Understanding the dynamics of politicians' visibility in traditional and social media

This study examines the extent to which politicians' visibility in traditional news coverage explains individual politicians' visibility on social media, and vice versa. We also explore whether these relationships depend on commonly identified characteristics of individual politicians. We collected data for all elected candidates from the 2012 Dutch national elections covering each 15 days prior to the election day (N = 2250). This includes 2736 newspaper articles and 77,597 mentions on Facebook and Twitter. Our results show that the traditional news agenda and social media agenda impact each other, but that the reciprocal influence is not independent of politician characteristics.     

Political persuasion on social media: A moderated moderation model of political discussion disagreement and civil reasoning

Abstract

Social media and news use arguably contribute to the prevalence of contentious politics because individuals may express dissent through their social networks as they consume news. This study seeks to test whether individuals might be more open to political persuasion in this context, especially if they are exposed to political disagreement or discuss politics in a civil manner. Relying on survey data from the UK, results based on a moderated moderation model show that (a) social media news use predicts political persuasion on social media (direct effects) and, (b) discussion disagreement and civil reasoning moderate this relationship in two-way and three-way interactions.     

面向语义缺失场景的社交媒体中热门新闻识别方法研究

[目的/意义]对社交媒体中热门新闻的及时识别,有助于加速正面资讯的投送或抑制负面资讯的扩散。当前,基于自然语言处理的传统识别方法正面临社交媒体新生态的挑战：大量新闻内容以图片、音视频形式存在,缺乏用于语义及情感分析的文本。[方法/过程]对此,本文首先将社交网络划分为众多社群,并按其层次结构组织为贝叶斯网络。接着,面向社群构建基于卷积神经网络的热门新闻识别模型,模型综合考虑新闻传播的宏观统计规律及微观传播过程,以提取社群内热门新闻传播的特征。最后,利用贝叶斯推理并结合局部性的模型识别结果进行全局性热度预测。[结果/结论]实验表明,本方法在语义缺失场景下可有效识别热门新闻,其准确度强于基于语义信息的机器学习方法,模型具有良好的时效性、可扩展性和适用性。该研究有助于社交媒体的监管机构及时识别出各类不含语义信息且迅速扩散的热点内容。     

Discourse-aware rumour stance classification in social media using sequential classifiers

Rumour stance classification, defined as classifying the stance of specific social media posts into one of supporting, denying, querying or commenting on an earlier post, is becoming of increasing interest to researchers. While most previous work has focused on using individual tweets as classifier inputs, here we report on the performance of sequential classifiers that exploit the discourse features inherent in social media interactions or ‘conversational threads’. Testing the effectiveness of four sequential classifiers – Hawkes Processes, Linear-Chain Conditional Random Fields (Linear CRF), Tree-Structured Conditional Random Fields (Tree CRF) and Long Short Term Memory networks (LSTM) – on eight datasets associated with breaking news stories, and looking at different types of local and contextual features, our work sheds new light on the development of accurate stance classifiers. We show that sequential classifiers that exploit the use of discourse properties in social media conversations while using only local features, outperform non-sequential classifiers. Furthermore, we show that LSTM using a reduced set of features can outperform the other sequential classifiers; this performance is consistent across datasets and across types of stances. To conclude, our work also analyses the different features under study, identifying those that best help characterise and distinguish between stances, such as supporting tweets being more likely to be accompanied by evidence than denying tweets. We also set forth a number of directions for future research.     

Identifying influencers on social media

The increased availability of social media big data has created a unique challenge for marketing decision-makers; turning this data into useful information. One of the significant areas of opportunity in digital marketing is influencer marketing, but identifying these influencers from big data sets is a continual challenge. This research illustrates how one type of influencer, the market maven, can be identified using big data. Using a mixed-method combination of both self-report survey data and publicly accessible big data, we gathered 556,150 tweets from 370 active Twitter users. We then proposed and tested a range of social-media-based metrics to identify market mavens. Findings show that market mavens (when compared to non-mavens) have more followers, post more often, have less readable posts, use more uppercase letters, use less distinct words, and use hashtags more often. These metrics are openly available from public Twitter accounts and could integrate into a broad-scale decision support system for marketing and information systems managers. These findings have the potential to improve influencer identification effectiveness and efficiency, and thus improve influencer marketing.     

