Improving matching process in social network using implicit and explicit user information

Personalised social matching systems can be seen as recommender systems that recommend people to others in the social networks. However, with the rapid growth of users in social networks and the information that a social matching system requires about the users, recommender system techniques have become insufficiently adept at matching users in social networks. This paper presents a hybrid social matching system that takes advantage of both collaborative and content-based concepts of recommendation. The clustering technique is used to reduce the number of users that the matching system needs to consider and to overcome other problems from which social matching systems suffer, such as cold start problem due to the absence of implicit information about a new user. The proposed system has been evaluated on a dataset obtained from an online dating website. Empirical analysis shows that accuracy of the matching process is increased, using both user information (explicit data) and user behavior (implicit data).

The analysis of social capital in online social communities

Social networks have proven to be an attractive avenue of investigation for researchers since humans are social creatures. Numerous literature have explored the term “social networks” from different perspectives and in diverse research fields. With the popularity of the Internet, social networking has taken on a new dimension. Online social communities therefore have become an emerging social avenue for people to communicate in today’s information age. People use online social communities to share their interests, maintain friendships, and extend their so-called circle of “friends”. Likewise, social capital, also known as human capital, is an important theory in sociology. Researchers usually utilise social capital theory when they investigate the topic relating to social networks. However, there is little literature that can provide an explicit and strong assertion in that research area due to the complexity of social capital. This thesis therefore focuses on the issue related to providing a better understanding about the relationship between social capital and online social communities. To enhance the value within the scope of this analysis, an online survey was conducted to examine the effects of the dimensions of social capital: relational capital, structural capital, and cognitive capital, determining the intensity of using online social communities. The data were derived from a total of 350 self-selected respondents completing an online survey during the research period. The main results indicate that social capital exists in online social communities under normal circumstances. Finally, this thesis also presents three contributions for both theory and practice in Chapter 5. The main results contribute to the understanding of connectivity in the interrelationships between individual social capital exchange within online social networks. Secondly, social trust was found to have a weak effect in influencing the intensity of individuals using online social communities. Third, the perpetual role of information sharing has an indirect influence on individual users participating in online social communities. This study also benefits online marketing consultants as marketers can not only gain consumer information easier from online social communities but also this understanding assists in designing effective communication within online social communities. The cross-sectional study, the reliability of Internet survey data, and sampling issues are the major three limitations in this research. The thesis provides a new research model and recommends that the mediating effects, privacy paradox, and social trust on online social communities should be further explored in future research.

A people-to-people recommendation system using Tensor Space Models

Existing recommendation systems often recommend products to users by capturing the item-to-item and user-to-user similarity measures. These types of recommendation systems become inefficient in people-to-people networks for people to people recommendation that require two way relationship. Also, existing recommendation methods use traditional two dimensional models to find inter relationships between alike users and items. It is not efficient enough to model the people-to-people network with two-dimensional models as the latent correlations between the people and their attributes are not utilized. In this paper, we propose a novel tensor decomposition-based recommendation method for recommending people-to-people based on users profiles and their interactions. The people-to-people network data is multi-dimensional data which when modeled using vector based methods tend to result in information loss as they capture either the interactions or the attributes of the users but not both the information. This paper utilizes tensor models that have the ability to correlate and find latent relationships between similar users based on both information, user interactions and user attributes, in order to generate recommendations. Empirical analysis is conducted on a real-life online dating dataset. As demonstrated in results, the use of tensor modeling and decomposition has enabled the identification of latent correlations between people based on their attributes and interactions in the network and quality recommendations have been derived using the 'alike' users concept.

Online multiple profile manager for eHealth information sharing

Online social networks connect millions of people around the globe. These electronic bonds make individuals comfortable with their behaviours. Such positive signs of sharing information is useful phenomena requires consideration to establish a socio-scientific effect. Recently, many web users have more than one social networking account. This means a user may hold multiple profiles which are stored in different Social Network Sites (SNNs). Maintaining these multiple online social network profiles is cumbersome and time-consuming [1]. In this paper we will propose a framework for the management of a user's multiple profiles. A demonstrator, called Multiple Profile Manager (MPM), will be showcased to illustrate how effective the framework will be.

