A tag-based personalized item recommendation system using tensor modeling and topic model approaches

This research falls in the area of enhancing the quality of tag-based item recommendation systems. It aims to achieve this by employing a multi-dimensional user profile approach and by analyzing the semantic aspects of tags. Tag-based recommender systems have two characteristics that need to be carefully studied in order to build a reliable system. Firstly, the multi-dimensional correlation, called as tag assignment <user, item, tag>, should be appropriately modelled in order to create the user profiles [1]. Secondly, the semantics behind the tags should be considered properly as the flexibility with their design can cause semantic problems such as synonymy and polysemy [2]. This research proposes to address these two challenges for building a tag-based item recommendation system by employing tensor modeling as the multi-dimensional user profile approach, and the topic model as the semantic analysis approach. The first objective is to optimize the tensor model reconstruction and to improve the model performance in generating quality rec-ommendation. A novel Tensor-based Recommendation using Probabilistic Ranking (TRPR) method [3] has been developed. Results show this method to be scalable for large datasets and outperforming the benchmarking methods in terms of accuracy. The memory efficient loop implements the n-mode block-striped (matrix) product for tensor reconstruction as an approximation of the initial tensor. The probabilistic ranking calculates the probabil-ity of users to select candidate items using their tag preference list based on the entries generated from the reconstructed tensor. The second objective is to analyse the tag semantics and utilize the outcome in building the tensor model. This research proposes to investigate the problem using topic model approach to keep the tags nature as the “social vocabulary” [4]. For the tag assignment data, topics can be generated from the occurrences of tags given for an item. However there is only limited amount of tags availa-ble to represent items as collection of topics, since an item might have only been tagged by using several tags. Consequently, the generated topics might not able to represent the items appropriately. Furthermore, given that each tag can belong to any topics with various probability scores, the occurrence of tags cannot simply be mapped by the topics to build the tensor model. A standard weighting technique will not appropriately calculate the value of tagging activity since it will define the context of an item using a tag instead of a topic.

Item reputation-aware recommender systems

Recommender systems provide personalized advice for customers online based on their own preferences, while reputation systems generate a community advice on the quality of items on the Web. Both systems use users’ ratings to generate their output. In this paper, we propose to combine reputation models with recommender systems to enhance the accuracy of recommendations. The main contributions include two methods for merging two ranked item lists which are generated based on recommendation scores and reputation scores, respectively, and a personalized reputation method to generate item reputations based on users’ interests. The proposed merging methods can be applicable to any recommendation methods and reputation methods, i.e., they are independent from generating recommendation scores and reputation scores. The experiments we conducted showed that the proposed methods could enhance the accuracy of existing recommender systems.

An efficient tagging data interpretation and representation scheme for item recommendation

A tag-based item recommendation method generates an ordered list of items, likely interesting to a particular user, using the users past tagging behaviour. However, the users tagging behaviour varies in different tagging systems. A potential problem in generating quality recommendation is how to build user profiles, that interprets user behaviour to be effectively used, in recommendation models. Generally, the recommendation methods are made to work with specific types of user profiles, and may not work well with different datasets. In this paper, we investigate several tagging data interpretation and representation schemes that can lead to building an effective user profile. We discuss the various benefits a scheme brings to a recommendation method by highlighting the representative features of user tagging behaviours on a specific dataset. Empirical analysis shows that each interpretation scheme forms a distinct data representation which eventually affects the recommendation result. Results on various datasets show that an interpretation scheme should be selected based on the dominant usage in the tagging data (i.e. either higher amount of tags or higher amount of items present). The usage represents the characteristic of user tagging behaviour in the system. The results also demonstrate how the scheme is able to address the cold-start user problem.