企业政策导向对社交媒体交互影响的调节作用

本文研究企业的政策导向（分为鼓励导向和控制导向）对边界人员使用社交媒体行为的调节作用,并通过实证方法验证了社交媒体对企业影响的双面性。通过550家中国制造企业的调查数据的实证研究,我们发现（1）企业员工使用社交媒体进行更多的任务型和关系型交互行为均能够给企业带来更高的绩效,企业员工更多的任务型交互行为能够减少渠道成员的投机行为,但是更多的关系型交互行为则会导致渠道成员产生更多的投机行为;（2）企业的鼓励导向能够强化关系型交互行为与企业绩效之间的关系,而控制导向会弱化关系型交互行为与企业绩效之间的关系。（3）企业的鼓励导向能够分别强化任务型和关系型交互行为与投机行为之间的关系,控制导向能够弱化他们之间的关系。这些结论对理论研究和企业实际应用都有重要的意义。     

Characterizing multi-domain false news and underlying user effects on Chinese Weibo

False news that spreads on social media has proliferated over the past years and has led to multi-aspect threats in the real world. While there are studies of false news on specific domains (like politics or health care), little work is found comparing false news across domains. In this article, we investigate false news across nine domains on Weibo, the largest Twitter-like social media platform in China, from 2009 to 2019. The newly collected data comprise 44,728 posts in the nine domains, published by 40,215 users, and reposted over 3.4 million times. Based on the distributions and spreads of the multi-domain dataset, we observe that false news in domains that are close to daily life like health and medicine generated more posts but diffused less effectively than those in other domains like politics, and that political false news had the most effective capacity for diffusion. The widely diffused false news posts on Weibo were associated strongly with certain types of users — by gender, age, etc. Further, these posts provoked strong emotions in the reposts and diffused further with the active engagement of false-news starters. Our findings have the potential to help design false news detection systems in suspicious news discovery, veracity prediction, and display and explanation. The comparison of the findings on Weibo with those of existing work demonstrates nuanced patterns, suggesting the need for more research on data from diverse platforms, countries, or languages to tackle the global issue of false news. The code and new anonymized dataset are available at https://github.com/ICTMCG/Characterizing-Weibo-Multi-Domain-False-News.     

Detecting breaking news rumors of emerging topics in social media

Users of social media websites tend to rapidly spread breaking news and trending stories without considering their truthfulness. This facilitates the spread of rumors through social networks. A rumor is a story or statement for which truthfulness has not been verified. Efficiently detecting and acting upon rumors throughout social networks is of high importance to minimizing their harmful effect. However, detecting them is not a trivial task. They belong to unseen topics or events that are not covered in the training dataset. In this paper, we study the problem of detecting breaking news rumors, instead of long-lasting rumors, that spread in social media. We propose a new approach that jointly learns word embeddings and trains a recurrent neural network with two different objectives to automatically identify rumors. The proposed strategy is simple but effective to mitigate the topic shift issues. Emerging rumors do not have to be false at the time of the detection. They can be deemed later to be true or false. However, most previous studies on rumor detection focus on long-standing rumors and assume that rumors are always false. In contrast, our experiment simulates a cross-topic emerging rumor detection scenario with a real-life rumor dataset. Experimental results suggest that our proposed model outperforms state-of-the-art methods in terms of precision, recall, and F1.     

Effect of anger,anxiety, and sadness on the propagation scale of social media posts after natural disasters

Social media is widely used for sharing disaster-related information following natural disasters. Drawing on negativity bias theory, integrated crisis mapping model, and arousal theory, this study characterized the emotional responses of the public and tested the way emotional factors and influential users (with high numbers of followers and activeness) affect the number of reposts. Results indicated that after unpredictable earthquakes, the public showed negative responses, and negativity bias theory manifested especially when the posts came from influential users. During a typhoon or earthquake, the number of reposts grew as the number of anger-related words in posts increased. Anxiety- and typhoon-related posts from users with high numbers of followers negatively affected the number of reposts, whereas sadness-related posts had contrasting effects. These findings can help emergency managers formulate proper emotional response strategies after various natural calamities and help researchers test the abovementioned theories or models using real-word data from social media.     

An agnotological analysis of APIs: or,disconnectivity and the ideological limits of our knowledge of social media

Adopting an agnotological perspective, this article extends the critical literature on APIs (application programing interfaces) by systematically showing that social media APIs are largely blind to acts of disconnectivity such as unfriending and unliking. We do this through analysis of the traces of social media usage that are not accessible through APIs as gleaned from the technical documentation published for developers by 12 major SNSs. Our findings make two main contributions. First, we show for the first time that APIs offer virtually no access to data about disconnectivity. Second, we show that APIs offer a very limited historical perspective, particularly regarding disconnectivity. However, for types of users that might spend money on advertising, far more historical and disconnectivity-oriented information is accessible through the API. This has practical consequences for research and contributes to an agnotology of social media that sheds critical light on the advertiser-friendly atmosphere of connectivity that social media try to create.     

