Search

On user-generated content platforms, individuals and firms alike seek to build and expand their follower base to eventually increase the reach of the content they upload. The bulk of the seeding literature in marketing suggests targeting users with a large follower base, that is, high-status influencers. In contrast, some recent studies find targeting lower-status influencers to be a more effective seeding policy. This multimethod article shifts the focus from the follower base of the seeding target to the focal content creator. The authors propose accelerating natural triadic closure by leveraging first-degree followers as interconnectors to target second-degree followers, that is, the nearby (low-status) influencers (who are interconnected with the focal content creator). Empirical studies document that this seeding target is much more effective for building and expanding the follower base, compared with targeting influencers who are not interconnected with the focal content creator—that is, the remote (both high- and low-status) influencers—by 2,300% and 46%, respectively. These studies on the acceleration of natural triadic closure are augmented by a preregistered field experiment to obtain convergent validity of the findings. [ABSTRACT FROM AUTHOR]

As customers increasingly rely on online reviews for making consumption decisions, the dangers arising from misinformation and fakery have become an acute source of concern for consumers, firms, and society at large. Many online review platforms claim a role as guardians of trust in the information exchange process. Yet, little is known about the practices firms can utilize to design platforms that build and safeguard consumer trust. The authors draw on governance and identity disclosure literature streams to propose five practices that mitigate fakery and build trust in the platform: monitoring, exposure, community building, status endowment, and identity disclosure. Five studies (1) establish the individual and joint effects these practices have on platform trust, (2) identify the mediating processes by which the practices build trust, (3) verify the ecological value of the conceptual framework, (4) provide support of the salience of the practices, and (5) show how the practices build trust above and beyond review content–level characteristics. Interaction effects suggest that exposure, community building, and status endowment obviate the need for identity disclosure in building platform trust, a finding that mitigates related privacy concerns. Collectively, the findings can improve platform design, enabling review platforms to fulfill their promise of mitigating fakery and increasing trust. [ABSTRACT FROM AUTHOR]

A new trend in influencer marketing is livestream commerce, which combines influencers' live video streaming with e-commerce. Little is known, though, about how firms should develop their influencer strategies to maximize product sales. Given a budget constraint, marketers may choose to employ a single, "big" influencer with a large number of followers or several small influencers. They may also employ a combination of both big and small influencers when their budget is adequate. Analyzing data from 1.3 million livestreams on TikTok, the authors find a negative interaction effect between big and small influencers when employed together due to decreased trust in big influencers and substitution effects. Further analysis reveals that livestream sales generated by a big influencer are adversely affected by small influencers who promoted the same product previously, but not the other way around. In addition, big influencers can reach a much larger audience, whereas small influencers are more effective at increasing the audience's conversion rates. Big and small influencers are also different in terms of how product and campaign characteristics moderate their sales effectiveness. Finally, the scenario analysis explores how the profitability of influencer strategies hinges on the influencer mix and their costs. This research is one of the first to investigate the sales effectiveness of influencer marketing and to provide general guidelines for developing influencer mix strategies. [ABSTRACT FROM AUTHOR]

When people share their prosocial behavior on social media, they face a dilemma. By making prosocial disclosures, they risk being perceived as self-promoting or even selfish and thus less likable. By staying silent, they fail to spread awareness about prosocial activities they value. Drawing on attribution theory, we study the digital reaction of likes to the self-disclosure of prosocial activities that involve multiple stakeholders to understand the affordances and constraints of social media. Leveraging field data on a social networking site, we found that reporting a higher level of self-effort increases the digital reaction of likes. To our surprise, expressing gratitude for the sponsor's efforts also increased likes for such selfdisclosures. Through lab experiments that emulated this context, we dissected this paradox by separating the positive effect of expressing gratitude and the negative effect of sharing credit with other stakeholders on likes. Further, we underscore the salience of expressing gratitude, even when gratitude was extended to sponsors with bad reputations. Our study contributes to the design of a more humane digital world where individuals share and promote prosocial activities without compromising their likability and offers valuable insights for navigating the evolving landscape of social networking platforms. [ABSTRACT FROM AUTHOR]

Are reviews with photos more helpful? If so, do consumers find reviews more helpful when photos and text convey similar or different information? This article examines the effect of content similarity between photos and text on review helpfulness and its underlying mechanism. Using a data set of 7.4 million reviews associated with 3.5 million photos from Yelp, and applying machine learning algorithms, the authors quantify the similarity of the content between text and photos. They find that, overall, photos increase the helpfulness of a review. More importantly, though, greater similarity between photos and text heightens review helpfulness more. The authors then validate algorithm-based similarity assessments with similarity perceptions of human judges. Using real-world reviews from Yelp and carefully designed stimuli, they replicate the core findings in five laboratory experiments. Further, testing the underlying mechanism, they find that greater similarity facilitates the ease with which consumers can process the review, which, in turn, increases that review's helpfulness to consumers. Finally, they show that factors that impede the ease of processing (e.g., language difficulty or poor image quality) can reduce the effect of similarity on helpfulness. These findings provide novel insights into the value of user-generated content that includes text and photos and its underlying mechanism. [ABSTRACT FROM AUTHOR]