Social networks for volunteered geographic information - A case study of OpenStreetMap

The world of mapping has changed. Earlier, only professional experts were responsible for map production, but today ordinary people without any training or experience can become map-makers. The number of online mapping sites, and the number of volunteer mappers has increased significantly. The development of the technology, such as satellite navigation systems, Web 2.0, broadband Internet connections, and smartphones, have had one of the key roles in enabling the rise of volunteered geographic information (VGI). As opening governmental data to public is a current topic in many countries, the opening of high quality geographical data has a central role in this study. The aim of this study is to investigate how is the quality of spatial data produced by volunteers by comparing it with the map data produced by public authorities, to follow what occurs when spatial data are opened for users, and to get acquainted with the user profile of these volunteer mappers. A central part of this study is OpenStreetMap project (OSM), which aim is to create a map of the entire world by volunteers. Anyone can become an OpenStreetMap contributor, and the data created by the volunteers are free to use for anyone without restricting copyrights or license charges. In this study OpenStreetMap is investigated from two viewpoints. In the first part of the study, the aim was to investigate the quality of volunteered geographic information. A pilot project was implemented by following what occurs when a high-resolution aerial imagery is released freely to the OpenStreetMap contributors. The quality of VGI was investigated by comparing the OSM datasets with the map data of The National Land Survey of Finland (NLS). The quality of OpenStreetMap data was investigated by inspecting the positional accuracy and the completeness of the road datasets, as well as the differences in the attribute datasets between the studied datasets. Also the OSM community was under analysis and the development of the map data of OpenStreetMap was investigated by visual analysis. The aim of the second part of the study was to analyse the user profile of OpenStreetMap contributors, and to investigate how the contributors act when collecting data and editing OpenStreetMap. The aim was also to investigate what motivates users to map and how is the quality of volunteered geographic information envisaged. The second part of the study was implemented by conducting a web inquiry to the OpenStreetMap contributors. The results of the study show that the quality of OpenStreetMap data compared with the data of National Land Survey of Finland can be defined as good. OpenStreetMap differs from the map of National Land Survey especially because of the amount of uncertainty, for example because of the completeness and uniformity of the map are not known. The results of the study reveal that opening spatial data increased notably the amount of the data in the study area, and both the positional accuracy and completeness improved significantly. The study confirms the earlier arguments that only few contributors have created the majority of the data in OpenStreetMap. The inquiry made for the OpenStreetMap users revealed that the data are most often collected by foot or by bicycle using GPS device, or by editing the map with the help of aerial imageries. According to the responses, the users take part to the OpenStreetMap project because they want to make maps better, and want to produce maps, which have information that is up-to-date and cannot be found from any other maps. Almost all of the users exploit the maps by themselves, most popular methods being downloading the map into a navigator or into a mobile device. The users regard the quality of OpenStreetMap as good, especially because of the up-to-dateness and the accuracy of the map.

A weight based context analysis system to provide a required UMM service

Ubiquitous Computing is an emerging paradigm which facilitates user to access preferred services, wherever they are, whenever they want, and the way they need, with zero administration. While moving from one place to another the user does not need to specify and configure their surrounding environment, the system initiates necessary adaptation by itself to cope up with the changing environment. In this paper we propose a system to provide context-aware ubiquitous multimedia services, without user’s intervention. We analyze the context of the user based on weights, identify the UMMS (Ubiquitous Multimedia Service) based on the collected context information and user profile, search for the optimal server to provide the required service, then adapts the service according to user’s local environment and preferences, etc. The experiment conducted several times with different context parameters, their weights and various preferences for a user. The results are quite encouraging.

Sistema recomendador de recursos educativos para la enseñanza de las ciencias

Resumen: En el dominio de la educación existe gran cantidad y diversidad de material multimedial que puede ser utilizado en la enseñanza y que constituye una importante contribución al proceso enseñanzaaprendizaje. Mucho de este material es accesible a través de diferentes repositorios de objetos de aprendizaje, donde cada objeto tiene metadatos descriptivos. Estos metadatos permiten recuperar aquellos objetos que satisfagan no sólo el tema de la consulta, sino también el perfil de usuario, teniendo en cuenta sus características y preferencias. En este trabajo se presenta una propuesta de un sistema recomendador de objetos de aprendizaje que ayuda a un usuario a encontrar

