Social Media Comments Research Articles

Explore How to Refine Social Media Marketing Strategies and Shape Consumer Travel Preferences: An In-depth Study on Airbnb

In a post-COVID-19 era of digital transformation and a gradually recovering tourism economy, the travel industry must continually seek innovative ways to enhance social media marketing strategies and better understand consumer behaviour. This paper provides insights into how social media marketing strategy optimisation can shape consumer travel preferences. Using Airbnb as a case study, this paper analyses the social media comments of Airbnb users to reveal consumers' overall positive attitudes towards Airbnb's services through sentiment analysis and explore how methods such as predictive analytics can be used to tailor social media marketing campaigns to provide a more personalised and effective service to potential travellers. The results show that consumers are very concerned about whether the service experience differs from what is advertised on social media, such as quality of accommodation, customer service and pricing strategies. Therefore, Airbnb should prioritise consumer feedback, improve social media content quality, and use predictive analytics to identify its target audience. Future research should incorporate diverse data sources and advanced analytics techniques to understand consumer needs better, establish stronger customer connections, and influence travel choices.

Enhancing understanding of social media literacy to better inform prevention of body image and eating disorders

ABSTRACT Research has revealed an important role for appearance-focused, and in particular photo-based, social media in the development of body image and eating pathology. Social media literacy is a multifaceted construct involving purposeful selection and exposure to social media content and use of protective filtering (deliberately screening and interpreting information in a protective manner), as well as implementing critical skills related to understanding the unrealistic nature of social media content, limiting appearance comparisons with images, and contributing to social media (comments and images) in ways that limit the pursuit of appearance ideals. Previous work has provided partial support for these facets as related to lower levels of body image and eating concerns. However, additional conceptual and measurement work is needed to advance understanding of this protective role and how to foster social media literacy. Although data are scarce, targeting social media literacy in prevention and intervention programs may also be valuable. In this perspective piece, key features that we identify as priorities for future prevention and intervention efforts include developing interventions that target the implementation of social media skills beyond their acquisition. In addition, leveraging social media user generated content for prevention purposes would likely be useful, as would embedding micro-skill delivery within platforms.

"My Dead Body": Development, production, and reception of a documentary that publicly displays the dissection of a human donor.

Recently, there has been an emphasis on keeping the study of anatomy using donor material confined to the domain of medical and allied healthcare professionals. Given the abundance of both accurate and inaccurate information online, coupled with a heightened focus on health following the COVID-19 pandemic, one may question whether it is time to review who can access learning anatomy using donors. In 2019, Brighton and Sussex Medical School (BSMS) obtained a Human Tissue Authority Public Display license with the aim of broadening the reach of who could be taught using donor material. In 2020, BSMS received its first full-body donor with consent for public display. Twelve workshops were delivered to student groups who do not normally have the opportunity to learn in the anatomy laboratory. Survey responses (10.9% response rate) highlighted that despite being anxious about seeing inside a deceased body, 95% felt more informed about the body. A documentary "My Dead Body" was filmed, focusing on the rare cancer of the donor Toni Crews. Viewing figures of 1.5 million, and a considerable number of social media comments highlighted the public's interest in the documentary. Thematic analysis of digital and social media content highlighted admiration and gratitude for Toni, the value of education, and that while the documentary was uncomfortable to watch, it had value in reminding viewers of life, their bodies, and their purpose. Fully consented public display can create opportunities to promote health-conscious life choices and improve understanding of the human body.

Classification of comments on social media based on long short-term memory

Social media has assumed a pivotal role in contemporary society, significantly enhancing the convenience of daily lives. Nonetheless, the prevalence of toxic comments on social media platforms has led to varying degrees of harm for individuals. The conventional practice of manually categorizing and blocking such toxic comments has proven to be highly inefficient. To address this issue, this study employs artificial intelligence natural language processing technology to classify social media comments, offering a more effective solution. In the past few years, many algorithms for handling text classification tasks have been introduced and applied in various scenarios. In this work, the author used an LSTM model that can effectively handle long sequence dependency problems to implement text classification. This study achieved an accuracy of 99.4% after training on the Kaggle toxic comments datasets. During the training process, the training accuracy is greater than the validation accuracy while the validation loss is lower than the training loss. After training, the trained model can accurately predict an input sentence and the results are within the expected range.