A people-to-people matching system using graph mining techniques

A people-to-people matching system (or a match-making system) refers to a system in which users join with the objective of meeting other users with the common need. Some real-world examples of these systems are employer-employee (in job search networks), mentor-student (in university social networks), consume-to-consumer (in marketplaces) and male-female (in an online dating network). The network underlying in these systems consists of two groups of users, and the relationships between users need to be captured for developing an efficient match-making system. Most of the existing studies utilize information either about each of the users in isolation or their interaction separately, and develop recommender systems using the one form of information only. It is imperative to understand the linkages among the users in the network and use them in developing a match-making system. This study utilizes several social network analysis methods such as graph theory, small world phenomenon, centrality analysis, density analysis to gain insight into the entities and their relationships present in this network. This paper also proposes a new type of graph called “attributed bipartite graph”. By using these analyses and the proposed type of graph, an efficient hybrid recommender system is developed which generates recommendation for new users as well as shows improvement in accuracy over the baseline methods.

Love hurts: The costly reality of online romance fraud

Online dating and romance scams continue to lure in Australians with figures this week showing people have lost more than A$23 million this year alone, with average individual losses at A$21,000 – three times higher than other types of fraud. The Australian Competition and Consumer Commission (ACCC) set up the Scam Disruption Project in August to help target those it believes have been caught in such scams. Over three months it sent 1,500 letters to potential victims in New South Wales and the Australian Capital Territory. The figures released this week show that 50 people have been scammed, losing a total A$1.7 million – that’s an average of A$34,000 per victim. Almost three quarters of the scams were dating and romance related, which saw it evolve into the number one category of fraud victimisation. Romance scams continue to pose a problem – despite the efforts of the police and ACCC – so why is it that people continue to fall for them?

Online self-disclosure across cultures: A study of Facebook use in Saudi Arabia and Australia

This research aimed to gain a sophisticated understanding of self-disclosure on Facebook across two distinctive cultures, Saudi Arabia and Australia. This study utilised an explanatory sequential mixed methods design, consisting of a quantitative phase followed by a qualitative phase. Findings from both quantitative and qualitative data provide a broad understanding of the types of information that people self-disclose on Facebook, identifies factors that have a significant influence (either positive or negative) on such disclosure, and explains how it is affected by one's national culture.

Construção da maternidade contemporânea e a participação em um grupo de suporte online no Facebook

Este estudo buscou contribuições da psicologia do desenvolvimento, pela perspectiva da psicologia evolucionista e sociocultural, para compreender a construção da maternidade contemporânea com uso do Facebook como suporte online. No último século ocorreram muitas transformações no papel social da mulher, o mercado de trabalho a incorporou, o nível de escolaridade aumentou, a taxa de natalidade caiu. Entretanto, a diminuição no número de filhos não reduziu o trabalho materno. Em contextos urbanos de grandes cidades, as famílias estendidas são menos frequentes. Em contraste, o uso de redes sociais, tipo Facebook, aumenta. O percentual de brasileiras (30-39 anos) que utiliza a internet supera 50%. Hipotetizou-se que redes sociais online podem complementar o apoio demandado pelas mães. Desse modo, entendendo que mulheres precisam de apoio para cuidar das crianças e que o mundo atual está interconectado através da internet, buscou-se abordar a maternidade contemporânea em sociedade urbana e a internet no contexto do suporte online à parentalidade. Foram feitos dois estudos com amostra de um grupo de suporte online para gestantes/mães no Facebook: 1) Análise de postagens coletadas (30 meses), objetivando compreender discurso materno e principais temas abordados; 2) Investigação da percepção sobre rede de apoio geral e online, como o apoio online pode ser conseguido, o que interessa às mães neste tipo de apoio e perfil sociodemográfico. O Estudo 1, analisou conteúdo de 2.510 postagens apontando dois grupos de categorias: psicológicas (45%) e não-psicológicas (55%). No primeiro, o discurso enquadra-se na teoria da constelação da maternidade de Daniel Stern: 1) vida crescimento (50%); 2) relacionar-se primário (8%); 3) matriz de apoio (40%); 4) reorganização da identidade (2%). O segundo indicou quatro categorias: 5) negócios/divulgação (54%); 6) desenvolvimento gestacional/parto (9%); 7) pós-parto (5%); 8) indicações/pedidos práticos (32%). O Estudo 2 apontou que as participantes têm idade média de 31,86 anos, 88,6% possui graduação completa, a maioria mora com companheiro, exerce atividade profissional remunerada e tem renda familiar mensal superior a 10 salários mínimos (48%). Os principais interesses estão nos temas relacionados à saúde e cuidados com bebê. A maioria indica que lê as postagens com mais frequência do que expõem suas dúvidas. Grande parte percebe o grupo online como uma ajuda importante no exercício da sua maternidade. A escala de apoio social (presencial) apresenta escores maiores do que a escala de apoio social online com diferença em todas as dimensões. A escala de apoio social online aponta que as dimensões apoio informacional e emocional apresentam escores maiores, revelando que a troca de informações e o encorajamento em momentos difíceis da vida parecem ser os mais relevantes, apontando, principalmente, que há diferença significativa entre a dimensão emocional e as demais dimensões da escala. Resumindo, o grupo de suporte online se mostrou uma importante ferramenta para compartilhar informações entre mulheres que estão passando pelo mesmo momento do ciclo vital, e o suporte online um instrumento relevante ao suporte à parentalidade, prestando-se a um serviço que não poderia ser imaginado décadas atrás. Novos estudos poderão aprofundar e ampliar os resultados desta investigação

