Herd behavior in purchasing books online

Previous studies on informational cascades have stressed the importance of informational social influences in decision-making. When people use the product evaluations of others to indicate product quality on the Internet, online herd behavior occurs. This work presents four studies examining herd behavior of online book purchasing. The first two studies addressed how two cues frequently found on the Internet, i.e., star ratings and sales volume, influence consumer online product choices. The last two studies investigated the relative effectiveness of different recommendation sources. The experimental results demonstrated that subjects use the product evaluations and choices of others as cues in making purchasing book decisions on the Internet bookstore. Additionally, recommendations of other consumers exerted a greater influence on subject choices than recommendations of an expert. Finally, recommendations from recommender system influenced online consumer choices more than those from website owners. The results and implications of this research are discussed.     

The effects of social media based brand communities on brand community markers,value creation practices,brand trust and brand loyalty

Social media based brand communities are communities initiated on the platform of social media. In this article, we explore whether brand communities based on social media (a special type of online brand communities) have positive effects on the main community elements and value creation practices in the communities as well as on brand trust and brand loyalty. A survey based empirical study with 441 respondents was conducted. The results of structural equation modeling show that brand communities established on social media have positive effects on community markers (i.e., shared consciousness, shared rituals and traditions, and obligations to society), which have positive effects on value creation practices (i.e., social networking, community engagement, impressions management, and brand use). Such communities could enhance brand loyalty through brand use and impression management practices. We show that brand trust has a full mediating role in converting value creation practices into brand loyalty. Implications for practice and future research opportunities are discussed.     

Community building among deaf and hard of hearing people by using written language on social networking sites

Since D/deaf and hard-of-hearing users of social networking sites (SNSs) may have communication specificities in comparison to hearing people, we proposed a model for understanding what factors affect building online communities. The model includes written language skills, the frequency of written communication, online Deaf and hearing identity, and the tendency for community building. One-hundred-and-sixty-two German D/deaf and hard-of-hearing users completed an online questionnaire in German sign and written language. Evaluation of the model with structural equation modelling revealed three main findings. Firstly, identification with the hearing online world has a positive effect on written language skills, the frequency of written communication on SNSs and indirectly on the tendency to build online communities. Secondly, the frequency of written communication has a positive effect on the tendency to build community. Thirdly, a positive effect of online Deaf identity on the frequency of written communication was found. Our findings may aid in understanding that, despite possible technological constraints, both D/deaf and hard-of-hearing people communicate on SNSs in written language more frequently due to their identification either with the Deaf or hearing online world which results in an increased tendency to build online communities.     

基于图卷积神经网络的在线社区行为预测

在线知识社区中,问题的回答可以看作多个回答者用户(领域专家)之间的协作行为。协作行为在知识社区中通常是大规模地发生,协作行为预测对在线社交中领域专家的推荐有重要意义。基于在线知识社区中回答者用户之间的协作行为,构建以领域专家为节点,以他们之间的协作回答关系为边的协作网络。由于协作行为网络的构建与社交关系网络的构建上结构的相似性,可以将协作行为预测构建为协作网络中的链接预测问题。通过构建基于图卷积神经网络的链接预测模型,对在线知识社区中回答者用户的协作行为进行预测。基于“知乎”数据集的实验验证,与其他经典的预测方法进行比较时,发现提出的方法能够更加有效地预测在线知识社区中回答者用户之间的协作行为。     

How media choice affects learner interactions in distance learning classes

In this research we explore aspects of learning, social interaction and community across online learning, also known as distance learning, in higher education. We measure the impact of online social networking (OSN) software versus traditional learning management system (LMS) software. Guided by a theoretical model for how individuals learn and interact within online communities, we measure student perceptions of learning, social interaction and course community before and after our interventions. Survey instruments measure perceived learning, social interaction and community, which we further explore using social network analysis (SNA). Survey results identified that students experienced higher levels of perceived social interaction and course community and, overall, had higher levels of satisfaction with OSN software than those using LMS software. Along this line, SNA results corroborated that OSN software yielded a higher number of interactions, providing a more engaging learning experience.     

The importance of trust and community in developing and maintaining a community electronic network

Focusing on two rural cities in Minnesota, this paper analyses ways in which these communities have gone about providing information technology to their citizens. This paper will explain why one city has chosen to take an entrepreneurial approach to networking and the other city has chosen a more collaborative approach, promoting equal access for its citizens. Based on interviews, focus groups, and surveys in the two cities, we find that these divergent approaches are related to fundamental cultural differences in the two communities. One city seems to have a more pronounced reservoir of social capital, meaning that people in this community tend to be more trusting, have more cohesive social ties and are prone toward collaboration. Cooperation and social trust, particularly among community leaders, seem to have played large roles in triggering the development of a community electronic network. Moreover, we discover that political engagement and interpersonal trust among the citizenry in this city seem to be pivotal in sustaining and perpetuating the community endeavor.     