Coronaphobia or sinophobia: How journalistic practices in early COVID-19 coverage and online commentary affect anti-Chinese sentiment in the U.S.

Historically, pandemics have spurred an influx of disorganized information and escalated intergroup animosity, and COVID-19 is no exception. Pandemic reporting often features cues and testimonials to mark the distinction between “us” versus “them”; however, the influence of such journalistic practices on intergroup animosity remains largely unexplored during public health crises, let alone their potential interplay with ubiquitous user-generated comments that often accompany pandemic news stories in the digital era. We conducted an online survey experiment with a sample of U.S. participants ( N = 1428) during the early phase of the COVID-19 pandemic, systematically varying the presence of stigmatizing outgroup cues, testimonials from in-versus outgroups, and social media comments either predominantly endorsing or condemning xenophobia. Our findings reveal that stigmatizing outgroup cues amplified the effects of testimonials detailing ingroup suffering, thus heightening anti-Chinese sentiment. These results underscore the importance of evaluating the implications of journalistic practices in public health reporting on intergroup dynamics and social solidarity. Additionally, we found that online comments predominantly condemning xenophobia moderated the effects of ingroup testimonials in the direction of inducing more positive sentiments, highlighting the vital role of an engaged audience in moderating the influences of public health news coverage.

Young consumers’ impulse buying tendency on social media: an empirical analysis in Vietnam in light of the LST theoretical perspective

Purpose Social commerce has brought about a significant transformation in consumer experience due to diverse factors. As a result, users often find themselves prone to impulsive buying behaviour when exposed to such an environment. Prior research was limited to demonstrating the expanding influence of celebrities on social media and the linkage between social engagement and impulse buying context. Furthermore, the impulse buying tendency of consumers on social media in the context of celebrity posts has yet to be validated. This paper aims to assess the influence of consumer awareness, consumer trust and observational learning on the latent state-trait (LST) theory regarding celebrity posts on impulse buying tendencies. Design/methodology/approach The empirical research builds on a sample survey involving 750 students from the “Big Four” economics universities in Hanoi. The proposed model was analysed using a partial least squares structural equation modelling technique. Findings The authors find that consumer trust and observational learning from celebrity’ posts positively affect impulse buying tendency. Yet celebrity influence awareness directly impacts trust in celebrity’ posts rather than directly impacting impulse buying tendency. Perceiving the importance of interactive and authentic posts by a celebrity in influencing consumers’ purchase behaviour on social media, this research offers valuable insights for stakeholders in the digital celebrity sphere of communication and marketing. Practical implications Perceiving the importance of interactive and authentic posts by a celebrity in influencing consumers’ purchase behaviour on social media, this research offers valuable insights for stakeholders in the digital celebrity sphere of communication and marketing. Originality/value From a theoretical perspective, this expands the applicability of the LST theory in social commerce to promote impulse buying tendencies. Second, this contributes to the literature on the emerging phenomenon of social media celebrities, as existing literature does not clarify their influence on impulse buying behaviour. Third, this research applies the concept of observational learning in online shopping through key features of social media platforms, namely, likes, shares and comments, to investigate their influence on the impulse buying tendency of consumers. Concerning managerial implications, the authors propose practical recommendations for practitioners, particularly those involved or interested in the commercial services industry and social media marketing (namely, celebrities and partner companies).