A survey of location inference techniques on Twitter

The increasing popularity of the social networking service, Twitter, has made it more involved in day-to-day communications, strengthening social relationships and information dissemination. Conversations on Twitter are now being explored as indicators within early warning systems to alert of imminent natural disasters such earthquakes and aid prompt emergency responses to crime. Producers are privileged to have limitless access to market perception from consumer comments on social media and microblogs. Targeted advertising can be made more effective based on user profile information such as demography, interests and location. While these applications have proven beneficial, the ability to effectively infer the location of Twitter users has even more immense value. However, accurately identifying where a message originated from or author’s location remains a challenge thus essentially driving research in that regard. In this paper, we survey a range of techniques applied to infer the location of Twitter users from inception to state-of-the-art. We find significant improvements over time in the granularity levels and better accuracy with results driven by refinements to algorithms and inclusion of more spatial features.

Entity Linking for Web Search Queries

We consider the problem of linking web search queries to entities from a knowledge base such as Wikipedia. Such linking enables converting a user’s web search session to a footprint in the knowledge base that could be used to enrich the user profile. Traditional methods for entity linking have been directed towards finding entity mentions in text documents such as news reports, each of which are possibly linked to multiple entities enabling the usage of measures like entity set coherence. Since web search queries are very small text fragments, such criteria that rely on existence of a multitude of mentions do not work too well on them. We propose a three-phase method for linking web search queries to wikipedia entities. The first phase does IR-style scoring of entities against the search query to narrow down to a subset of entities that are expanded using hyperlink information in the second phase to a larger set. Lastly, we use a graph traversal approach to identify the top entities to link the query to. Through an empirical evaluation on real-world web search queries, we illustrate that our methods significantly enhance the linking accuracy over state-of-the-art methods.

Infra-estrutura para portal internet integrador de serviços

Esta tese surge no contexto de sistemas e serviços web. O objectivo é propor uma solução para o problema da integração de informação de diversas fontes, numa plataforma web única, personalizável e adaptável ao utilizador. Nos casos de empresas ou organizações que tenham para diferentes tarefas, diferentes sistemas de informação independentes, o problema da integração de informação surge com a necessidade de integração destes numa única interface disponibilizada aos seus utilizadores. A integração de serviços numa mesma interface pressupõe que haja comunicação entre um sistema central (que fornece a interface) e os diversos sistemas existentes (que detêm a totalidade – ou parte – da informação a apresentar). Assim, será necessário garantir a identidade do utilizador a cada um dos serviços apresentados, bem como assegurar que cada utilizador tem à sua disposição de forma centralizada, apenas e só a informação e operações a que realmente tem acesso em cada um dos sistemas. Trata-se de uma plataforma que pretende por um lado, fornecer a informação correcta e orientada ao utilizador e, por outro lado, garantir que a organização que suporta o sistema consegue informar e interagir com os seus utilizadores de forma mais eficaz. O cenário adoptado é a Universidade de Aveiro. Esta pretende disponibilizar uma plataforma electrónica, onde os diferentes interlocutores (alunos, docentes, funcionários, ex-alunos, etc.) possam ter acesso a informação dirigida e orientada aos seus interesses e funções na Universidade. De modo a que cada utilizador seja realmente visto como um utilizador único, serão estudados e comparados serviços de modelação de utilizador e perfis de utilizador. Será proposto um serviço de modelação de utilizador e uma lógica de criação de perfis de utilizador, distintos do existente no estado de arte. Esta lógica conjuga a personalização da interface por parte do utilizador, com a gestão de operações e definição de políticas de segurança por parte da organização, de forma independente relativamente ao sistema de informação subjacente.