Identifying widely disseminated scientific papers on social media

Identifying widely disseminated papers (WDPs) on social media can help to understand dissemination mechanisms of scientific papers from academia to social media and assist in the formulation of public and science policy. This study applies machine learning methods to explore the possibility of identifying WDPs and to investigate the influence mechanisms of literature-related and social media-related features. A pre-task was first conducted to investigate whether the visibility of scientific papers on social media can be predicted, and the role of various features was analyzed. Then, we defined two predictive tasks for identifying WDPs before and after they are visible on social media. The performance of eight state-of-the-art algorithms was compared in three experiments against the dataset of the oncology field, and the contribution of literature-related and social media-related features in the tasks was explained based on the Shapley additional explanations (SHAP) value. The results show that XGBoost performs better than other algorithms, especially with an F1 score of 0.988 and AUC of 0.998 in the trend prediction task. Nearly all of the literature-related features have great effects on identifying long-term disseminated papers, and most social media-related features play more significant roles in identifying broadly mentioned papers. Moreover, journal features contribute more to identifying papers of social media visibility, while paper features, especially research topics, have a greater influence on identifying WDPs. The number and proportion of academic-related Twitter users have great impacts on the scale and duration of papers’ dissemination. The number and duration of first-generation tweets play critical roles in identifying broadly mentioned and long-term disseminated papers, respectively. This study provides profound insights into the influencing factors in the dissemination of papers from the scientific community to and across social media, and helps to understand the difference in knowledge propagation between academia and the public.     

A symbolic interactionism perspective of using social media for personal and business communication

Achieving the anticipated business benefits of a social medium is important as organizations diligently invest in different social media platforms. While much previous research assumes that social media helps organizations to communicate with customers, less is known about whether customers embrace using social media to interact with organizations. It is important to understand the role of social media for business communication from the customers’ perspective, as this may significantly deviate from the organizations’ own communicative intentions. In this exploratory case study of the Moon Struck hotel in China, we investigate both how customers interpret the hotel’s use of WeChat official account for business communication and how customers respond to messages received from Moon Struck’s WeChat account. Adopting a symbolic interactionism perspective, we surprisingly find that WeChat personal accounts and Moon Struck’s official account offer radically different meanings to followers. Specifically, WeChat personal account symbolizes a sociality-oriented meaning (e.g., relationship and image building), while Moon Struck’s WeChat official account symbolizes information broadcasting-related meaning (e.g., selling, advertising, and branding). Both technological features and the distance of relationships among users contribute to the constructed symbolic meaning of technology, subsequently affecting users’ WeChat use patterns. The theoretical implications of this study are discussed and recommendations are made for future research and practice.     

How social media brand pages contribute to functional conflict: The central role of commitment

Although brand pages on social media platforms are burgeoning, companies frequently have difficulty in sustaining customer relationships on their brand pages. Consequently, this study focuses on how a social media brand page develops customer commitment and encourages them to perceive that future conflicts with the company can be resolved for their mutual benefit. On the basis of a review of the literature on customer value theory and commitment, this study develops an integrative model that explores the antecedents of functional conflict and the boundary condition under which brand page commitment enhances functional conflict. The model is tested using data collected from 293 followers of brand pages on a social networking site. The results demonstrate the salient roles of customer values and commitment in determining customer perceptions of future conflicts. By shifting scholarly attention from economic outcomes characterized by purchase intention to relationship outcomes characterized by functional conflict, the findings contribute to the research of the business implications of social networking sites.     

Social media analytics – Challenges in topic discovery,data collection,and data preparation

Since an ever-increasing part of the population makes use of social media in their day-to-day lives, social media data is being analysed in many different disciplines. The social media analytics process involves four distinct steps, data discovery, collection, preparation, and analysis. While there is a great deal of literature on the challenges and difficulties involving specific data analysis methods, there hardly exists research on the stages of data discovery, collection, and preparation. To address this gap, we conducted an extended and structured literature analysis through which we identified challenges addressed and solutions proposed. The literature search revealed that the volume of data was most often cited as a challenge by researchers. In contrast, other categories have received less attention. Based on the results of the literature search, we discuss the most important challenges for researchers and present potential solutions. The findings are used to extend an existing framework on social media analytics. The article provides benefits for researchers and practitioners who wish to collect and analyse social media data.     