Online crowdfunding has become an important fundraising channel for medical care. Yet, individuals in need face numerous challenges in meeting their fundraising goals. To improve fundraising, individuals may use project updates to evoke donors' sympathy and secure donations. Informed by the sympathy bias literature, this paper conceptualizes two important but distinct aspects of project updates—positive sentiment and negative sentiment—and hypothesizes their individual and relative impacts on the donation amount of a crowdfunding project. In addition, this paper explores moderating effects of social endorsements on the influence of update sentiment. To test our hypotheses, we conducted two studies. Study 1 examined unique project-day panel data from 1,467 projects on a leading medical crowdfunding platform. Results reveal that both positive and negative update sentiment positively affect the donation amount of a crowdfunding project, but negative updates have a greater effect. Further, endorsements by strong ties and weak ties attenuate the positive effects of update sentiment. Study 2 was a controlled, randomized experiment that corroborated findings from Study 1, established the causality of observed effects, and confirmed the mediating effects of sympathy. The findings of this paper underscore the role of sympathy in enhancing online charitable crowdfunding to individual donors and show project updates with positive or negative sentiment to be potent mechanisms to boost donations. Furthermore, the substitution effect of social endorsement on donation amount also adds nuance to our knowledge suggesting that a proper combination of various information can better help improve crowdfunding performance. Platform operators and fundraisers should prioritize project update sentiment to enhance online charitable crowdfunding success. [ABSTRACT FROM AUTHOR]

In 2004, South Africa was awarded the opportunity to host the 2010 FIFA World Cup. The opportunity to reshape their national identity in the spotlight of the World Cup came at a particularly useful time for South Africa. Despite the country's seemingly miraculous transition from apartheid to democracy—a transition lauded around the world—the country's reputation was soon dragged down by concerns about crime, unemployment, and a rising rate of HIV infections. Although a number of scholars have looked at the long- and short-term effects of South Africa's effort at creating a national identity during the 2010 FIFA World Cup, questions of process remain to be explored. What rhetorical strategies were employed to build this national image? What role did developing social media platforms play in the World Cup campaign? What were the communication tactics that led to a successful World Cup campaign? Using the theory of dialectical vernacular, I argue that South Africa was able to use the stage and emotional setting of the World Cup, in combination with a unique moment in time in branding and social media, to cultivate and deploy user-generated content to create a sense of authenticity that successfully sold a positive image of South Africa to the world. Essentially, South Africa was able to take digital material that was submitted by citizens around the country, and around the world, and use it to build a campaign that was vernacular, transnational, and embodied in nature. This allowed them to manufacture a national identity that effectively (at least in the short term) redirected conversations away from the more complicated issues affecting the country to, instead, showcase South Africa as a successful democratic nation. [ABSTRACT FROM AUTHOR]

Prior research has shown that user-generated content (UGC) on social media is an important source for consumers seeking information about mental health treatment. The purpose of this study is to explore UGC about prescription drugs for depression as a type of digital 'pharma' folklore. Using qualitative inquiry, the authors analyse 73 user-generated product reviews on YouTube. Findings yield a compelling portrait of people's struggle with mental illness and their treatment journey. Applying folklore as a framework provides a novel strategy for analysing and theorising the cultural worldview of a consumer group. It allows marketers to decipher the knowledge being passed on to others from product review videos and gain a deeper understanding of stories that resonate with consumers seeking treatment with depression drugs. [ABSTRACT FROM AUTHOR]

Marketers frequently create social media content (i.e., firm-generated content; FGC) to ignite interest in new movies. Thus, there is a clear need to understand the magnitude and heterogeneity of the effect of FGC on movie demand and associated user-generated content (UGC). The authors empirically examine the complex interactions among FGC, UGC, and sales using social media (tweet) data that are normally available to firms. They investigate two potential mechanisms by which FGC may drive box office revenues: (1) a direct mechanism, such that users who see FGC directly drive revenue, and (2) an indirect "ripple effect," by which FGC increases movie-related UGC, which then drives consumption. By analyzing 145,502 firm-generated and 5.9 million user-generated Twitter posts associated with 159 movies, the authors find a positive and significant effect of FGC on movie sales, which UGC fully mediates, which supports the indirect ripple effect reasoning. Impressions of FGC by followers of firm accounts, as opposed to nonfollowers of firm accounts, mainly drive the effect of FGC on UGC. In addition, FGC by movie accounts is more effective than that by actors and studios. Firms' regular posts with a movie-specific hashtag are more effective than replies, retweets, and posts without the hashtag. The finding of the ripple effect suggests that movie executives should focus on creating FGC that sparks conversations among followers when new movies are released. [ABSTRACT FROM AUTHOR]

Social technologies on online review platforms enable social interactions among users, such as establishing following relationships and commenting on others' posts. Although it is well recognized that more socially engaged reviewers tend to be more active and generate content of higher quality, our knowledge about the impact of social interactions on peer evaluations of reviews is limited. To address this issue, we use a unique dataset from a major online review platform and find that, ceteris paribus, reviews posted by more socially engaged users receive more helpfulness votes than those posted by less socially engaged users. Similarly, users tend to vote more for reviews written by their mutual followers than for those written by nonfollowers. In addition, we find that less socially engaged users review a broader range of products and services but are less likely to stay on a platform, which may further contribute to the inflation of peer evaluations (toward online reviews). Our study provides unique empirical evidence regarding the influence of social interactions on review evaluations. Furthermore, we caution researchers and practitioners against utilizing review helpfulness scores as a sole measure for review quality and diagnosticity. [ABSTRACT FROM AUTHOR]

