社会化推荐系统的研究进展综述

对社会网络环境下构建个性化推荐系统的现有技术进行综述。介绍社会网络的基本概念,简述推荐系统的应用领域和目前面临的挑战,重点介绍社会化推荐的相关技术的研究现状,包括用户生成内容、社会化标签推荐、博客挖掘和基于信任的推荐,分析社会化推荐面临的主要问题。利用Web 2．0环境下的用户生成内容,为解决用户配置和冷启动问题提供一个研究方向。     

The state-of-the-art in personalized recommender systems for social networking

With the explosion of Web 2.0 application such as blogs, social and professional networks, and various other types of social media, the rich online information and various new sources of knowledge flood users and hence pose a great challenge in terms of information overload. It is critical to use intelligent agent software systems to assist users in finding the right information from an abundance of Web data. Recommender systems can help users deal with information overload problem efficiently by suggesting items (e.g., information and products) that match users’ personal interests. The recommender technology has been successfully employed in many applications such as recommending films, music, books, etc. The purpose of this report is to give an overview of existing technologies for building personalized recommender systems in social networking environment, to propose a research direction for addressing user profiling and cold start problems by exploiting user-generated content newly available in Web 2.0.     

How Trust and Need Satisfaction Motivate Producing User-Generated Content

The motivation of user-generated content (UGC) is a vital issue for social media providers. This study investigates this issue using the self-determination theory (SDT). The SDT identifies three fundamental human psychological needs, namely the need for competence, autonomy, and relatedness. This study aims to answer the question of how the satisfaction of these needs motivates users to produce UGC and utilizes the multi-study model comparison approach. Two survey studies were conducted in China and the United States. The partial least squares (PLS) analyses confirmed that the SDT indeed explained UGC motivation significantly and that trust beliefs support people’s need for relatedness. Post hoc analyses showed that there were significant differences between Chinese and American culture. Those results make important contributions to theory and practice. For example, practitioners need to motivate users to produce UGC by supporting their psychological needs. Besides, different trust beliefs should be emphasized in different countries.     

Analyzing sentiments in Web 2.0 social media data in Chinese: experiments on business and marketing related Chinese Web forums

Web 2.0 has brought a huge amount of user-generated, social media data that contains rich information about people’s opinions and ideas towards various products, services, and ongoing social and political events. Nowadays, many companies start to look into and try to leverage this new type of data to understand their customers in order to make better business strategies and services. As a nation with rapid economic growth in recently years, China has become visible and started to play an important role in the global business and economy. Also, with the large number of Chinese Internet users, a considerable amount of options about Chinese business and market have been expressed in social media sites. Thus, it will be of interest to explore and understand those user-generated contents in Chinese. In this study, we develop an integrated framework to analyze user sentiments from Chinese social media sites by leveraging sentiment analysis techniques. Based on the framework, we conduct experiments on two popular Chinese Web forums, both related to business and marketing. By utilizing Elastic Net together with a rich body of feature representations, we achieve the highest F-measures of 84.4 and 86.7 % for the two data sets, respectively. We also demonstrate the interpretability of Elastic Net by discussing the top-ranked features with positive or negative sentiments.     

New members’ online socialization in online communities: The effects of content quality and feedback on new members’ content-sharing intentions

Online communities’ viability and success are dependent on current members’ active participation and content contribution, as well as on the sustainable community registration of new members. Based on the member-life cycle perspective, this study attempted to discover mechanisms that might be employed to increase new members’ community participation. This study focused on user-generated content (UGC) sharing. The results of this study suggest that UGC quality gaps that exist between current and new members are important factors that might affect new members’ socialization. In addition, the results demonstrated that feedback provided by members can affect new members’ participation when UGC quality gaps exist. The results revealed that new members preferred an equivalent UGC community to either a superior or inferior community when they were unable to derive benefits from those communities. However, an investigation of the types of feedback provided revealed that new members expressed preferences for superior UGC communities to obtain learning opportunities and expressed preferences for inferior UGC communities to develop social relationships. This study can help researchers better understand how UGC communities’ elements can affect new members’ behaviors. In addition, the results can help community managers devise differentiated approaches.     

