80% of the YouTube videos contained information in the field of the prevention and management of burn injuries deemed useful in this study, comparable to the other medical disciplines' reports in the literature.

Pengungkapan Diri di Situs Media Sosial Youtube

Social media is a rapidly growing phenomenon, not only a growing phenomenon in Indonesia. This development is certainly accompanied by the enthusiasm of the community and the existence of social media as a place of self-expression which is increasingly popular and easier to utilize. One of the most popular social media is YouTube. Youtube is a platform where users can upload, watch and share videos. This easily accessible social media platform makes its users come from all ages. This phenomenon is an opportunity for YouTube content creators to make self-disclosure or self-use which is often personal. Self-disclosure plays an important role in life and in the daily life of an individual does not escape the activity of self-disclosure. Researchers want to see the extent to which youtube users use social media as a means of self-disclosure. This research was conducted based on previous studies with similar cases.

Suggesting text alternatives for images in social media

Image description has been a recurrent topic on web accessibility over the years. With the increased use of social networks, this discussion is even more relevant. Social networks are responsible for a considerable part of the images available on the web. In this context, users are not only consuming visual content but also creating it. Due to this shared responsibility of providing accessible content, major platforms must go beyond accessible interfaces. Additional resources must also be available to support users in creating accessible content. Although many of today's services already support accessible media content authoring, current efforts still fail to properly integrate and guide their users through the authoring process. One of the consequences is that many users are still unaware of what an image description is, how to provide it, and why it is necessary. We present SONAAR, a project that aims to improve the accessibility of user-generated content on social networks. Our approach is to support the authoring and consumption of accessible social media content. Our prototypes currently focus on Twitter and Facebook and are available as an Android application and as a Chrome extension.