While monetary rewards have been widely used by online platforms to motivate user-generated content (UGC) contributions, users may not always demonstrate the expected behaviors. Unintended consequences of reward policies, exemplified by unchanged or reduced UGC contributions, may occur. Through two natural experiments, this study investigates the implications of providing users with an incentive structure that rewards users' continued contribution according to the volume of UGC. Using a unique data set on two completion-contingent incentive programs from a popular online aesthetic medicine platform, we examine user responses to reward thresholds. We found that after users reach a threshold to obtain a monetary reward, they are less likely to continue contributing UGC, suggesting a minimal-effort effect. Our findings indicate that social approval from peers helps to mitigate unintended user responses to monetary reward policies. We also observed that monetary rewards primarily improve the quality and website traffic of low- to moderate-quality contributions. [ABSTRACT FROM AUTHOR]

The topics of social media and consumer behavior are inextricably linked. Since 2008, scholars in sport-studies fields such as sport communication and sport management have increasingly focused their research on social media use by sport entities and consumers. This commentary provides an overview of sport social media and consumer behavior scholarship to date, including prominent and growing topics such as consumers' uses of social media, social media engagement, user segmentation, and user-generated content. A scoping review was conducted to illustrate the current state of research on social media, sport, and consumer behavior. Future research priorities to advance this area of inquiry are also discussed, including more qualitative research resulting in rich and descriptive analyses, the need to better understand Gen Z as sport social media consumers, and the need to understand the connection between social media consumption and purchasing behavior. Finally, the commentary encourages scholars to expand their research focus in geographic contexts outside of North America, on underrepresented groups, such as women's sport and disability sport, and to adopt new theoretical frameworks for such research. [ABSTRACT FROM AUTHOR]

Recommender systems on online platforms are often accused of polarizing user attention and consumption. The authors examine this phenomenon using a quasi-experiment conducted by Zhihu, the largest online knowledge-sharing platform (or Q&A community) in China. Zhihu originally used a content-based filtering algorithm, which recommends content to users on the basis of the topics to which each user has subscribed. After more than a year, Zhihu moved to a social filtering algorithm, which recommends content with which users' social connections are already engaged. The authors find that this algorithm change increased the creation of social ties by approximately 15% but decreased question subscriptions by 20% and answer contributions by 23%. The authors show that users' increased social interests mainly involved following popular users, leading to a greater concentration of social interests on the platform. However, users' topical interests became less concentrated, as popular topics received significantly fewer subscribers than unpopular topics. The authors explain these findings by exploring the underlying mechanism. They show that compared with content-based filtering algorithms, social filtering algorithms are more likely to expose general users to content consumed by their followees, who are more interested in niche topics than general users are. [ABSTRACT FROM AUTHOR]

Nowadays, the web has emerged as an enormous multimedia data resource. Social media platforms are becoming the mass producers of user-generated multimedia content. Web search engines usually organize media-specific information, such as text, images, video, etc., in specialized data repositories (verticals), providing easy access to multimedia content. Web search engines have become efficient in retrieving data across various distinct verticals. However, users still need help formulating queries to retrieve the relevant multimedia results from verticals. Novice users often issue short-length ambiguous queries due to a lack of domain knowledge or query formulation experience, resulting in the retrieval of irrelevant results. The query formulation itself is a time-consuming process for the users. We presented an end-to-end deep-learning automatic query recommendation approach to address the associated issues. The proposed method autonomously extracts the domain knowledge using pseudo-relevance feedback, transforms it into a unified text-to-text summary, and assists users in generating non-ambiguous and well-balanced query recommendations. The proposed system employs Google's real-time dataset and is compared to the Google search engine. The evaluation consists of empirical and usability perspectives. The empirical evaluation of shorter query formulation and reformulation time obtained 89% accuracy scores in automated query recommendation. The usability testing (N=37) reveals 85.4% usefulness & ease-of-use, and "A" category proposed system usability. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) has gained much attention since sensor technology has become more advanced and cost-effective. HAR is a process of identifying the daily living activities of an individual with the help of an efficient learning algorithm and prospective user-generated datasets. This paper addresses the technical advancement and classification of HAR systems in detail. Design issues, future opportunities, recent state-of-the-art related works, and a generic framework for activity recognition are discussed in a comprehensive manner with analytical discussion. Different publicly available datasets with their features and incorporated sensors are also descr-processing techniques with various performance metrics like - Accuracy, F1-score, Precision, Recall, Computational times and evaluation schemes are discussed for the comprehensive understanding of the Activity Recognition Chain (ARC). Different learning algorithms are exploited and compared for learning-based performance comparison. For each specific module of this paper, a compendious number of references is also cited for easy referencing. The main aim of this study is to give the readers an easy hands-on implementation in the field of HAR with verifiable evidence of different design issues. [ABSTRACT FROM AUTHOR]

Despite opaque automated systems and few formal channels for participation, YouTubers navigate algorithmic governance on the platform through a strategy we call user-generated accountability: the generation of publicity via content creation to reveal failures, oversights, or harmful policies. Through an analysis of 250 videos, we identify common strategies, concerns, and targets of accountability. Creators primarily upload vlogs that acknowledge the platform's positive aspects, even as they express concern with YouTube's policies, automated enforcement systems, poor communication practices, and discrimination against certain creators or content. In publicizing critiques of platform operations, videos enroll creators and audiences as active stakeholders in platform governance that can coordinate actions to draw the company's attention to matters of concern. We argue that user-generated accountability practices offer a productive starting point for understanding how platform governance disputes come to be and how systems might be shaped or rebuilt to better serve the needs of competing stakeholders. [ABSTRACT FROM AUTHOR]