Understanding the efficiency of social media based crisis communication during hurricane Sandy

Rapid communication during extreme events is one of the critical aspects of successful disaster management strategies. Due to their ubiquitous nature, social media platforms are expected to offer a unique opportunity for crisis communication. In this study, about 52.5 million tweets related to hurricane Sandy posted by 13.75 million users are analyzed to assess the effectiveness of social media communication during disasters and identify the contributing factors leading to effective crisis communication strategies. Efficiency of a social media user is defined as the ratio of attention gained over the number of tweets posted. A model is developed to identify more efficient users based on several relevant features. Results indicate that during a disaster event, only few social media users become highly efficient in gaining attention. In addition, efficiency does not depend on the frequency of tweeting activity only; instead it depends on the number of followers and friends, user category, bot score (controlled by a human or a machine), and activity patterns (predictability of activity frequency). Since the proposed efficiency metric is easy to evaluate, it can potentially detect effective social media users in real time to communicate information and awareness to vulnerable communities during a disaster.     

我国社交化电子商务研究综述

随着社交媒体技术的快速发展,社交媒体技术与电子商务深度融合成为社交化电子商务。作为电子商务一种新的衍生方式,社交化电子商务越来越受到企业和学术界的广泛关注。本文详细阐述了社交化电子商务兴起的原因、发展的过程,并且对我们的社交化电子商务进行系统性地分类,最后总结归纳我国社交化电子商务的研究现状,为我国社交化电子商务持续健康地发展提供理论上的参考意见。     

Online news comments: Social network and emergent public

Abstract

The research on online news comments has been dominated by a normative approach and has centered on media engagement. Normativity and media dominance have also featured big in the theoretical discussions on the public sphere. This article presents a case study of online news comments, combining a novel methodological testing of social network hypotheses to examine user–user interactions in online comments with a conceptual discussion of the potential connections between social network research and theories of the public. The social network analysis in this study indicated that users (online commentators) do not constitute highly dense networks, although their relations can be studied as social networks. However, this analysis can only explore limited features of this online phenomenon and requires complementary methods. From a conceptual perspective, this article confirms the role of shared issue for a potential public and also emphasizes the importance of context, actors, and meanings for understanding the public.     

Gender-specific emotional characteristics of crisis communication on social media: Case studies of two public health crises

Understanding the effects of gender-specific emotional responses on information sharing behaviors are of great importance for swift, clear, and accurate public health crisis communication, but remains underexplored. This study fills this gap by investigating gender-specific anxiety- and anger-related emotional responses and their effects on the virality of crisis information by creatively drawing on social role theory, integrated crisis communication modeling, and text mining. The theoretical model is tested using two datasets (Changsheng vaccine crisis with 2,423,074 textual data and COVID-19 pandemic with 893,930 textual data) collected from Weibo, a leading social media platform in China. Females express significantly high anxiety and anger levels (p value<0.001) during the Changsheng fake vaccine crisis, while express significantly higher levels of anxiety during COVID-19 than males (p value<0.001), but not anger (p value=0.13). Regression analysis suggests that the virality of crisis information is significantly strengthened when the level of anger in posts of males is high or the level of anxiety in posts of females is high for both crises. However, such gender-specific virality differences of anger/anxiety expressions are violated once females have large numbers of followers (influencers). Furthermore, the gender-specific emotional effects on crisis information are more significantly enhanced for male influencers than female influencers. This study contributes to the literature on gender-specific emotional characteristics of crisis communication on social media and provides implications for practice.     

Web and social media usage by museums: Online value creation

This paper contributes to the understanding of online strategies in the context of museums as examples of cultural organisations, an underrepresented sector in the information management literature. It presents a theoretical framework for understanding the online strategies of museums’ use of Web and social media, their sources of online value (efficiency, novelty, lock-in, complementarities) and some measurements of Internet performance, such as the Alexa Internet ranking and the number of followers of museums in social media. This type of analysis has not been conducted before and the findings will help museum curators and managers of other cultural institutions to appreciate the impact of these technologies and to make better informed decisions regarding online strategies and resource allocation. In addition, the results of this research are applicable to similar organisations, such as archives and cultural exhibitions, as well as to other service organisations related to information, education and entertainment activities.