Multilingual sentiment analysis: from formal to informal and scarce resource languages

The ability to analyse online user-generated content related to sentiments (e.g., thoughts and opinions) on products or policies has become a de-facto skillset for many companies and organisations. Besides the challenge of understanding formal textual content, it is also necessary to take into consideration the informal and mixed linguistic nature of online social media languages, which are often coupled with localised slang as a way to express ‘true’ feelings. Due to the multilingual nature of social media data, analysis based on a single official language may carry the risk of not capturing the overall sentiment of online content. While efforts have been made to understand multilingual sentiment analysis based on a range of informal languages, no significant electronic resource has been built for these localised languages. This paper reviews the various current approaches and tools used for multilingual sentiment analysis, identifies challenges along this line of research, and provides several recommendations including a framework that is particularly applicable for dealing with scarce resource languages.     

Integrating User-Generated Content and Pervasive Communications

This month's Works in Progress features eight projects that support the integration of user-generated content (UGC) in a world of pervasive communications. The projects range from AI-based UGC service discovery in the first essay to a semantically enriched information model that communication systems can use to deploy UGC in pervasive applications in the last essay. Other projects leverage the growing ubiquity of camera-equipped mobile phones, a global architecture that enriches hosted service-layer applications with user-generated contextual information, a mobile tourist-service application supporting tourism as a social activity, a prototype interactive digital TV application, and an access-control framework that captures information dynamically generated by customers of multiservice business areas.     

Co-creation and user-generated content–elderly people’s user requirements

There is an increasing demand on citizens to participate in social network websites and to create and share their own user-generated content (UGC), such as photographs, videos, and blogs. So far, little is known about how elderly people respond to these new trends and master the techniques required. This paper reports on three studies that investigated elderly people’s user requirements related to consumption, sharing and co-creation of UGC in new media. The first study, conducted in Norway, identifies patterns of Internet usage, age differences, and participation in online communities and the consumption, sharing and co-creation of UGC on a macro level. The second study, conducted in Belgium, investigated the social requirements of elderly people on a group level. The third study, also conducted in Belgium, investigated user and context requirements on an individual level. The results of the first study show that the elderly rarely participate in online communities and share audio-visual UGC. However, they embrace some aspects of the new media and more often express themselves politically. The results of the second study show that the elderly are very motivated to contribute with UGC, given the right circumstances. The results of the third study show that it is important for elderly people that they be able to use the new technologies easily and identifies their worries about using them.     

Trust perceptions of online travel information by different content creators: Some social and legal implications

Consumers are increasingly turning to the online environment to provide information to assist them in making purchase decisions related to travel products. They often rely on travel recommendations from different sources, such as sellers, independent experts and, increasingly, other consumers. A new type of online content, user-generated content (UGC), provides a number of legal and social challenges to providers and users of that content, especially in relation to areas such as defamation, misrepresentation and social embarrassment. This paper reports research that examined the level of trustworthiness of online travel information from these different sources. The study used a survey of Australian travel consumers (n = 12,000) and results support the notion that there are differences in the level of trust for online travel information from different sources. Respondents ‘tended to agree’ that they trusted information provided by travel agents, information from commercial operators and comments made by travellers on third party websites. However, the highest level of trust was afforded to information provided on State government tourism websites. These results suggest that greater trust is placed in online travel comments when they are on a specific travel website than when they are on a more generic social networking website. However, respondents were ‘not sure’ that they trusted comments made by travellers on weblogs and on social networking sites. Some 88% of respondents that had not visited UGC websites (or were unsure if they had) indicated that they thought that UGC would be useful in the future – suggesting that they feel that any concerns they may have in relation to legal and social problems resulting from its use will be resolved.     

Who interacts on the Web?: The intersection of users’ personality and social media use

In the increasingly user-generated Web, users’ personality traits may be crucial factors leading them to engage in this participatory media. The literature suggests factors such as extraversion, emotional stability and openness to experience are related to uses of social applications on the Internet. Using a national sample of US adults, this study investigated the relationship between these three dimensions of the Big-Five model and social media use (defined as use of social networking sites and instant messages). It also examined whether gender and age played a role in that dynamic. Results revealed that while extraversion and openness to experiences were positively related to social media use, emotional stability was a negative predictor, controlling for socio-demographics and life satisfaction. These findings differed by gender and age. While extraverted men and women were both likely to be more frequent users of social media tools, only the men with greater degrees of emotional instability were more regular users. The relationship between extraversion and social media use was particularly important among the young adult cohort. Conversely, being open to new experiences emerged as an important personality predictor of social media use for the more mature segment of the sample.     