This study examines the adoption of web tools by Greek legacy media organizations from a historical perspective, covering the period from the 1990s to 2023. The study employs a mixed-method approach, including a literature review, content analysis of websites, and survey of social media and application use in two time-points. The results reveal that Greek legacy media have embraced web 2.0 technologies, such as tags, live broadcasting, and on-demand content. However, the study also identifies some areas for improvement, including the need to create more interactive public discussion environments and explore new technologies such as podcasting and new platforms. [ABSTRACT FROM AUTHOR]

Every day, patients access and generate online health content through a variety of channels, creating an ever-expanding sea of digital data. At the same time, proponents of public health have recently called for timely, granular, and actionable data to address a range of public health issues, stressing the need for social listening platforms that can identify and compile this valuable data. Yet previous attempts at social listening in healthcare have yielded mixed results, largely because they have failed to incorporate sufficient context to understand the communications they seek to analyze. Guided by activity theory to design HealthSense, we propose a platform for efficiently sensing and gathering data across the web for real-time analysis to support public health outcomes. HealthSense couples theory-guided content analysis and graph propagation with graph neural networks (GNNs) to assess the relevance and credibility of information, as well as intelligently navigate the complex online channel landscape, leading to significant improvements over existing social listening tools. We demonstrate the value of our artifact in gathering information to support two exemplar public health tasks: (1) performing postmarket drug surveillance for adverse reactions and (2) addressing the opioid crisis by monitoring for potent synthetic opioids released into communities. Our results across data, user, and event experiments show that effective design artifacts can enable better outcomes across both automated and human decision-making contexts, making social listening for public health possible, practical, and valuable. Through our design process, we extend activity theory to address the complexities of modern online communication platforms, where information resides not only in the collection of individual communication activities but also in the complex network of interactions among them. [ABSTRACT FROM AUTHOR]

Online knowledge communities (OKCs), such as question-and-answer sites, have become increasingly popular venues for knowledge sharing. Accordingly, it is necessary for researchers and practitioners to develop effective and efficient text analysis tools to understand the massive amount of user-generated content (UGC) on OKCs. Unsupervised topic modeling has been widely adopted to extract humaninterpretable latent topics embedded in texts. These identified topics can be further used in subsequent analysis and managerial practices. However, existing generic topic models that assume documents are independent are inappropriate for analyzing OKCs where structural relationships exist between questions and answers. Thus, a new method is needed to fill this research gap. In this study, we propose a new topic model specifically designed for the text in OKCs. We make three primary contributions to the research on topic modeling in this context. First, we build a general and flexible Bayesian framework to explicitly model structural and temporal dependencies among texts. Second, we statistically demonstrate the approximate model inference using mean-field and coordinate ascent algorithms. Third, we showcase the practical value and relative merit of our method via a specific downstream task (i.e., user profiling). The proposed model is illustrated using two real-world datasets from well-known OKCs (i.e., Stack Exchange and Quora), and extensive experiments demonstrate its superiority over several cutting-edge benchmarks. [ABSTRACT FROM AUTHOR]

Bilateral ratings on online marketplaces may soften price competition and sellers of higher quality may charge lower prices. Abstract. Peer-to-peer (P2P) markets have become a critical aspect of the modern economy. We consider a P2P market in which a time-sensitive service is provided through a platform that matches providers of varying qualities to customers of varying costs. The P2P platform features bilateral ratings, which distinguish it from a traditional market: ratings of a provider reveal the provider's service quality and ratings of a customer reveal the customer's service cost. The existence of a cost measure in the P2P market leads to novel pricing considerations: a provider can attract low-cost customers by charging a low price, leading to an endogenous composition effect. As a result, equilibrium prices may decrease as customers become more costly to serve or as the platform's commission rate gets higher. Under certain conditions, high-quality providers may even charge a lower equilibrium price than low-quality providers in order to cherry-pick low-cost customers. Exploratory analysis reveals that, compared with unilateral ratings, bilateral ratings may soften provider competition and raise equilibrium prices as the providers target customers in different cost segments. History: Anthony Dukes served as the senior editor. Funding: This work was supported by the NET Institute (summer research fund). Supplemental Material: The online appendix is available at https://doi.org/10.1287/mksc.2022.0158. [ABSTRACT FROM AUTHOR]

Repeat customers are crucial for business success. Previous studies have mainly focused on those factors that affect repeat patronage but ignored how repeat customers reevaluate the same service provider after consumption. We obtained a dataset containing 637,748 reviews of restaurants in New York City and used a generalized difference-in-differences design to further explore the rating behavior of local repeat customers. The results of this study contribute to theories of customer satisfaction, repeat patronage, and customer location in the context of user-generated content as repeat customers are found to be sensitive to quality variations. Such sensitivity is even accentuated by local customers. Relevant practical implications for restaurant managers are also drawn from the results. [ABSTRACT FROM AUTHOR]

Many platforms host user-generated content (UGC) and content developed by professionals side by side. However, thus far, their impact on platform ecosystems has been mostly studied in isolation. In this paper, we use data from a network of 122 local news outlets hosted by an online news platform to study the spillover effects from UGC developed by citizen journalists to the content developed by professional journalists. We use the removal of a status index associated with citizen journalists as an exogenous shock to their supply of UGC to identify these spillover effects. We find that experienced citizen journalists reduce their production of content when this status index is removed. We then find that inexperienced professional journalists increase their output in response to this behavior. However, as a result of these changes, we find a reduction in the overall content hosted by the platform, especially in the case of local news and in more isolated regions. We further show that this is likely to have detrimental effects for the platform. In particular, there is a decline in overall viewership, and the platform may need to hire and pay salaries to more professional journalists to produce enough articles to close the gap left by the departing citizen journalists. Our work contributes to the literature on UGC and online platforms and to the literature on local news. This paper was accepted by D. J. Wu, information systems division. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.4962. [ABSTRACT FROM AUTHOR]