Differences in Emotional Preferences toward Urban Green Spaces among Various Cultural Groups in Macau and Their Influencing Factors

This study explores the diversity in emotional tendencies and needs toward urban green spaces (UGSs) among people from different cultural backgrounds in the wave of cultural integration. We utilized social media data as research tools, gathering a wide range of perspectives and voices. Utilizing geolocation data from 176 UGSs in Macau, we collected 139,162 social media comments to analyze the emotional perceptions of different cultural groups. Furthermore, we conducted regression analysis on the number of posts and emotional intensity values from four linguistic groups—Chinese, English, Southeast Asian languages, and Portuguese—in UGSs, correlating them with ten locally relevant landscape features. Our findings reveal diverse attitudes, emotional inclinations, and functional and design needs of different linguistic groups toward UGSs, as follows: (1) there were significant differences in emotional intensity and tweet counts across 176 UGSs; (2) Chinese and Portuguese speakers showed a more positive attitude toward plazas and natural ecological areas, whereas English- and Southeast-Asian-language speakers tended to favor recreational areas and suburban parks; (3) Chinese speakers exhibited a more positive emotional intensity toward sports facilities, while English speakers placed more emphasis on green space areas, architecture, sports infrastructure, and plant landscapes; (4) there was no specific landscape feature preference for Portuguese- and Southeast-Asian-language speakers. This research not only deepens our understanding of the emotional perceptions and preferences of UGSs among different cultural groups but also explores the association between these groups and various urban landscape features. This provides important theoretical and practical insights for future UGS planning, construction, and promoting multicultural coexistence for sustainable urban development.

What’s in my mince? Reader responses to news coverage about novel plant-based protein foods

ABSTRACT Plant-based protein products have recently become more prominent on Australian supermarket shelves. However, despite rapidly increasing interest in meat-free or reduced-meat diets, limited research has explored responses toward these foods. Our research analyses Facebook comments (n = 1384) in response to two ABC News articles that covered the Australian launch of Naturli’s “Minced” product in 2018. Our qualitative analysis generated seven main themes, with comments relatively evenly split between self-declared meat consumers and those who did not eat meat. Our analysis shows that social media comments can provide real-time access to what we term “critical moments” in ongoing debates as well as values, in this case related to meat and meat alternatives. Hence people’s views on contentious topics relating to food are more robust and less open to persuasion than political and industry actors might hope or expect, and alternatives to use of framing approaches are required for any media analysis in domains where conflict is present.

Filtering offensive language from multilingual social media contents: A deep learning approach

In the face of uncontrolled offensive content on social media, automated detection emerges as a critical need. This paper tackles this challenge by proposing a novel approach for identifying offensive language in multilingual, code-mixed, and script-mixed settings. The study presents a novel multilingual hybrid dataset constructed by merging diverse monolingual and bilingual resources. Further, we systematically evaluate the impact of input representations (Word2Vec, Global Vectors for Word Representation (or GloVe), Bidirectional Encoder Representations from Transformers (or BERT), and uniform initialization) and deep learning models (Convolutional Neural Network (or CNN), Bidirectional Long Short Term Memory (or Bi-LSTM), Bi-LSTM-Attention, and fine-tuned BERT) on detection accuracy. Our comprehensive experiments on a dataset of 42,560 social media comments from five languages (English, Hindi, German, Tamil, and Malayalam) reveal the superiority of fine-tuned BERT. Notably, it achieves a macro average F1-score of 0.79 for monolingual tasks and an impressive 0.86 for code-mixed and script-mixed tasks. These findings significantly advance offensive language detection methodologies and shed light on the complex dynamics of multilingual social media, paving the way for more inclusive and safer online communities.

Identifying the Risk Factors of Allergic Rhinitis Based on Zhihu Comment Data Using a Topic-Enhanced Word-Embedding Model: Mixed Method Study and Cluster Analysis.

