Collaborative filtering with facial expressions for online video recommendation

Online video recommender systems help users find videos suitable for their preferences. However, they have difficulty in identifying dynamic user preferences. In this study, we propose a new recommendation procedure using changes of users’ facial expressions captured every moment. Facial expressions portray the users’ actual emotions about videos. We can utilize them to discover dynamic user preferences. Further, because the proposed procedure does not rely on historical rating or purchase records, it properly addresses the new user problem, that is, the difficulty in recommending products to users whose past rating or purchase records are not available. To validate the recommendation procedure, we conducted experiments with footwear commercial videos. Experiment results show that the proposed procedure outperforms benchmark systems including a random recommendation, an average rating approach, and a typical collaborative filtering approach for recommendation to both new and existing users. From the results, we conclude that facial expressions are a viable element in recommendation.     

Fairness and devotion go far: Integrating online justice and value co-creation in virtual communities

Although building long-term, successful virtual communities is important, rare studies have examined both in- and extra-role value co-creation behaviors from the perspective of social exchange theory and equity theory. Specially, we incorporate five different online justice perceptions into our model and examine the mediating role of “sense of virtual community” between these perceived online justice antecedents and both in- and extra-role online value co-creation behavior (reflected by knowledge contribution and online community citizenship behaviors, respectively). We empirically examine the model using data from 278 members of virtual communities. The results reveal that perceived online justice leads to value co-creation behavior through sense of virtual community. The findings elicit several implications for theory and practice.     

在线科技合作社区的一个计算机支持系统

随着互联网的飞速发展,在线科技合作社区大量涌现,并在科学研究与技术开发中日益发挥重要作用。本文从在线社区集体智能的概念模型出发,提出一个针对在线科技合作社区的计算机支持系统框架,促进社区人员网络和知识网络的演化。本文所提的框架以社会网络站点和知识门户为基础,综合多项Web/Web 2.0技术,为在线科技合作社区提供较为全面的支持。     

Knowledge collaboration among physicians in online health communities: A transactive memory perspective

Knowledge teams have emerged in online health communities (OHCs) where physicians collaborate spontaneously with others through the Internet to gather knowledge. Knowledge collaboration (KC) facilitates physicians’ communication and the provision of better services to patients in today's medical environment. However, the underlying mechanism through which KC improves team performance in OHCs is not clear. This study aims to advance understanding of the KC process by exploring the role of the transactive memory system (TMS). Real operation data from 1071 teams in a leading OHC in China used to understand both the antecedent and consequences of the TMS and the interaction effects among different dimensions of TMS. The findings have demonstrated that leader's capital was a critical factor in KC by promoting the effective TMS development and further affect both team's process and outcome performance. Positive moderating effects of coordination on the relationship between credibility and performance are also found. This study reveals for the first time the role of KC in improving performance in online health markets from the TMS perspective. The findings provide theoretical guidance to physician–physician collaborative teams with guidelines on boosting chances for higher performance.     

Developing online health communities through digital media

Twenty-first century's advancement in information technologies and the emergence of online communities have considerably influenced the online communication channels between patients and health service providers. Online health communities are now popular venues for health information sharing, yet little is known about the benefits in developing countries such as Iran. The aim of this case is to investigate on online health communities in Iran and to have a better understanding of consumer's behaviour using health services. The case integrates social support theory and social media concepts with traditional consumer behaviour theory, notably satisfaction. Using a content analysis of three online health communities indicates the value of social media in developing service quality in health industry.     

A fine-grained and multi-context-aware learning path recommendation model over knowledge graphs for online learning communities

Existing approaches to learning path recommendation for online learning communities mainly rely on the individual characteristics of users or the historical records of their learning processes, but pay less attention to the semantics of users’ postings and the context. To facilitate the knowledge understanding and personalized learning of users in online learning communities, it is necessary to conduct a fine-grained analysis of user data to capture their dynamical learning characteristics and potential knowledge levels, so as to recommend appropriate learning paths. In this paper, we propose a fine-grained and multi-context-aware learning path recommendation model for online learning communities based on a knowledge graph. First, we design a multidimensional knowledge graph to solve the problem of monotonous and incomplete entity information presentation of the single layer knowledge graph. Second, we use the topic preference features of users’ postings to determine the starting point of learning paths. We then strengthen the distant relationship of knowledge in the global context using the multidimensional knowledge graph when generating and recommending learning paths. Finally, we build a user background similarity matrix to establish user connections in the local context to recommend users with similar knowledge levels and learning preferences and synchronize their subsequent postings. Experiment results show that the proposed model can recommend appropriate learning paths for users, and the recommended similar users and postings are effective.     