Improving customer satisfaction is the key factor in enhancing the core competitiveness of hotels, as higher customer satisfaction can lead to long-term benefits such as a positive reputation, customer loyalty, and sustained profitability. Multi-source user-generated content (UGC) can provide high-quality and sufficient information for improving customer satisfaction; however, related research is limited. Therefore, a method considering multi-source UGC to improve customer satisfaction is proposed in this paper. First, the service attributes of the hotels that customers care about are obtained from multi-source UGC. Then, evaluation information is obtained by processing multi-source UGC based on the heuristic-systematic model, and the credibility of the evaluation information is measured. Furthermore, evaluation information is combined based on evidence theory to estimate the importance and performance of hotel service attributes. Finally, impact asymmetry-gap analysis (IAGA) is proposed to generate customer satisfaction improvement strategies for different attributes. The application of the method is illustrated using data from actual hotels. [ABSTRACT FROM AUTHOR]

Understanding visitors’ park experience in urban tourist destinations to enhance their satisfaction is crucial for effective park management and urban planning. Through a topic modelling analysis using user-generated data from TripAdvisor and employing the Latent Dirichlet Allocation (LDA) algorithm, 20 attributes of urban park experience are identified and grouped into three categories and five dimensions. Besides confirming some of the attributes of park experience identified in previous research, this study also uncovers new attributes that provide insights into visitors’ urban park experience related to the historical and cultural aspects (e.g. filming location, carriage rides and rickshaws). Furthermore, positive and negative effects of each attribute on visitor satisfaction are identified. Findings also suggest significant seasonal difference in attributes of visitors’ urban park experience. [ABSTRACT FROM AUTHOR]

Copyright of Environmental & Social Management Journal / Revista de Gestão Social e Ambiental is the property of Environmental & Social Management Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Environmental & Social Management Journal / Revista de Gestão Social e Ambiental is the property of Environmental & Social Management Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

On the Internet, online microblogging and social networks have experienced tremendous growth. Millions of individuals share opinions on social networking platforms including Twitter, Facebook, YouTube, and Microblogging sites. Millions of individuals express their thoughts on social platforms namely Twitter, Facebook, YouTube, and microblogging sites. As user‐generated content is growing to a huge extent on the internet, the analysis, extraction identification and classification of opinion and sentiment polarity of different aspects has now become a challenging issue in sentiment analysis. In sentiment analysis, aspect level opinion mining, opinion spam review detection, extraction and representation of most relevant accessed data from the user‐generated data is a difficult process. The word vector representation using existing deep learning techniques affects the performance in aspect level opinion mining. Spammers propagate false opinion for payment exchange, which leads to degradation of the financial growth, business, and fame of the organization. To overcome the limitations aspect level opinion mining is used to recognize sentiment and polarity of aspects in the specified text. This work presents various input feature vectors of deep learning approaches aiming to improve performance in aspect level opinion mining. Next, three meta‐heuristic algorithms with k‐means clustering approach for classification of opinion spam reviews on social media transit tweets is presented. The proposed approaches are evaluated and compared with other existing approaches as well as other benchmark datasets namely Restaurant and Amazon reviews. [ABSTRACT FROM AUTHOR]

E-commerce live streaming has become a lucrative global industry. As the main carrier to convey information in live broadcasting, user-generated content (UGC)—and especially bullet screens—are crucial in influencing users' purchase intentions. However, the influence of bullet screens' multidimensional information characteristics on consumers' decision-making processes requires further exploration. Additionally, most existing studies start with the short-term effects of live product realization, and must address how to enhance customers' psychological ownership using new means of live streaming marketing to obtain long-term sustainable brand-building effects. This study introduces psychological ownership and the communicative presence as mediating variables based on the theory of elaboration likelihood modeling to explore the mechanism of the influence of UGC's multidimensional features on viewers' purchase intentions in live e-commerce broadcasting rooms. We collected 404 valid online questionnaires and tested our hypotheses using structural equation modeling. These findings indicate that UGC emotions, quality, and their interaction significantly and positively affect purchase intentions. Moreover, psychological ownership and the communicative presence mediate UGC's effect on purchase intentions. These results provide a new perspective for understanding consumer behavior in live e-commerce to improve marketing effectiveness of e-commerce live streaming platforms. [ABSTRACT FROM AUTHOR]