Allergic rhinitis (AR) is a chronic disease, and several risk factors predispose individuals to the condition in their daily lives, including exposure to allergens and inhalation irritants. Analyzing the potential risk factors that can trigger AR can provide reference material for individuals to use to reduce its occurrence in their daily lives. Nowadays, social media is a part of daily life, with an increasing number of people using at least 1 platform regularly. Social media enables users to share experiences among large groups of people who share the same interests and experience the same afflictions. Notably, these channels promote the ability to share health information. This study aims to construct an intelligent method (TopicS-ClusterREV) for identifying the risk factors of AR based on these social media comments. The main questions were as follows: How many comments contained AR risk factor information? How many categories can these risk factors be summarized into? How do these risk factors trigger AR? This study crawled all the data from May 2012 to May 2022 under the topic of allergic rhinitis on Zhihu, obtaining a total of 9628 posts and 33,747 comments. We improved the Skip-gram model to train topic-enhanced word vector representations (TopicS) and then vectorized annotated text items for training the risk factor classifier. Furthermore, cluster analysis enabled a closer look into the opinions expressed in the category, namely gaining insight into how risk factors trigger AR. Our classifier identified more comments containing risk factors than the other classification models, with an accuracy rate of 96.1% and a recall rate of 96.3%. In general, we clustered texts containing risk factors into 28 categories, with season, region, and mites being the most common risk factors. We gained insight into the risk factors expressed in each category; for example, seasonal changes and increased temperature differences between day and night can disrupt the body's immune system and lead to the development of allergies. Our approach can handle the amount of data and extract risk factors effectively. Moreover, the summary of risk factors can serve as a reference for individuals to reduce AR in their daily lives. The experimental data also provide a potential pathway that triggers AR. This finding can guide the development of management plans and interventions for AR.

Perceptions on Cultural Ecosystem Services of World Cultural Heritages in Beijing: A cross-cultural Comparison of Social Media-based Online Reviews and Images

This study introduces an innovative approach combining social media text and image comments to quantify the perceptual differences of cultural ecosystem services among various sociocultural groups. For five World Heritage Sites in Beijing, natural-language processing classifies visitor perceptions using social media comments and image data, and importance-performance analysis quantifies the differences between Chinese and international visitor perceptions of these cultural ecosystem services. For the six perceived cultural ecosystem service categories, cross-cultural and local visitors exhibit the same satisfaction trends. In particular, international tourists assign higher importance scores for a given cultural ecosystem service than Chinese tourists. The proposed methods incur a lower cost than traditional methods and acquire large volumes of broad-ranging data. Additionally, the importance of‒the performance analysis data-acquisition method is improved. Moreover, World Heritage Site sustainability can be promoted by understanding the different heritage tourism perceptions of different cultural groups. Furthermore, this study provides valuable insights for decision-makers to improve tourism management and conservation strategies.

Gerakan Perlawanan Body Shaming melalui Musik Video Lagu Berhak Bahagia

This research was motivated by the many acts of body shaming that attack women. The emergence of society's views regarding ideal body image encourages people, whether consciously or not, to compare themselves with other people. Women's space for movement becomes narrow due to patriarchy which regulates men in a dominant position while women are in a subordinate position. This is why women experience body shaming more often than men. The impacts range from a person's lack of self-confidence to mental disorders. Basically everyone can be a target for body shaming, such as Aurel Hermansyah. Aurel Hermansyah experienced body shaming through social media comments when she was pregnant with her first child because she was considered to have changed her body shape. The negative comments given to Aurel Hermansyah made Atta Hlilintar release a song entitled Berhak Bahagia. Therefore, this research aims to determine the form of resistance of the anti-body shaming movement in the song Berhak Bahagia. Using qualitative methods with a critical approach. The data collection techniques used were observation, literature study and documentation.

Negative Stances Detection from Multilingual Data Streams in Low-Resource Languages on Social Media Using BERT and CNN-Based Transfer Learning Model

Online social media allows users to connect with a large number of people across the globe and facilitate the exchange of information efficiently. These platforms cater to many of our day-to-day needs. However, at the same time, social media have been increasingly used to transmit negative stances such as derogatory language, hate speech, and cyberbullying. The task of identifying the negative stances from social media posts or comments or tweets is termed negative stance detection . One of the major challenges associated with negative stance detection is that most of the content published on social media is often in a multilingual format. This work aims to identify negative stances from multilingual data streams in low-resource languages on social media using a hybrid transfer learning and deep convolutional neural network approach. The proposed work starts by preprocessing the multilingual datasets by removing irrelevant information such as special characters and hyperlinks. The processed dataset is then passed through a pretrained BERT (bidirectional encoder representations from Transformers) model to generate embeddings by fine-tuning the model as per the dataset under consideration. The generated word embeddings are then passed to a deep convolutional neural network for extracting the latent features from the texts and removing the unessential information. This helps our model to achieve robustness and effectiveness for efficient learning on the given dataset and make appropriate predictions on zero-shot data. The article utilizes several optimization strategies for examining the impact of fine-tuning different BERT layers on the model’s performance. Intensive experiments on a variety of languages — namely, English, French, Italian, Danish, Arabic, Spanish, Indonesian, German, and Portuguese — are performed. The experimental results demonstrate the effectiveness and efficiency of the proposed framework.