The role of atmospheric cues in online impulse-buying behavior

This study extends a stimulus–organism–response (S–O–R) model to include impulse-buying behavior, which plays a vital role in electronic shopping but has not gained much attention in e-commerce research. Grounding our research in environmental psychology, we test the effects of virtual atmospheric cues on online impulse-buying behavior and spending, via a consumer survey. The study applies elaborated mediating variables (shopping enjoyment and impulsiveness) to develop a structural model linking three categories of atmospheric cues of an electronic store (content, design, and navigation) to approach behavior variables (impulse-buying behavior and expenditure). The results support the validity of the S–O–R model in the context of online impulse-buying behavior and show a significant positive effect of two dimensions of virtual atmospheric cues (design and navigation).     

CSD: A multi-user similarity metric for community recommendation in online social networks

Communities are basic components in networks. As a promising social application, community recommendation selects a few items (e.g., movies and books) to recommend to a group of users. It usually achieves higher recommendation precision if the users share more interests; whereas, in plenty of communities (e.g., families, work groups), the users often share few. With billions of communities in online social networks, quickly selecting the communities where the members are similar in interests is a prerequisite for community recommendation. To this end, we propose an easy-to-compute metric, Community Similarity Degree (CSD), to estimate the degree of interest similarity among multiple users in a community. Based on 3460 emulated Facebook communities, we conduct extensive empirical studies to reveal the characteristics of CSD and validate the effectiveness of CSD. In particular, we demonstrate that selecting communities with larger CSD can achieve higher recommendation precision. In addition, we verify the computation efficiency of CSD: it costs less than 1 hour to calculate CSD for over 1 million of communities. Finally, we draw insights about feasible extensions to the definition of CSD, and point out the practical uses of CSD in a variety of applications other than community recommendation.     

Becoming Friends in Online Brand Communities: Evidence From China

With the aid of information technology, consumers have increasingly engaged in social interaction in online brand communities. How can these strangers make friends online? Drawing on embeddedness theory and media richness theory, we examine the antecedents and intermediate mechanisms of online friendship. We theorize that online brand community interactivity aided by instant messaging technology is the main driving force of online friendship, whereas social presence and a sense of yuan (a Chinese concept describing predetermined relations) mediate online friendship development. Online friendship in turn enhances consumer online brand community commitment. We test our conceptual model with a sample of consumers from Chinese online sporting goods forums. The results support our hypotheses and inform online brand community research and practice.     

Dual influence embedded social recommendation

Recommender systems are designed to solve the information overload problem and have been widely studied for many years. Conventional recommender systems tend to take ratings of users on products into account. With the development of Web 2.0, Rating Networks in many online communities (e.g. Netflix and Douban) allow users not only to co-comment or co-rate their interests (e.g. movies and books), but also to build explicit social networks. Recent recommendation models use various social data, such as observable links, but these explicit pieces of social information incorporating recommendations normally adopt similarity measures (e.g. cosine similarity) to evaluate the explicit relationships in the network - they do not consider the latent and implicit relationships in the network, such as social influence. A target user’s purchase behavior or interest, for instance, is not always determined by their directly connected relationships and may be significantly influenced by the high reputation of people they do not know in the network, or others who have expertise in specific domains (e.g. famous social communities). In this paper, based on the above observations, we first simulate the social influence diffusion in the network to find the global and local influence nodes and then embed this dual influence data into a traditional recommendation model to improve accuracy. Mathematically, we formulate the global and local influence data as new dual social influence regularization terms and embed them into a matrix factorization-based recommendation model. Experiments on real-world datasets demonstrate the effective performance of the proposed method.     

基于用户邻域和主题的新颖性Web社区推荐方法

社区推荐从海量社区中为用户过滤出有价值的社区,变得越来越重要.新颖性推荐逐渐得到关注,因为单纯追求准确度的推荐结果存在局限性.已有新颖性推荐方法不适用于社区推荐,因其无法处理Web社区特性,包括社区成员用户通过交互形成的关系网络以及社区主题.提出了一种新颖性社区推荐方法NovelRec,向用户推荐其有潜在兴趣但不知道的社区,旨在拓展用户视野和推动社区发展.NovelRec基于用户交互网络中的邻域关系,利用用户之间在主题上的关联,计算候选社区对用户的准确度;根据用户与社区在邻域和主题上的关联,提出一种用户社区距离度量方式,并利用该距离计算候选社区的新颖度.在此基础上,NovelRec最终进行新颖性社区推荐,并兼顾推荐结果的准确性.真实数据集上的对比实验结果表明,NovelRec方法在新颖性上优于现有方法,同时能够保证推荐结果的准确性.     