As user-generated data diversifies, an increasing number of big data tasks now encompass unstructured data forms, including audio, imagery, and video content. The processing of these data often requires the support of GPU devices in the cluster. However, most of the existing cluster resource management frameworks lack effective decoupling of CPU resources and GPU resources, and the management granularity of GPU resources is too coarse, resulting in poor GPU sharing and low resource utilization. Given, for the inadequacy of the existing cluster resource management framework that cannot support batch stream integration and CPU-GPU resource scheduling, we design and implement a Hybrid Heterogeneous Resource Management (H-HRM) for CPU-GPU heterogeneous clusters. The resource queue binding mechanism on computing nodes provides flexible binding of CPU resources to GPU resources, which solves the problem that CPU resources and GPU resources in the cluster are difficult to decouple. According to the different uses of CPU or GPU as the main resource, a Hybrid Domain Resource Fairness (HDRF) model is proposed to realize the reasonable allocation of CPU resources and GPU resources. Through the queue stacking technology and the mechanism that multiple executors can run simultaneously on the queue, fine-grained sharing of GPU resources is realized and the utilization rate of GPU resources is improved. Finally, this paper realizes the docking of H-HRM and Spark programming framework and conducts real load tests, and after comparing with the performance of Mesos, it is proved that H-HRM can handle the mixed scenarios of batch jobs and stream processing jobs in the cluster, and the HDRF algorithm also greatly improves the utilization of the GPU. [ABSTRACT FROM AUTHOR]

Hospitality services play a crucial role in shaping tourist satisfaction and revisiting intention toward destinations. Traditional feedback methods like surveys often fail to capture the nuanced and real-time experiences of tourists. Digital platforms such as TripAdvisor, Yelp, and Google Reviews provide a rich source of user-generated content, but the sheer volume of reviews makes manual analysis impractical. This study proposes integrating aspect-based sentiment analysis with zero-shot learning to analyze online tourist reviews effectively without requiring extensive annotated datasets. Using pretrained models like RoBERTa, the research framework involves keyword extraction, sentence segment detection, aspect construction, and sentiment polarity measurement. The dataset, sourced from TripAdvisor reviews of attractions, hotels, and restaurants in Central Java, Indonesia, underwent preprocessing to ensure suitability for analysis. The results highlight the importance of aspects such as food, accommodation, and cultural experiences in tourist satisfaction. The findings indicate a need for continuous service improvement to meet evolving tourist expectations, demonstrating the potential of advanced natural language processing techniques in enhancing hospitality services and customer satisfaction. [ABSTRACT FROM AUTHOR]

With the use of Generative AI (GenAI), Online Social Networks (OSNs) now generate a huge volume of content data. Yet, user-generated content on OSNs, aided by GenAI, presents challenges in analyzing and understanding its characteristics. In particular, tweets generated by GenAI at the request of authentic human users present difficulties in determining the gendered variation of the content. The vast amount of data generated from tweets' content necessitates a thorough investigation into the gender-specific language used in these tweets. This study explores the task of predicting the gender of text content in tweets generated by GenAI. Through our analysis and experimentation, we have achieved a remarkable 90% accuracy in attributing gender-specific language to these tweets. Our research not only highlights the potential of GenAI in gender prediction but also underscores the sophisticated techniques employed to decipher the refined linguistic cues that differentiate male and female language in GenAI-generated content. This advancement in understanding and predicting gender-specific language in GenAI-generated tweets covers the way for more refined and accurate content analysis in the evolving landscape of OSNs. [ABSTRACT FROM AUTHOR]

The global COVID-19 pandemic produced several changes in nearly every aspect of our lives. Ride-sharing platforms such as Uber and Lyft must adapt their strategies and aims to stay afloat. The analysis in this study is based on 216,120 tweets in the U.S. between January 1, 2019, and December 30, 2021, about Uber. It includes four separate analyses: Popularity and Usage Analytics, Sentimental Analytics, Voice Analytics, and Topic Mining Analytics. The result shows that usage and popularity of Uber on Twitter negatively affect Covid and death cases. In contrast, vaccination helps mitigate the shock of Covid. Additionally, ' 'Uber's policy and business model was beneficial in improving its positive image during the pandemic; On the early breakout of Covid in the U.S. Uber had a jump on the positive sentiment, mainly because Uber provided safer service than public transportation. [ABSTRACT FROM AUTHOR]

The primary goal of this study is to compare the analysis results of sentiment analysis using three different machine learning models: Naïve Bayes, Support Vector Machine (SVM), and Random Forest. The raw dataset used for this study is sourced from the Google Play Scraper API, which is then preprocessed to ensure quality and accuracy of feature extraction. Once preprocessed, the machine divides the dataset for training and testing using the 80:20 rule. The results of this comparison provide insights into the strengths and weaknesses of each algorithm in the context of sentiment analysis of user reviews. This study aims to inform practitioners about the most effective techniques for extracting actionable insights from user-generated content on digital platforms. The evaluation shows that the Naïve Bayes model achieved the highest accuracy of 81%, followed by the SVM model with 80%, and the Random Forest model with 76%. These findings highlight the Naïve Bayes model as the most accurate for sentiment analysis in this context, with all models demonstrating robust performance. [ABSTRACT FROM AUTHOR]

With the progressive enhancement of social media, several people prefer posting their opinions on various social media instead of posting on radios, television or newspapers. The postings differ in dimensions and include various titles and comments. Nowadays, the formation of plagiarism is increasing tremendously which occurs by rewriting or repeating one’s work. There are many ways to detect plagiarism by browsing through the internet. The significant intention of this paper involves the detection of plagiarism in social media using four different phases, namely the data pre-processing phase, n-gram evaluation, similarity/distance computation analysis and the plagiarism detection phase. The pre-processing includes data cleaning processes, such as the removal of redundant data, upper case letters, noise, irrelevant punctuations and characterizing into a vector form. After pre-processing the data are fed for n-gram evaluation to develop a post- ing attribution system. Then finally, an ensemble support vector machine-based African vulture optimization (ESVM-AVO) approach is employed to detect plagiarism which signifies that the performance based on detection is enhanced and the execution time in obtaining a high rate of detection accuracy is very low. Finally, the performance evaluation and the comparative analysis are carried out to determine the performance of the proposed system. [ABSTRACT FROM AUTHOR]

