Searching the Web involves more than sifting through a huge graph of pages and hyperlinks. Specific collaboration networks have emerged that serve domain-specific queries better by exploiting the principles and patterns that apply there. We continue this trend by suggesting heuristics and algorithms to mine the evolution of collaboration networks, to discover interesting roles played by entities. The first section of the dissertation introduces the concept of nurturers using the computer science research community as a case study, while the second section formulates three roles - scouts, promoters and connectors, played by ratings in collaborative filtering systems. Nurturers: Nurturing, a pervasive mammalian trait, naturally extends to most association networks that involve humans. The increased availability of digital and online data about associations lets researchers experiment with algorithms to gain insight into such phenomena. Consider some examples of nurturing: • Slashdot endorsement. Slashdot was not the first site to link to Firefox, but the publicity Firefox received from this association surely helped it become popular quickly. The phenomenon of many small websites crashing due to publicity received through Slashdot has become well known as the Slashdot Effect. • A VC (Venture Capitalist) seed-funding a new startup. This event has a high nurturing value if the startup’s valuation increases rapidly after the funding. • A blogger writing about a topic. Kim Cameron has nurtured the “Laws of Identity” topic if it later becomes the buzz in blog circles. A nurturer need not always be the innovator or originator. The evangelist who adopts a prodigal idea and launches it on its way to success can also be a nurturer. • A professor guiding his student through the art of scientific research and bootstrapping him into a vibrant research community. New nodes not only emerge around these nurturers, but also become important in the network. Knowing nurturers is useful especially in vertical search, where algorithms exploit the structure of specialized collaboration networks to make search more relevant: knowing early adopters of good web pages can make web-search fresher; a list of VCs ranked by their nurturing value is useful to people with new startup ideas; the list of top nurturers in computer science is a valuable resource for a student seeking to do research. This dissertation presents a framework for discovering nurturers by mining the evolution of an association network, and discusses heuristics and customizations that can be applied through a case study: finding the Best Nurturers in Computer Science Research. Roles of Ratings in Collaborative Filtering: Recommender systems aggregate individual user ratings into predictions of products or services that might interest visitors. The quality of this aggregation process crucially affects user experience and hence the effectiveness of recommenders in e-commerce. The dissertation presents a novel study that disaggregates global recommender performance metrics into contributions made by each individual rating, allowing us to characterize the many roles played by ratings in nearest neighbor collaborative filtering. In particular, we formulate three roles - scouts, promoters, and connectors that capture how users receive recommendations, how items get recommended, and how ratings of these two types are themselves connected (respectively). These roles find direct uses in improving recommendations for users, in better targeting of items, and most impor -tantly, in helping monitor the health of the system as a whole. For instance, they can be used to track the evolution of neighborhoods, to identify rating subspaces that do not contribute (or contribute negatively) to system performance, to enumerate users who are in danger of leaving, and to assess the susceptibility of the System to attacks such as shilling. The three rating roles presented here provide broad primitives to manage a recommender system and its community.