O perfil do utilizador abusivo dos Serviços de Urgência Portugueses: um estudo no Hospital de São João

A afluência desmedida aos Serviços de Urgência é uma questão que acarreta preocupações a nível financeiro. Contribui para este fato, a mentalidade da população, que acredita que este serviço oferece mais facilidades de acesso, dispõe de mais recursos e fornece melhores cuidados de saúde. Novas medidas foram preconizadas, como o aumento das taxas moderadoras, para tentar travar este fenómeno. No entanto, apesar da descida dos episódios de urgência em cerca de 10%, em Portugal, estudos apontam para valores na ordem dos 30-35% de episódios não urgentes. Assim, torna-se importante que não só se enfatizem as novas medidas, como se eduque a população com vista à correta utilização destes serviços, através de campanhas de sensibilização. Torna-se, assim, necessário que se chegue ao perfil do utilizador abusivo. Para a identificação de um perfil de abusividade, foram solicitados dados de episódios de urgência ocorridos durante um período de 6 meses no Hospital de São João, tendo depois sido estimado um modelo de regressão logística. A metodologia permite identificar quais as características que influenciam uma utilização abusiva do serviço e quantificar o impacto de cada uma destas características na probabilidade de um utente apresentar um comportamento abusivo. Concluiu-se que, uma mulher entre os 18-30 anos, que resida em Vila Nova de Gaia, recorra à urgência durante a noite tendo-lhe sido atribuída uma pulseira azul e seja abrangida pelo Serviço Nacional de Saúde, apresenta 91,92% de probabilidade de utilizar este serviço de forma abusiva. Contrariamente, um homem com mais de 60 anos, residente na Maia, que recorra ao serviço durante o dia, esteja isento do pagamento de taxas moderadoras e seja abrangido pela ADSE, e lhe seja atribuída uma pulseira laranja, apresenta apenas 39,93% de probabilidade de ter um comportamento abusivo. Estes resultados são importantes para definir campanhas de sensibilização que diminuam comportamentos abusivos.

Estudo descritivo do perfil de utilizador da linha Saúde 24 com análise de impacto ao nível da eficiência, equidade e empowerment em comparação com o modelo inglês NHS Direct

RESUMO - A 8 de Maio de 2008 surgiu o centro de atendimento “Linha Saúde24” (S24) no sentido de modernizar o SNS, aproximando-o do cidadão. O serviço surge baseado no modelo inglês – o NHS Direct – que pode ser encarado como um serviço de informação telefónico apoiado por enfermeiros, disponível 24h por dia, concebido para expandir os serviços púbicos de acesso à rede prestadora de cuidados com intuito de aliviar a pressão da procura na rede de urgências hospitalares e médicos de família, assim como diluir as iniquidades regionais na prestação de serviços. A S24 assenta na perspectiva de ser um ponto de contacto inicial do utente com a rede de prestação de cuidados de saúde com capacidade de orientação. O objectivo da linha está na tentativa mais eficiente no uso dos recursos disponíveis, ao mesmo tempo que delega responsabilidade no cidadão na forma como este utiliza os recursos disponíveis, com melhor racionalização financeira na área da saúde aliada a uma melhor qualidade de serviço prestada e adequada, colocando os cidadãos no mesmo patamar, diluindo as dificuldades de acesso a aqueles que necessitam na tentativa de harmonizar e racionalizar o consumo de serviços de saúde. Esta estrutura permite ao cidadão conhecer melhor o seu estado de saúde e decidir mais acertadamente quanto à decisão a tomar. Com este estudo, e com base na literatura nacional e internacional, pretende-se descrever o perfil de utilizador que acede à S24 – definir o tipo de utilizador, disposição geográfica, motivos pelo qual acede ao serviço e qual o seu destino final, fazendo comparação com o perfil do NHS Direct. Assim, e com os dados obtidos, far-se-á uma avaliação preliminar em termos do contributo da linha S24 no que concerne à sua eficiência, equidade e empowerment dado ao utilizador. --- ------------------------------ABSTRACT - Saúde 24 (S24) is a national 24-hour health line initiated in May 2008 aiming at modernizing the Portuguese NHS by bringing it closer to the citizen. Indeed, S24 be seen as an initial contact point between the patient and the healthcare network, facilitating a better a management of health care demand. The service is inspired on the UK NHS Direct – a nurse-led telephone line to provide easier and faster advice information to people about health, illness and NHS services. It is expected to provide information so that people can deal with their health problems or their families´ on their own, with the purpose of reducing demand to A&E department and out-of-hours GP services. Additionally it can contribute to a reduction in regional inequities in healthcare provision through bringing health care advice to remote areas. The purpose of S24 is to handle more efficiently the available resources by enabling responsibilities in citizens. By doing so, S24 encourages a more appropriate use of available resources, with better financial outcomes and a better quality of care. It is meant, in terms of empowerment, to help people to be in control of their health and healthcare interactions by participating in the final decision. Based on quantitative data, this study defines the S24 caller user profile in terms of type, geographical reference, reasons for calling and outcome. This analysis allows us to perform a preliminary evaluation of the S24 in terms of its contribution to efficiency, equity and empowerment. Then the S24 is compared to