The rapid growth, large volume, and easy access to publicly available netnographic data have increased the need for understanding its potential in leveraging innovation. At the heart of quality management is a focus on customers and their needs, driving the innovation of products and services. In this study, we systematically compare netnography and focus groups as research methods regarding their ability to capture various types of customer needs. This study makes four valuable contributions to quality management theory: (1) netnography and focus groups captures similar customer needs, (2) netnography provides clear need statements, which are rich and overrepresented compared to focus groups, (3) both netnography and focus groups are vulnerable to groupthink, where customers prioritize consensus; however, this effect is more evident in netnography, (4) netnography captures more need statements about current product and service usage, while focus groups focus more on past product and service usage. [ABSTRACT FROM AUTHOR]

The prevalence of online misinformation, termed "fake news", has exponentially escalated in recent years. These deceptive information, often rich with multimodal content, can easily deceive individuals into spreading them via various social media platforms. This has made it a hot research topic to automatically detect multimodal fake news. Existing works made a great progress on inter-modality feature fusion or semantic interaction yet largely ignore the importance of intra-modality entities and feature aggregation. This imbalance causes them to perform erratically on data with different emphases. In the realm of authentic news, the intra-modality contents and the inter-modality relationship should be in mutually supportive relationships. Inspired by this idea, we propose an innovative approach to multimodal fake news detection (IFIS), incorporating both intra-modality feature aggregation and inter-modality semantic fusion. Specifically, the proposed model implements a entity detection module and utilizes attention mechanisms for intra-modality feature aggregation, whereas inter-modality semantic fusion is accomplished via two concurrent Co-attention blocks. The performance of IFIS is extensively tested on two datasets, namely Weibo and Twitter, and has demonstrated superior performance, surpassing various advanced methods by 0.6 The experimental results validate the capability of our proposed approach in offering the most balanced performance for multimodal fake news detection tasks. [ABSTRACT FROM AUTHOR]

Content-based authorship identification is an emerging research problem in online social media networks, due to a wide collection of issues ranging from security to privacy preservation, from radicalization to defamation detection, and so forth. Indeed, this research has attracted a relevant amount of attention from the research community during the past years. The general problem becomes harder when we consider the additional constraint of identifying the same false profile over different social media networks, under obvious considerations. Inspired by this emerging research challenge, in this paper we propose and experimentally assess an innovative framework for supporting content-based authorship identification and analysis in social media networks. [ABSTRACT FROM AUTHOR]

Since social media such as Facebook and X (formerly known as Twitter) have permeated various aspects of daily life, people have strong incentives to influence information dissemination on these platforms and differentiate their content from the fierce competition. Existing dissemination strategies typically employ marketing techniques, such as seeking publicity through renowned actors or targeted advertising placements. Despite their various forms, most simply spread information to strengthen user impressions without conducting formal analyses of specific influence enhancement. And coupled with high costs, most fall short of expectations. To this end, we ingeniously formulate the task of social media dissemination as poisoning attacks, which influence specified content's dissemination among target users by intervening in some users' social media behaviors (including retweeting, following, and profile modifying). Correspondingly, we propose a novel poisoning attack, Influence-based Social Media Attack (ISMA) to generate discrete poisoning behaviors, which is difficult to achieve with existing attacks. In ISMA, we first contribute an efficient influence evaluator to quantify the spread influence of poisoning behaviors. Based on the estimated influence, we then present an imperceptible hierarchical selector and a profile modification method ProMix to select influential behaviors to poison. Notably, our attack is driven by custom attack objectives, which allows one to flexibly design different optimization goals to change the information flow, which could solve the blindness of existing influence maximization methods. Besides, behaviors such as retweeting are gentle and simple to implement. These properties make our attack more cost-effective and practical. Extensive experiments on two large-scale real-world datasets demonstrate the superiority of our method as it significantly outperforms baselines, and additionally, the proposed evaluator's analysis of user influence provides new insights for influence maximization on social media. [ABSTRACT FROM AUTHOR]

Copyright of Environmental & Social Management Journal / Revista de Gestão Social e Ambiental is the property of Environmental & Social Management Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Bullet‐screen comments (BSCs), a type of novel user‐generated content for online videos, have been rapidly adopted in recent years. Previous research has focused on consumers' responses to the presence and quantity of BSCs but overlooked their contents. We examine how one characteristic feature of BSCs' content—lexical diversity—affects users' payments. A large‐scale real‐world behavioral data set analysis and three lab studies show that high (vs. low) lexical diversity of BSCs increases viewers' payments in online video streaming contexts (e.g., online videos and live streaming). We further reveal that the positive effect of BSC diversity on payment is mediated by perceived social presence and information richness. We also demonstrate the moderating role of viewers' BSC usage level (heavy vs. light), such that the effect of BSC diversity on payment is significant for heavy BSC users, but diminishes for light users. [ABSTRACT FROM AUTHOR]