This thesis examines recommendation dialogue, in the context of dialogue strategy design for conversational recommender systems. The purpose of a recommender system is to produce personalized recommendations of potentially useful items from a large space of possible options. In a conversational recommender system, this task is approached by utilizing natural language recommendation dialogue for detecting user preferences, as well as for providing recommendations. The fundamental idea of a conversational recommender system is that it relies on dialogue sessions to detect, continuously update, and utilize the user's preferences in order to predict potential interest in domain items modeled in a system. Designing the dialogue strategy management is thus one of the most important tasks for such systems. Based on empirical studies as well as design and implementation of conversational recommender systems, a behavior-based dialogue model called bcorn is presented. bcorn is based on three constructs, which are presented in the thesis. It utilizes a user preference modeling framework (preflets) that supports and utilizes natural language dialogue, and allows for descriptive, comparative, and superlative preference statements, in various situations. Another component of bcorn is its message-passing formalism, pcql, which is a notation used when describing preferential and factual statements and requests. bcorn is designed to be a generic recommendation dialogue strategy with conventional, information-providing, and recommendation capabilities, that each describes a natural chunk of a recommender agent's dialogue strategy, modeled in dialogue behavior diagrams that are run in parallel to give rise to coherent, flexible, and effective dialogue in conversational recommender systems. Three empirical studies have been carried out in order to explore the problem space of recommendation dialogue, and to verify the solutions put forward in this work. Study I is a corpus study in the domain of movie recommendations. The result of the study is a characterization of recommendation dialogue, and forms a base for a first prototype implementation of a human-computer recommendation dialogue control strategy. Study II is an end-user evaluation of the acorn system that implements the dialogue control strategy and results in a verification of the effectiveness and usability of the dialogue strategy. There are also implications that influence the refinement of the model that are used in the bcorn dialogue strategy model. Study III is an overhearer evaluation of a functional conversational recommender system called CoreSong, which implements the bcorn model. The result of the study is indicative of the soundness of the behavior-based approach to conversational recommender system design, as well as the informativeness, naturalness, and coherence of the individual bcorn dialogue behaviors. / I denna avhandling undersöks rekommendationsdialog med avseende på utformningen av dialogstrategier f¨or konverserande rekommendationssystem. Syftet med ett rekommendationssystem är att generera personaliserade rekommendationer utifrån potentiellt användbara domänobjekt i stora informationsrymder. I ett konverserande rekommendationssystem angrips detta problem genom att utnyttja naturligt språkk och dialog för att modellera användarpreferenser, liksom för att ge rekommendationer. Grundidén med konverserande rekommendationssystem är att utnyttja dialogsessioner för att upptäcka, uppdatera och utnyttja en användares preferenser för att förutsäga användarens intresse för domänobjekten som modelleras i ett system. Utformningen av dialogstrategihantering är därför en av de viktigaste uppgifterna för sådana system. Baserat på empiriska studier, liksom på utformning och implementering av konverserande rekommendationssystem, presenteras en beteendebaserad dialogmodell som kallas bcorn. bcorns bas utgörs av tre konstruktioner, vilka alla presenteras i denna avhandling. bcorn utnyttjar ett preferensmodelleringsramverk (preflets) som stöder och anv¨ander sig av naturligt språk i dialog och tillåter deskriptiva, komparativa och superlativa preferensuttryck i olika situationer. Den andra komponenten i bcorn är dess interna meddelande-formalism pcql, som är en notation som kan beskriva preferens- och faktiska påståenden och frågor. bcorn är utformat som en generell rekommendationshanteringsstrategi med konventionella, informationsgivande och rekommenderande förmågor, som var och en beskriver naturliga delar av en rekommendationsagents dialogstrategi. Dessa delar modelleras i dialogbeteendediagram som exekveras parallellt för att ge upphov till koherent, flexibel och effektiv dialog i konverserande rekommendationssystem. Tre empiriska studier har utförts för att utforska problemkomplexet som utgör rekommendationsdialog och för att verifiera de lösningar som tagits fram inom ramen för detta arbete. Studie I är en korpusstudie i filmrekommendationsdomänen. Studien resulterar i en karakteristik av rekommendationsdialog, och utgör basen för en första prototyp av dialoghanteringsstrategi för rekommendationsdialog mellan människa och dator. Studie II är en slutanvändarutvärdering av systemet acorn som implementerar denna dialoghanteringsstrategi och resulterar i en verifiering av effektivitet och användbarhet av strategin. Studien resulterar också i implikationer som påverkar utformningen av den modell som används i bcorn. Studie III är en medhörningsutvärdering av det funktionella konverserande rekommendationssystemet CoreSong, som implementerar bcorn-modellen. Resultatet av studien indikerar att det beteendebaserade angreppssättet är funktionellt och att de olika dialogbeteendena i bcorn ger upphov till h¨og informationskvalitet, naturlighet och koherens i rekommendationsdialog.