Investigating and counteracting popularity bias in group recommendations

Popularity bias is an undesirable phenomenon associated with recommendation algorithms where popular items tend to be suggested over long-tail ones, even if the latter would be of reasonable interest for individuals. Such intrinsic tendencies of the recommenders may lead to producing ranked lists, in which items are not equally covered along the popularity tail. Although some recent studies aim to detect such biases of traditional algorithms and treat their effects on recommendations, the concept of popularity bias remains elusive for group recommender systems. Therefore, in this study, we focus on investigating popularity bias from the view of group recommender systems, which aggregate individual preferences to achieve recommendations for groups of users. We analyze various state-of-the-art aggregation techniques utilized in group recommender systems regarding their bias towards popular items. To counteract possible popularity issues in group recommendations, we adapt a traditional re-ranking approach that weighs items inversely proportional to their popularity within a group. Also, we propose a novel popularity bias mitigation procedure that re-ranks items by incorporating their popularity level and estimated group ratings in two distinct strategies. The first one aims to penalize popular items during the aggregation process highly and avoids bias better, while the second one puts more emphasis on group ratings than popularity and achieves a more balanced performance regarding conflicting goals of mitigating bias and boosting accuracy. Experiments performed on four real-world benchmark datasets demonstrate that both strategies are more efficient than the adapted approach, and empowering aggregation techniques with one of these strategies significantly decreases their bias towards popular items while maintaining reasonable ranking accuracy.     

A rough set-based association rule approach for a recommendation system for online consumers

Increasing use of the Internet gives consumers an evolving medium for the purchase of products and services and this use means that the determinants for online consumers’ purchasing behaviors are more important. Recommendation systems are decision aids that analyze a customer's prior online purchasing behavior and current product information to find matches for the customer's preferences. Some studies have also shown that sellers can use specifically designed techniques to alter consumer behavior. This study proposes a rough set based association rule approach for customer preference analysis that is developed from analytic hierarchy process (AHP) ordinal data scale processing. The proposed analysis approach generates rough set attribute functions, association rules and their modification mechanism. It also determines patterns and rules for e-commerce platforms and product category recommendations and it determines possible behavioral changes for online consumers.     

构建团体标准有效性的专利制度研究

团体标准作为新兴产业制度安排,对产业发展的指导和引领作用越来越明显。然而,标准在其聚集的技术或制度形式下,往往受限于这些技术或制度,特别是技术标准。面对市场中所流行的"技术专利化、专利标准化"发展路径,通过建立团体专利制度来厘清专利与标准之间的动态转化问题显得尤为重要。     

Trolling in online communities: A practice-based theoretical perspective

The literature on trolling has viewed trolling as discrete instances of transgression undertaken by antagonistic individuals. We identify three main issues with current theorizations: diffuse definitions of “trolling,” blurred boundaries between trolling and other online anti-social behaviors, and the context dependency of trolling. To address these unresolved issues, we adopt a practice-based theoretical approach. Informed by this approach, we analyze trolling behaviors not as products of individuals' attitudes, values, and decisions, but rather as behaviors embedded within and occurring as part of social practices. Specifically, we conduct a practice-based theoretical analysis in a multi-site exploratory study involving online archival research and in-depth interviews with online community members. Based on this analysis, we propose that trolling be conceived as a constellation of three social practices: learning, assimilating, and transgressing. Also, we find that practices of trolling transgression can have a dual pro-social and anti-social impact in online communities.     

基于用户偏好的文献推荐系统

本系统基于模糊联想记忆神经网络,建立偏好评价模型,根据用户偏好对搜索引擎搜索到的候选文献进行评级,为用户推荐偏好值高的文献。本系统的学习模块采用PCA-CG算法和误差反向传播算法,以用户阅读过的基准文献和其对应评级作为训练样本,对用户偏好进行学习;推理模块根据学习到的模糊规则和隶属函数来计算候选文献的偏好值,并以偏好值排序,把偏好值高的文献推荐给用户。把该模型应用于信息技术类文献的检索,实验表明系统提供的推荐文献具有较高可信度。     

Relationships among community interaction characteristics,perceived benefits,community commitment,and oppositional brand loyalty in online brand communities

To stand up for the brands they support, members of brand communities develop “oppositional brand loyalty” towards other rival brands. This study identifies how the interaction characteristics of brand community affect the perceived benefits of community members, and whether the perceived benefits cause members to develop community commitment, as well as the relationship between community commitment and oppositional brand loyalty. This study examined members of online automobile communities in Taiwan, and obtained a total of 283 valid samples. The analytical results reveal that interaction characteristics of brand community make members perceive many benefits, with “brand community engagement” being the most noticeable. Furthermore, hedonic, social, and learning benefits are the main factors to form community commitments. When members have community commitments, they will form oppositional brand loyalty to other rival brands. Based on the analytical results, this study provides suggestions to enterprises regarding online brand community operations.     

Motivation for online impulse buying: A two-factor theory perspective

Impulse buying accounts for a large proportion of consumer shopping behavior in the bricks-and-mortar retail market. Online retailers also expect to profit from impulse buying. It is therefore interesting and beneficial to investigate the design elements of online stores and the sales promotion stimuli that e-retailers can use to either arouse consumers’ desire or decrease their self-control to evoke their purchase impulses. This study seeks to explicitly identify the factors associated with online store design and sales promotion stimuli that most affect online impulse buying behavior throughout the consumer decision-making process. Drawing on the two-factor theory, it successfully identifies the hygiene and motivation factors that trigger online impulse buying. The questionnaire responses of 239 valid respondents revealed that most of the hygiene factors are associated with the design of online stores, and all of the motivation factors are forms of sales promotion stimuli that effectively facilitate online impulse buying and present utilitarian or hedonic benefits to consumers. This study also identifies the most effective sales promotion stimuli and offers a comprehensive checklist for Web designers. Moreover, the distribution of motivation and hygiene factors for each stage of the EKB model is uneven, and some stages include only hygiene factors. The findings of this study demonstrate that the triggers of consumers’ online shopping behavior do not always apply to online impulse buying, and have important implications for impulse buying research and practice.     