Modern Information and Communication Technology (ICT) has been used in safety-critical situations for over twenty years. Rooted in Human-Computer Interaction (HCI) and related disciplines, the field of crisis informatics made considerable efforts to investigate social media use and role patterns in crises, facilitate the collection, processing and refinement of social media data, design and evaluate supportive ICT, and provide cumulative and longitudinal research. This narrative review examines contemporary challenges of human-centred crisis informatics and envision trends for the following decade, including (I) a broadening scope of crisis informatics, (II) the professionalisation of cross-platform collaboration of citizen communities and emergency services, (III) expert interfaces for explainable and multimodal artificial intelligence for user-generated content assessment, (IV) internet of things and mobile apps for bidirectional communication and warnings in disruption-tolerant networks, as well as (V) digital twins and virtual reality for the effective training of multi-agency collaboration in hybrid hazards. [ABSTRACT FROM AUTHOR]

In contemporary society, the discourse on body image is increasingly emerging as a notable social issue. In particular, the body positivity movement is promoting healthy body image and self-esteem through various means. This study was conducted to analyze the discourse on sustainable body image in Korean society. User-generated content from 1 January 2014 to 31 July 2023 underwent data refinement and term frequency (TF), TF–inverse document frequency (TF–IDF), and Latent Dirichlet Allocation (LDA) analyses. The number of blog posts in 2020 was nearly triple the number in 2019. Thus, the analysis period was divided into first (from 2014 to 2019) and second (from 2020 to 31 July 2023) periods. The TF–IDF analysis showed that shooting, photo, diet, exercise, goal, and challenge were among the top words in the first period, while Instagram-related words were mosr frequent in the second period. This finding suggested that social distancing policies significantly affected social media usage. The LDA analysis revealed five topics that were common in the first and second periods and three topics that emerged in the second period. Overall, while Western societies tend to idealize specific body types, body image discourse in Korea is centered around exercise as a means to achieve "photography" or "photo shoot"-related goals. Exercise is perceived as an activity performed for pleasure rather than attaining a particular body shape. Furthermore, there is a desire to document one's body beautifully and maintain exercise habits in the long run. The results of this study could serve as foundational material for establishing and sustaining a positive body image culture. [ABSTRACT FROM AUTHOR]

The rise of social media has changed how people view connections. Machine Learning (ML)-based sentiment analysis and news categorization help understand emotions and access news. However, most studies focus on complex models requiring heavy resources and slowing inference times, making deployment difficult in resource-limited environments. In this paper, we process both structured and unstructured data, determining the polarity of text using the TextBlob scheme to determine the sentiment of news headlines. We propose a Stochastic Gradient Descent (SGD)-based Ridge classifier (RC) for blending SGDR with an advanced string processing technique to effectively classify news articles. Additionally, we explore existing supervised and unsupervised ML algorithms to gauge the effectiveness of our SGDR classifier. The scalability and generalization capability of SGD and L2 regularization techniques in RCs to handle overfitting and balance bias and variance provide the proposed SGDR with better classification capability. Experimental results highlight that our string processing pipeline significantly boosts the performance of all ML models. Notably, our ensemble SGDR classifier surpasses all state-of-the-art ML algorithms, achieving an impressive 98.12% accuracy. McNemar's significance tests reveal that our SGDR classifier achieves a 1% significance level improvement over K-Nearest Neighbor, Decision Tree, and AdaBoost and a 5% significance level improvement over other algorithms. These findings underscore the superior proficiency of linear models in news categorization compared to tree-based and nonlinear counterparts. This study contributes valuable insights into the efficacy of the proposed methodology, elucidating its potential for news categorization and sentiment analysis. [ABSTRACT FROM AUTHOR]

With the rapid growth of smart terminal industry and User-Generated Content products, Social Media Applications (SMA) products, represented by TikTok, have been booming growth. How to capture and maintain users' attention in order to prolong their stay on the product and increase customer stickiness has become the focus of the industry. Therefore, according to the duration and characteristics of users using SMA, this paper takes the layout of SMA as an example to study the visual attention quality. Firstly, through the literature review, the study of visual attention quality in SMA was summarized into four aspects, including the span, maintenance, allocation, and switch of attention. Secondly, eye movement and behavior experiments were designed based on common content consumption tasks of SMA users to verify the hypotheses proposed in this paper. According to the results: (1) In terms of attention maintenance, linear layout outperformed masonry layout, masonry layout outperformed matrix layout, and in terms of attention span, the reverse was true; (2) In attention allocation, linear layout showed the best anti-interference characteristics; The masonry layout is suitable to be used in the task search stage and also in the dual-task execution stage; (3) In terms of attention switch, the energy cost of attention switch increased in the order of matrix layout, masonry layout and linear layout. (4) In terms of interaction, double-clicking interaction had more advantages in attention allocation and cognitive load than swiping interaction. The research in this paper has provided objective and quantitative data support for the design and operation of SMA products. [ABSTRACT FROM AUTHOR]

This paper presents an evolutionary game model of the "government‐platform‐platform user" based on the assumption of bounded rationality. The model explores the copyright governance mechanism of user‐generated content (UGC) in China by analyzing the strategic interaction between managers and the managed and the influence of various factors. The findings highlight that the government plays a leading role in the governance mechanism of UGC copyright, and the participation of the platform, as the direct manager of information content, can greatly improve the efficiency of supervision. Increasing government penalties, reducing excess revenue from passive platform filtering, and imposing additional payments for users' infringing use can expedite the adoption of evolutionary stability strategies. Furthermore, there exists a practical threshold for government incentives for platforms. Therefore, the construction and optimization of the UGC copyright governance mechanism need to be supported by a dynamic and coordinated reward and punishment system, diversified business objectives, and continuously improving users' copyright awareness. [ABSTRACT FROM AUTHOR]