Identifying interesting Twitter contents using topical analysis

Social media platforms such as Twitter are becoming increasingly mainstream which provides valuable user-generated information by publishing and sharing contents. Identifying interesting and useful contents from large text-streams is a crucial issue in social media because many users struggle with information overload. Retweeting as a forwarding function plays an important role in information propagation where the retweet counts simply reflect a tweet’s popularity. However, the main reason for retweets may be limited to personal interests and satisfactions. In this paper, we use a topic identification as a proxy to understand a large number of tweets and to score the interestingness of an individual tweet based on its latent topics. Our assumption is that fascinating topics generate contents that may be of potential interest to a wide audience. We propose a novel topic model called Trend Sensitive-Latent Dirichlet Allocation (TS-LDA) that can efficiently extract latent topics from contents by modeling temporal trends on Twitter over time. The experimental results on real world data from Twitter demonstrate that our proposed method outperforms several other baseline methods.     

Location and Trajectory Identification from Microblogs

Journal of Computer Science and Technology - The rapid development of social networks has resulted in a proliferation of user-generated content (UGC), which can benefit many applications. In this...     

The Personal is the Political: Internet Filtering and Counter Appropriation in the Islamic Republic of Iran

Issues of trust, privacy and security at the intersection of state intervention and the use of the internet both by ‘publics’ and by individuals for—from the State’s point of view- dispreferred purposes have been of great recent interest to researchers. This has been accompanied by a slowly developing concern for the way in which these issues pan out for people in non-Western cultures. Based on a study of Iranians living in urban centers, we examine the way in which culture, State institutions, technological infrastructure and practices intersect. Iran is a republic with a theocratic constitution and relatively strict regulation of private life. It has one of the highest rates of internet appropriation and social media use in the MENA region, but use is heavily mediated by state interventions, for instance the filtering of sites such as Facebook and Twitter. We show how young Iranians, due to restrictions on their private lives, learn from early age on to deal with illegal access techniques such as proxy servers and virtual private networks (VPNs). These access technologies are often used for private purposes such as contacting and meeting other genders. However, these capabilities become even more important when preparing to leave the country or to articulate their political dissatisfaction, specifically at moments of political unrest. We discuss and develop the concept of ‘counter-appropriation’ and the ‘counter-public’ to describe the practices of urban dwellers in circumventing increasingly more sophisticated intervention by the state security apparatus.

     

Monotone submodular subset for sentiment analysis of online reviews

Neural Computing and Applications - Along with online social media’s prosperity, the amount of user-generated reviews dramatically increases. The kinds of text-based user-generated content...     

Aligning principal and agent’s incentives: A principal–agent perspective of social networking sites

The viability of networked communities depends on the creation and disclosure of user-generated content and the frequency of user visitation (Facebook 10-K Annual Report, 2012). However, little is known about how to align the interests of user and social networking sites. In this study, we draw upon the principal-agent perspective to extend Pavlou et al.’s uncertainty mitigation model of online exchange relationships (2007) and propose an empirically tested model for aligning the incentives of the principal (user) and the agent (service provider). As suggested by Pavlou et al., we incorporated a multi-dimensional measure of trust: trust of provider and trust of members. The proposed model is empirically tested with survey data from 305 adults aged 20-55. The results support our model, delineating how real individuals with bounded rationality actually make decision about information disclosure under uncertainty in the social networking site context. There is show little to no relationship between online privacy concerns and information disclosure on online social network sites. Perceived benefits provide the linkage between the incentives of principal (user) and agent (provider) while usage intensity demonstrated the most significant impact on information disclosure. We argue that the phenomenon may be explained through Communication Privacy Management Theory. The present study enhances our understanding of agency theory and human judgment theory in the context of social media. Practical implications for understanding and facilitating online social exchange relationships are also discussed.     

用户评论的质量检测与控制研究综述

随着网络技术的发展,越来越多用户生成的内容（user-generated content）出现在网络应用中,其中,用户评论富含用户的观点,它们在网络环境中充当越来越重要的角色.据美国Cone公司2011年的调查报告,64%的用户在购买行为之前会参考已有的用户评论.因此,为用户提供准确、简洁和真实的评论是一个迫切且重要的任务.主要围绕评论质量评估、评论总结和垃圾评论检测这3个方面综述了国际上评论质量检测与控制的研究内容、技术和方法的研究进展.在此基础上,展望该领域的发展给出了可能的研究方向.     