Make new friends or keep the old: Gender and personality differences in social networking use

The present study examined the influence of gender and personality on individuals’ use of online social networking websites such as Facebook and MySpace. Participants were 238 undergraduate students who reported being members of Facebook, MySpace, or both. Based on prior research examining online behavior, we expected that gender and scores on the Big Five personality scale would moderate online social networking behavior. The results supported our predictions. Specifically, men reported using social networking sites for forming new relationships while women reported using them more for relationship maintenance. Furthermore, women low in agreeableness reported using instant messaging features of social networking sites more often than women high in agreeableness, whereas men low in openness reported playing more games on social networking sites compared to men high in openness. Overall, these results indicate the importance of examining individual differences in online behavior.     

Who to follow recommendation in large-scale online development communities

ContextOpen source development allows a large number of people to reuse and contribute source code to the community. Social networking features open opportunities for information discovery, social collaborations, and improved recommendations of potential collaborators.ObjectiveOnline community and development platforms rely on social network features to increase awareness and attention among community members for improved collaborations. The objective of this work is to introduce an approach for recommending relevant users to follow. Follower networks provide means for informal information propagation. The efficiency and effectiveness of such information flows is impacted by the network structure. Here, we aim to understand the resilience of networks against random or strategic node removal.MethodSocial network features of online software development communities present a new opportunity to enhance online collaboration. Our approach is based on the automatic analysis of user behavior and network structure. The proposed ‘who to follow’ recommendation algorithm can be parametrized for specific contexts. Link-analysis techniques such as PageRank/HITS provide the basis for a novel ‘who to follow’ recommendation model.ResultsWe tested the approach using a GitHub-based dataset. Currently, users follow popular community members to get updates regarding their activities instead of maintaining personal relations. Thus, social network features require further improvements to increase reciprocity. The application of our ‘who to follow’ recommendation model using the GitHub dataset shows excellent results with respect to context-sensitive following recommendations. The sensitivity of GitHub’s follower network to random node removal is comparable with other social networks but more sensitive to follower authority based node removal.ConclusionLink-based algorithm can be used for context-sensitive ‘who to follow’ recommendations. GitHub is highly sensitive to authority based node removal. Information flow established through follower relations will be strongly impacted if many authorities are removed from the network. This underpins the importance of ‘central’ users and the validity of focusing the ‘who to follow’ recommendations on those users.     

How heterogeneous community engage newcomers? The effect of community diversity on newcomers’ perception of inclusion: An empirical study in social media service

Online communities that provide social media services need to engage newcomers so as to not lose them to competitors. This study examines the role of community diversity (in terms of perceived visible dissimilarity, perceived informational dissimilarity and perceived value dissimilarity) in influencing perceived inclusion of newcomers in the online community and the influence of such perception on newcomers’ engagement intention. The theoretical background on perceived inclusion is obtained from the optimal distinctiveness theory, which comprises of two dimensions, namely, social identification and perceived uniqueness. The results support the multiple roles of community diversity on a newcomer’s perceived inclusion. The findings of this study contribute to a better understanding of the effect of community diversity on newcomers’ engagement behavior, and provide recommendations on designing a personalized community diversity environment.     

A semantic social network-based expert recommender system

This research work presents a framework to build a hybrid expert recommendation system that integrates the characteristics of content-based recommendation algorithms into a social network-based collaborative filtering system. The proposed method aims at improving the accuracy of recommendation prediction by considering the social aspect of experts’ behaviors. For this purpose, content-based profiles of experts are first constructed by crawling online resources. A semantic kernel is built by using the background knowledge derived from Wikipedia repository. The semantic kernel is employed to enrich the experts’ profiles. Experts’ social communities are detected by applying the social network analysis and using factors such as experience, background, knowledge level, and personal preferences. By this way, hidden social relationships can be discovered among individuals. Identifying communities is used for determining a particular member’s value according to the general pattern behavior of the community that the individual belongs to. Representative members of a community are then identified using the eigenvector centrality measure. Finally, a recommendation is made to relate an information item, for which a user is seeking an expert, to the representatives of the most relevant community. Such a semantic social network-based expert recommendation system can provide benefits to both experts and users if one looks at the recommendation from two perspectives. From the user’s perspective, she/he is provided with a group of experts who can help the user with her/his information needs. From the expert’s perspective she/he has been assigned to work on relevant information items that fall under her/his expertise and interests.     