In this thesis, we consider a distributed collaborative platform in which each peer hosts his private information, such as the URLs he liked or the news articles that grabbed his interest or videos he watched, on his own machine. Then, without relying on a trusted third party, the peer engages in a distributed protocol, combining his private data with other peers' private data to perform collaborative filtering. The main objective is to be able to receive personalized recommendations or other services such as a personalized distributed search engine. User-based collaborative filtering protocols, which depend on computing user-to-user similarity, have been applied to distributed systems. As computing the similarity between users requires the use of their private profiles, this raises serious privacy concerns. In this thesis, we address the problem of privately computing similarities between peers in collaborative platforms. Our work provides a private primitive for similarity computation that can make collaborative protocols privacy-friendly. We address the unique challenges associated with applying privacy-preserving techniques for similarity computation to dynamic large scale systems. In particular, we introduce a two-party cryptographic protocol that ensures differential privacy, a strong notion of privacy. Moreover, we solve the privacy budget issue that would prevent peers from computing their similarities more than a fixed number of times by introducing the notion of bidirectional anonymous channel. We also develop a heterogeneous variant of differential privacy that can provide different level of privacy to different users, and even different level of privacy to different items within a single user's profile, thus taking into account different privacy expectations. Moreover, we propose a non-interactive protocol that is very efficient for releasing a small and private representation of peers' profiles that can be used to estimate similarity. Finally, we study the problem of choosing an appropriate privacy parameter both theoretically and empirically by creating several inference attacks that demonstrate for which values of the privacy parameter the privacy level provided is acceptable.

Thesis (Ph. D.)--Ohio State University, 2009. / Title from first page of PDF file. Includes vita. Includes bibliographical references (p. 115-119).

Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2017-09-14T18:41:16Z No. of bitstreams: 1 dissertacao_saulo_toledo_recsys_uml.pdf: 2345909 bytes, checksum: dcaa7238380f7791f922778432a5b9ea (MD5) / Made available in DSpace on 2017-09-14T18:41:16Z (GMT). No. of bitstreams: 1 dissertacao_saulo_toledo_recsys_uml.pdf: 2345909 bytes, checksum: dcaa7238380f7791f922778432a5b9ea (MD5) Previous issue date: 2016-09-05 / Modelos UML são usados de várias formas na engenharia de software. Eles podem modelar desde requisitos até todo o software, e compreendem vários diagramas. O diagrama de classes, o mais popular dentre os diagramas da UML, faz uso de vários elementos UML e adornos, tais como abstração, interfaces, atributos derivados, conjuntos de generalização, composições e agregações. Atualmente, não há maneira fácil de encontrar este tipo de diagrama com base nestas características para a reutilização ou a aprendizagem por tarefas de exemplo. Por outro lado, Sistemas de Recomendação são ferramentas e técnicas que são capazes de descobrir os elementos mais adequados para um usuário, dentre muitos outros. Existem várias técnicas de recomendação, que usam informações dos elementos de várias maneiras, ao uso da opinião de outros usuários. Sistemas de recomendação já foram utilizados com sucesso em vários problemas de engenharia de software. Este trabalho tem como objetivo propor e avaliar (i) uma representação baseada em conteúdo para diagramas de classe e as preferências do usuário,(ii) um novo algoritmo de recomendação baseado no conhecimento, (iii) a aplicação deste algoritmo e outros dois outros do estado da arte para a recomendação de diagramas de classe UML e (iv) uma avaliação destas abordagens contra uma sugestão aleatória. Para atingir este objetivo, foi realizado um estudo de caso com estudantes de ciência da computação e egressos. Depois de comparar os algoritmos, os nossos resultados mostram que, para o nosso conjunto de dados, todos eles são melhores do que uma recomendação aleatória. / UML models are used in several ways in the software engineering. They can model from requirements to the entire software, and comprise several diagrams. The Class diagram, the most popular among the UML diagrams, makes use of several UML elements and adornments, such as abstraction, interfaces, derived attributes, generalization sets, compositions and aggregations. Currently, there is no easy way to find this kind of diagram based on these features for reuse or learning by example’s tasks, for instance. On the other hand, Recommender Systems are powerful tools and techniques that are able to discover the most appropriate elements to an user among many others. There are several recommender techniques, from using the elements’ information in several ways, to using other users’ opinions. Recommender systems were already used successfully in several software engineering problems, as discovering pieces of code to recommend (as methods, for example) and finding the best developer to work in certain software problems. This work aims to propose and evaluate (i) a content-based Recommender System’s representation for class diagrams’ features and user’s preferences, (ii) a new knowledge-based recommender algorithm, (iii) the application this algorithm and two other state of the art content-based ones to the recommendation of UML class diagrams and (iv) an evaluation of these approaches against a random suggestion. To achieve this goal, we conducted a case study with computer science students and egresses. After comparing the algorithms, our results show that, for our dataset, all of them are better than a random recommendation.