Autonomy in information: pre-trial publicity,commercial media,and user generated content

When information is no longer scarce, what does this mean for a legal system? Will this effectively eliminate the possibility of an unbiased juror in the United States? This article will look at the history of pre-trial publicity cases and the impending effect of rapidly increasing technological outlets. I argue that greater media availability will not necessarily increase the biases of potential jurors. Instead, adopting the main argument from Yochai Benkler's, The Wealth of Networks, I posit that non-traditional, user-generated content (UGC) can solve a failure in the conventional mass media market. Looking at the sharing of information as an iterated game, I contend that non-commercial UGC creation is free from constraints imposed on for profit media. Paradoxically, it is this unorganized and unprofessional publicity that can remedy defects in the professional media market. Non-commercial media is more autonomous, allowing the coverage of opinions and viewpoints mainstream media outlets commonly fail to address. As these non-commercial firms successfully fill holes in traditional media reporting, new outlets will be encouraged to enter the market.     

Designing for video: investigating the contextual cues within viewing situations

The viewing of video increasingly occurs in a wide range of public and private environments via a range of static and mobile devices. The proliferation of content on demand and the diversity of the viewing situations means that delivery systems can play a key role in introducing audiences to contextually relevant content of interest whilst maximising the viewing experience for individual viewers. However, for video delivery systems to do this, they need to take into account the diversity of the situations where video is consumed, and the differing viewing experiences that users desire to create within them. This requires an ability to identify different contextual viewing situations as perceived by users. This paper presents the results from a detailed, multi-method, user-centred field study with 11 UK-based users of video-based content. Following a review of the literature (to identify viewing situations of interest on which to focus), data collection was conducted comprising observation, diaries, interviews and self-captured video. Insights were gained into whether and how users choose to engage with content in different public and private spaces. The results identified and validated a set of contextual cues that characterise distinctive viewing situations. Four archetypical viewing situations were identified: ‘quality time’, ‘opportunistic planning’, ‘sharing space but not content’ and ‘opportunistic self-indulgence’. These can be differentiated in terms of key contextual factors: solitary/shared experiences, public/private spaces and temporal characteristics. The presence of clear contextual cues provides the opportunity for video delivery systems to better tailor content and format to the viewing situation or additionally augment video services through social media in order to provide specific experiences sensitive to both temporal and physical contexts.     

The Future of Social Networks on the Internet: The Need for Semantics

Everyone on the Internet knows the buzzword social networking. Social networking services (SNS) usually offer the same basic functionalities: network of friends listings, person surfing, private messaging etc. With such features, SNSs demonstrate how the Internet continues to better connect people for various social and professional purposes. The fundamental problems with today's SNSs block their potential to access the full range of available content and networked people online. A possible solution is to build semantic social networking into the fabric of the next-generation Internet itself-interconnecting both content and people in meaningful ways. The semantic Web is a useful platform for linking and for performing operations on diverse person-and object-related data gathered from heterogeneous social networking sites. In the other direction, object-centered networks can serve as rich data sources for semantic Web applications.     

Habit formation in social media consumption: a case of political engagement

This study draw upon the theory of habit formation in consumption from macroeconomics to support the evidence on the existence of habit formation in social media consumption. Treating social media consumption as a form of digital good consumption and using aggregated weekly posts from the Facebook pages of a group of 12 politicians in the cabinet of Singapore, we verified through a non-separable recursive time model that social media consumption habits were developed among this group of politicians. This study further confirms the existence of reciprocity by validating habit formation in the social media consumption of citizens and followers of these politicians’ posts using time aggregated data of ‘likes’, ‘shares’ and ‘comments’. Further, this study shows the relationship between the strength of habit formation in social media consumption of politicians and citizens is positively correlated: the stronger the habit formation, the stronger the social capital reciprocity. Through these measurements, our analysis proved that political engagement in social media is a bi-directional habitual process and the use of a habit formation coefficient as a new parameter to measure ‘reciprocal engagement’ in social media provides a better understanding of the dynamic exchange between users of social media.