Discovery of Web user communities and their role in personalization

One of the major innovations in personalization in the last 20?years was the injection of social knowledge into the model of the user. The user is not considered an isolated individual any more, but a member of one or more communities. User communities have been facilitated by the striking advancements of electronic communications and in particular the penetration of the Web into people??s everyday routine. Communities arise in a number of different ways. Social networking tools typically allow users to proactively connect to each other. Alternatively, data mining tools discover communities of connected Web sites or communities of Web users. In this article, we focus on the latter type of community, which is commonly mined from logs of users?? activity on the Web. We recall how this process has been used to model the users?? interests and personalize Web applications. Collaborative filtering and recommendation are the most widely used forms of community-driven personalization. However, we examine a range of other interesting alternatives that are worth investigating further. This effort leads us naturally to the recent developments on the Web and particularly the advent of the social Web. We explain how this development draws together the different viewpoints on Web communities and introduces new opportunities for community-based personalization. In particular, we propose the concept of active user community and show how this relates to recent efforts on mining social networks and social media.     

Mediating roles of self-presentation desire in online game community commitment and trust behavior of Massive Multiplayer Online Role-Playing Games

Massive Multiplayer Online Role-Playing Games (MMORPGs), which allow simultaneous participation of several gamers, have attracted a great deal of attention recently. Since MMORPGs can be categorized as a type of online community, the behavior of MMORPGs users needs to be considered as the general behavior in online communities. However, previous studies of online communities did not pay enough attention to MMORPGs, in which users can express themselves by interacting actively through games and game avatars. Understanding the characteristics of MMORPGs as online game communities where users communicate and interact will allow games to be vitalized and users to be immersed in games in a more positive way. Hence, using self-presentation theory and social identity theory, this study examined the factors influencing self-presentation desire and the mediating role of self-presentation desire examined in terms of trust of and commitments to online game communities. The results showed that the interactivity in the spaces of MMORPGs had the biggest impacts on self-presentation desire; personal innovativeness and game design quality also was influential. The results also indicated that self-presentation desire caused trust of online games and eventually led to even stronger commitments to gamers.     

社会语义网社区发现标签传递算法研究

针对在线社会网络的特性和现有社区发现算法的不足,提出一种基于语义网技术的在线社会网络社区发现算法ISLPA(Improved Semantic Label Propagation Algorithm),即一种适用于大规模在线社会网络的社区发现和标识算法。ISLPA算法对语义标签算法SemTagP进行改进,在社区划分过程中将在线社会网络视为有向加权图,通过语义网和社会化标签技术,充分结合在线社会网络丰富的语义信息和网络拓扑特征进行社区划分。ISLPA算法不需要预先设定社区数量和大小,就能实现社区发现,并能根据标签自动识别划分的社区。算法接近线性时间复杂度,具有较高的效率。通过实验表明,ISLPA算法能有效划分和标识真实在线社会网络。     

The effect of gratifications derived from use of the social networking site Qzone on Chinese adolescents’ positive mood

Drawing from Uses and Gratifications Theory, this study explores the influence of the gratifications derived from use of the social networking site Qzone on Chinese adolescents’ positive mood. Qzone is the social networking site that is most preferred and used by Chinese adolescents. Hypothesized relationships are analyzed by structural equation analysis in a sample of 220 Chinese adolescents aged 14–19 with an online Qzone profile. Gratifications that Chinese adolescents receive from use of the online social network Qzone, such as socializing, information-seeking, and entertainment are found to have a significantly positive influence on their positive mood. Findings of this study extend the existing theoretical framework on the application of the Uses and Gratifications Theory to social networking sites. In addition, findings are in line with those of a number of authors who suggest that social networking site use may have positive consequences for teenagers. Theoretical and practical implications are discussed.     

基于两层社区混合计算的个性化推荐方法

社区发现在个性化推荐系统中有着良好的应用。考虑到具有联系的不同层次社区之间能够构成一种混合的计算模型(HCPR),将该混合计算模型从用户-项目关系图演化到三维立体混合计算模型中,采用不同的融合相似度分别构建项目层社区和用户层社区,并基于用户-项目之间关注-被关注关系定义混合计算层。提出了一种基于两层社区混合计算的个性化推荐方法,面对新用户、旧用户、新项目、旧项目的不同输入定义相应的计算,其能推荐较为精准、个性化的信息。在3种不同类型的数据集上进行了实验,结果表明该模型能够较好地表示用户之间、项目之间以及用户和项目之间的关系,与U-CF和I-CF的推荐方法相比,HCPR借助构建的混合计算层在保证推荐精确度的同时,推荐结果 更为 个性化。