基于模糊概念格的领先用户个性化知识推荐研究

针对创新社区日益增长的海量信息阻碍了用户对知识进行有效获取和创造的现状,将模糊形式概念分析（FFCA）理论应用于创新社区领先用户的个性化知识推荐研究。首先识别出创新社区领先用户并对其发帖内容进行文本挖掘得到用户——知识模糊形式背景,然后构建带有相似度的模糊概念格对用户偏好进行建模,最后基于模糊概念格和协同过滤的推荐算法为领先用户提供个性化知识推荐有序列表。以手机用户创新社区为例,验证了基于FFCA的领先用户个性化知识推荐方法的可行性,有助于满足用户个性化知识需求,促进用户更好地参与社区知识创新。     

基于系统动力学的线上供应链金融信用风险研究

在分析影响线上供应链金融信用风险因素以及其因果关系的基础上,运用系统动力学方法,建立各影响因素之间关系的系统动力学模型。根据融资主体、供应链运营状况、外部环境三个子系统,找出影响线上供应链金融信用风险的三方面因素。结论:研究系统动力学模型提出的对策,可降低线上供应链金融信用风险,为商业银行风险管理提供理论基础。     

一种基于支持向量机回归的推荐算法

随着电子商务的迅速发展，推荐系统与算法已经成为理论研究的热点。支持向量机是一种强大的分类工具，由其衍生出的支持向量机回归方法能很好地解决非线性回归问题。文中以电影推荐为例，引入支持向量机回归方法来分析项目的内容，构建用户模型，进而给出推荐。实验结果和理论分析表明这种推荐算法与传统协同过滤算法相比，能够明显提高推荐精度，并显著缩短了推荐所需时间；在大样本量情况下也能同样高效。     

A new deep graph attention approach with influence and preference relationship reconstruction for rate prediction recommendation

Graph neural networks have been frequently applied in recommender systems due to their powerful representation abilities for irregular data. However, these methods still suffer from the difficulties such as the inflexible graph structure, sparse and highly imbalanced data, and relatively shallow networks, limiting rate prediction ability for recommendations. This paper presents a novel deep dynamic graph attention framework based on influence and preference relationship reconstruction (DGA-IPR) for recommender systems to learn optimal latent representations of users and items. The entire framework involves a user branch and an item branch. An influence-based dynamic graph attention (IDGA) module, a preference-based dynamic graph attention (PDGA) module, and an adaptive fine feature extraction (AFFE) module are respectively constructed for each branch. Concretely, the first two attention modules concentrate on reconstructing influence and preference relationship graphs, breaking imbalanced and fixed constraints of graph structures. Then a deep feature aggregation block and an adaptive feature fusion operation are built, improving the network depth and capturing potential high-order information expressions. Besides, AFFE is designed to acquire finer latent features for users and items. The DGA-IPR architecture is formed by integrating IDGA, PDGA, and AFFE for users and items, respectively. Experiments reveal the superiority of DGA-IPR over existing recommendation models.     

电力系统继电保护装置远方在线操作的实现方法

随着电网规模的发展,变电站数量迅速增加,变电运行人员资源紧张问题突显。文章结合变电站监控系统、调度自动化系统、继电保护故障信息系统等二次系统的技术特点,以及无人值班运行管理模式的生产应用需求,开展远方切换定值区、投退软压板、查看和修改任意区定值、复归保护信号等操作,以提高工作效率、应对人力资源紧张的局面。     

An asynchronous collaborative search system for online video search

There are a number of multimedia tasks and environments that can be collaborative in nature and involve contributions from more than one individual. Examples of such tasks include organising photographs or videos from multiple people from a large event, students working together to complete a class project, or artists and/or animators working on a production. Despite this, current state of the art applications that have been created to assist in multimedia search and organisation focus on a single user searching alone and do not take into consideration the collaborative nature of a large number of multimedia tasks. The limited work in collaborative search for multimedia applications has concentrated mostly on synchronous, and quite often co-located, collaboration between persons. However, these collaborative scenarios are not always practical or feasible. In order to overcome these shortcomings we have created an innovative system for online video search, which provides mechanisms for groups of users to collaborate both asynchronously and remotely on video search tasks. In order to evaluate our system an user evaluation was conducted. This evaluation simulated multiple conditions and scenarios for collaboration, varying on awareness, division of labour, sense making and persistence. The outcome of this evaluation demonstrates the benefit and usability of our system for asynchronous and remote collaboration between users. In addition the results of this evaluation provide a comparison between implicit and explicit collaboration in the same search system.