Public views of sexual assault, and its prevention, in residential aged care facilities

The prevalence of sexual assaults against older people in Residential Aged Care Facilities (RACFs) is estimated to be more than double the incidents in the community, yet there is a paucity of empirical research focused on this context. Considering significant revelations and community concerns stemming from Australia's recent Royal Commission into Aged Care Quality and Safety, the current study sought to assess public knowledge of sexual assaults in RACFs, specifically, the causes, delegations of responsibility, and possible solutions to limit reoccurrences. Thematic analysis was conducted on 2,398 social media comments made in response to posts concerning sexual assault in RACFs ( n = 27 sources). Results suggest systemic factors frequently contributed to incidents (e.g., staffing insufficiencies, apathetic management, and meagre regulatory requirements), while improved guardianship, sanctions, and regulation were expected to mitigate risk. Notably, the government was frequently blamed for its role in establishing and maintaining conditions that manifest in abuse within RACFs, with responsibility also delegated to family members. Importantly, public opinion strongly coincided with prior empirical prevention recommendations, endorsing the implementation of identified measures to limit sexual victimisation risk in RACFs.

‘Because of People Like You…’: Banal Politics in the Making of the Pandemic Governmentality in Italy

At first sight, social media comments seem to be the place where anti-vaxxer discourse and mocking regularly occurred during the global pandemic. Based on an exploratory analysis of comments that were published on the social media account of the Italian Department of Civil Protection from February 2020 to December 2021, this paper argues that social media comments can also help to detect the subjectivity augured by discourses of COVID19 crisis management: the responsible subject. Drawing on governmentality studies and a social semiotic understanding of social media comments as ‘banal politics’, this paper discusses the reconfiguration of the political during and beyond the global pandemic. It looks at the reconstitution of a new political subject that emerged throughout the COVID19 crisis: the responsible, a subject who does not limit herself to following the governmental rules but also reproduces and enforces them on a molecular communication scale.

Exploring public opinion on health effects of prepared dishes in China through social media comments.

In the 2020s, particularly following 2022, the Chinese government introduced a series of initiatives to foster the development of the prepared dishes sector, accompanied by substantial investments from industrial capital. Consequently, China's prepared dishes industry has experienced rapid growth. Nevertheless, this swift expansion has elicited varied public opinions, particularly concerning the potential health effects of prepared dishes. Therefore, this study aims to gather and analyze comments from social media on prepared dishes using machine learning techniques. The objective is to ascertain the perspectives of the Chinese populace on the health implications of consuming prepared dishes. Social media comments, characterized by their broad distribution, objectivity, and timeliness, served as the primary data source for this study. Initially, the data underwent preprocessing to ensure its suitability for analysis. Subsequent steps in this study involved conducting sentiment analysis and employing the BERTopic model for topic clustering. These methods aimed to identify the principal concerns of the public regarding the impact of prepared dishes on health. The final phase of the study involved a comparative analysis of changes in public sentiment and thematic focus across different time frames. This approach provides a dynamic view of evolving public perceptions related to the health implications of prepared dishes. This study analyzed over 600,000 comments gathered from various social media platforms from mid-July 2022 to the end of March 2024. Following data preprocessing, 200,993 comments were assessed for sentiment, revealing that more than 64% exhibited negative emotions. Subsequent topic clustering using the BERTopic model identified that 11 of the top 50 topics were related to public health concerns. These topics primarily scrutinized the safety of prepared dish production processes, raw materials, packaging materials, and additives. Moreover, significant public's interest was in the right to informed consumption across different contexts. Notably, the most pronounced public opposition emerged regarding introducing prepared dishes into primary and secondary school canteens, with criticisms directed at the negligence of educational authorities and the ethics of manufacturers. Additionally, there were strong recommendations for media organizations to play a more active role in monitoring public opinion and for government agencies to enhance regulatory oversight. The findings of this study indicate that more than half of the Chinese public maintain a negative perception towards prepared dishes, particularly concerning about health implications. Chinese individuals display considerable sensitivity and intense reactions to news and events related to prepared dishes. Consequently, the study recommends that manufacturers directly address public psychological perceptions, proactively enhance production processes and service quality, and increase transparency in public communications to improve corporate image and people acceptance of prepared dishes. Additionally, supervisory and regulatory efforts must be intensified by media organizations and governmental bodies, fostering the healthy development of the prepared food industry in China.