Étude de l’état de préparation organisationnelle à la Cyber santé en réadaptation

Introduction : La cyber santé (CS) a le potentiel d’améliorer l'efficience et l'efficacité des services de santé. Malgré cela, son adoption demeure problématique et jusqu’à 70 % des projets d’implantation échouent. Objectifs : Cette étude vise à évaluer l’état de préparation d’une organisation par rapport à la CS et à identifier les facteurs personnels qui influencent cet état. Méthode : Une étude transversale a été réalisée auprès de 137 cliniciens, 28 gestionnaires et 47 membres du personnel non clinique d’un centre de réadaptation à Montréal. Les participants ont répondu à un questionnaire auto administré sur l’état de préparation organisationnelle vis-à-vis la CS qui comprend trois sous échelles (Individu, Organisation et Technologie) avec chacune un score sur 100. Des données ont aussi été colligées sur le profil des utilisateurs, leur utilisation des technologies et leur style de réponse à la nouvelle information. Résultats : Les participants se perçoivent prêts à adopter la CS dans leur travail ( = 73.8, SD = 8.5) et perçoivent aussi favorablement les technologies disponibles ( = 73.8, SD = 7.2). Toutefois, le personnel perçoit le centre comme étant modérément prête ( = 66.6, SD = 9.8). La charge de travail perçue et la fonction au sein de l'organisation ont été identifiées comme ayant une influence sur l'état de préparation à la CS. Discussion : Ces résultats appuient la pertinence d’aborder l’état de préparation organisationnelle comme un concept multidimensionnel. À partir des résultats obtenus, des stratégies d'implantation adaptées ont pu être identifiées.

PROTECT_U: Un système communautaire pour la protection des usagers de Facebook

Article publié dans le journal « Journal of Information Security Research ». March 2012.

Présentation personnalisée des informations environnementales

Nous présentons dans cette thèse notre travail dans le domaine de la visualisation. Nous nous sommes intéressés au problème de la génération des bulletins météorologiques. Étant donné une masse énorme d’information générée par Environnement Canada et un utilisateur, il faut lui générer une visualisation personnalisée qui répond à ses besoins et à ses préférences. Nous avons développé MeteoVis, un générateur de bulletin météorologique. Comme nous avons peu d’information sur le profil de l’utilisateur, nous nous sommes basés sur les utilisateurs similaires pour lui calculer ses besoins et ses préférences. Nous utilisons l'apprentissage non supervisé pour regrouper les utilisateurs similaires. Nous calculons le taux de similarité des profils utilisateurs dans le même cluster pour pondérer les besoins et les préférences. Nous avons mené, avec l’aide d'utilisateurs n’ayant aucun rapport avec le projet, des expériences d'évaluation et de comparaison de notre outil par rapport à celui utilisé actuellement par Environnement Canada. Les résultats de cette évaluation montrent que les visualisation générées par MeteoVis sont de loin meilleures que les bulletins actuels préparés par EC.