Social networks applied to training

In this article, we address the importance and relevance that social networks exhibit in their use as an educational resource.  This relevance relies in the possibility of implementing new learning resources or increasing the level of the participant's connectivity, as well as developing learning communities.  Also, the risk entailed from their use is discussed, especially for the students that have a low technological education or those having excessive confidence on the media.  It is important to highlight that the educational use of social networks is not a simple extension or translation of the student's habitual, recreational use, but that it implies an important change in the roles given to teachers as well as learners; from accommodative learning environments that only encourage memorization to other environments that demand an active, reflective, collaborative and proactive attitude, that require the development/acquisition of technological as well as social abilities, aptitudes and values.  It is also important to highlight that a correct implementation and adequate use will not only foment formal learning, but also informal and non-formal learning.

SocialLDA:Scalable Topic Modeling in Social Networks

Thesis (Master's)--University of Washington, 2012

Adaptive Probabilistic Topic Models for Social Networks

Thesis (Master's)--University of Washington, 2012

Community Detection in Multi-Layer Networks

In the scope of the current thesis we review and analyse networks that are formed by nodes with several attributes. We suppose that different layers of communities are embedded in such networks, besides each of the layers is connected with nodes' attributes. For example, examine one of a variety of online social networks: an user participates in a plurality of different groups/communities – schoolfellows, colleagues, clients, etc. We introduce a detection algorithm for the above-mentioned communities. Normally the result of the detection is the community supplemented just by the most dominant attribute, disregarding others. We propose an algorithm that bypasses dominant communities and detects communities which are formed by other nodes' attributes. We also review formation models of the attributed networks and present a Human Communication Network (HCN) model. We introduce a High School Texting Network (HSTN) and examine our methods for that network.

CIP-OSN; Networks as Graphs

Curriculum Innovation Programme - Online Social Networks (UOSM2012) - Networks as Graphs

O uso das redes sociais online nas interações de produtores e receptores de televisão

This paper discusses the possibility of receiver’s participation in the production of television content mediated by online social networks. Buoyed by media convergence, this research demonstrates how the receiver has been working in online digital media such as TV can take advantage of the specific interaction between the medias to promote the creation of collaborative content, in which the user of social network may interfere the result of the product developed, becoming a new mediatic protagonist. Tool not so used for the production of television that slowly begins to enter the virtual reality, the forging of this new compose process would not only entertain the receiver, but also enrich the language and content television constantly criticized. This study shows the influence of the television medium in which is discussed online, the attitude still shy of the user in content production, and discusses the potential of social networks as a channel of communication between producers and receivers. This work is structured from the definition of social network, in addition to conducting the study what kind of interaction between TV and online social networks is practiced today. Finally, debate whether the potential interaction between TV and social networks is used to its fullest.

Online disclosure and privacy concerns: a study of Moroccan and American facebook users

In using online social networks to connect and interact with people has become extremely popular all around the world. Thelargest Social Networking Site (SNS), Facebook, offers its services in over 70 languages and increasingly relies oninternational users to grow its membership. Aiming to understand the role of culture in SNS participation, this study adopts a‘privacy calculus’ perspective to examine the differences in participation patterns between American and MoroccanFacebook users. Survey results show that Moroccans users disclose less on Facebook than US users, yet perceive moredamage should their privacy on Facebook be violated. American users, on the other hand, have lower privacy concerns, trustfellow SNS members and legal system more, and disclose more in their profile. From a practical standpoint, the resultsindicate that SNS providers cannot rely on the same methods to encourage user participation and disclosure in differentcountries.