Phonogram-based Automatic Typo Correction in Malayalam Social Media Comments

The Internet has emerged as a pivotal medium for human interaction, leading to profound transformations in language dynamics, especially in computer-mediated communication (CMC) platforms. These transformations are reflected in changing orthography, graphology, vocabulary, grammar, syntax, pragmatics, and the style of natural languages. Internet-based communication has become more accessible. To increase accessibility, users of Internet-based communication platforms speak in the language that comes more naturally to them. Internet users use new terminologies and phrases to make their messages more engaging. Internet users all over the world are following this trend. Internese is the name of this emerging trend in internet lingo. All the internese features are vividly marked in Malayalam social media comments. Typographical errors are common in Malayalam social media comments. None of the spell checkers currently available in Malayalam recognize words and phrases in the social media comments scripted in Malayalam. This study proposes two different models of automatic typo detectors and typo correctors for Malayalam social media comments. The first model of Malayalam typo detectors and typo correctors is a sequence-2-sequence deep learning model, and the other is a hybrid model. These two models analyzed the input words at their phonogram level. The proposed hybrid system has achieved acceptable performance with the recently built corpus. The sequence-2-sequence model performs rather well. Because of Malayalam's intricate structure, the model's significant reliance on data influences its accuracy.

Guide for the application of the data augmentation approach on sets of texts in Spanish for sentiment and emotion analysis.

Over the last ten years, social media has become a crucial data source for businesses and researchers, providing a space where people can express their opinions and emotions. To analyze this data and classify emotions and their polarity in texts, natural language processing (NLP) techniques such as emotion analysis (EA) and sentiment analysis (SA) are employed. However, the effectiveness of these tasks using machine learning (ML) and deep learning (DL) methods depends on large labeled datasets, which are scarce in languages like Spanish. To address this challenge, researchers use data augmentation (DA) techniques to artificially expand small datasets. This study aims to investigate whether DA techniques can improve classification results using ML and DL algorithms for sentiment and emotion analysis of Spanish texts. Various text manipulation techniques were applied, including transformations, paraphrasing (back-translation), and text generation using generative adversarial networks, to small datasets such as song lyrics, social media comments, headlines from national newspapers in Chile, and survey responses from higher education students. The findings show that the Convolutional Neural Network (CNN) classifier achieved the most significant improvement, with an 18% increase using the Generative Adversarial Networks for Sentiment Text (SentiGan) on the Aggressiveness (Seriousness) dataset. Additionally, the same classifier model showed an 11% improvement using the Easy Data Augmentation (EDA) on the Gender-Based Violence dataset. The performance of the Bidirectional Encoder Representations from Transformers (BETO) also improved by 10% on the back-translation augmented version of the October 18 dataset, and by 4% on the EDA augmented version of the Teaching survey dataset. These results suggest that data augmentation techniques enhance performance by transforming text and adapting it to the specific characteristics of the dataset. Through experimentation with various augmentation techniques, this research provides valuable insights into the analysis of subjectivity in Spanish texts and offers guidance for selecting algorithms and techniques based on dataset features.

Federated Learning-Based Architecture for Personalized Next Emoji Prediction for Social Media Comments

Federated Learning-Based Architecture for Personalized Next Emoji Prediction for Social Media Comments

An Experiment in Keyword-based Approach for Hate Speech Detection in Online Social Media Comments

An Experiment in Keyword-based Approach for Hate Speech Detection in Online Social Media Comments