Atualmente, pesquisadores e acadêmicos têm beneficiado-se muito com o crescimento acelerado das tecnologias Web, pois os resultados de pesquisa podem ser publicados e acessados eletronicamente tão logo a mesma tenha sido realizada. Esta possibilidade é vantajosa na medida em que minimiza as barreiras de tempo e espaço associadas à publicação tradicional. Neste contexto, surgem as Bibliotecas Digitais como repositórios de dados que, além dos documentos digitais propriamente ditos, ou de apontadores para estes documentos, armazenam os metadados associados. Para permitir que diferentes Bibliotecas Digitais possam interoperar surgiu a Open Archives Initiative (OAI) e, para resolver a questão da padronização dos metadados utilizados pelos repositórios, foi criado o formato Dublin Core (DC). Por outro lado, a enorme quantidade de documentos digitais disponíveis na Web tem causado o fenômeno conhecido como “sobrecarga de informação”. Com o objetivo de suprir esta dificuldade, Sistemas de Recomendação têm sido propostos e desenvolvidos. Estes sistemas visam prover uma interface alternativa para tecnologias de filtragem e recuperação de informações, tendo como foco a predição daqueles itens ou partes da informação que o usuário acharia interessante e útil. Portanto, os Sistemas de Recomendação atuam baseados em personalização da informação sendo que as predições geralmente são realizadas utilizando-se um perfil de cada usuário. A personalização está relacionada com o modo pelo qual a informação e serviços podem ser ajustados às necessidades específicas de um usuário ou comunidade. Esta dissertação descreve um Sistema de Recomendação de artigos científicos, armazenados em bibliotecas digitais. Este sistema é dirigido à comunidade científica da área da Ciência da Computação. Tecnologicamente, o sistema proposto foi desenvolvido sob a perspectiva da Web Semântica, à medida que faz uso de suas tecnologias emergentes tais como: uso de metadados padrão para a descrição de documentos - Dublin Core, uso do padrão XML para a descrição do perfil do usuário - Currículo Lattes, e provedores de serviços e de dados (OAI) envolvidos no processo de geração das recomendações. Este trabalho ainda apresenta e discute alguns resultados de experimentos baseados em avaliações quantitativas e qualitativas de recomendações geradas pelo sistema. / Currently, researchers and academics have been benefited by the expressive growth of web technologies, due to the possibility of publishing and accessing research results as soon as they are achieved. This possibility is advantageous as it minimizes the time and space barriers that traditional publications present. In this context, Digital Libraries emerged as data repositories that, beyond digital documents or links to them, store associated metadata. To allow the interoperability among different Digital Libraries, the Open Archives Initiative (OAI) was defined and, to solve the problem of metadata standardization, the Dublin Core standard (DC) was created. On the other hand, the great amount of available digital documents in the Web has caused the phenomenon known as “information overload”. In order to avoid this difficulty, Recommender Systems have been proposed and developed. These systems intend to provide an alternative interface for information filtering and retrieval technologies, focusing on the prediction of items or information parts that are interesting and useful for the user. Therefore, Recommender Systems act based on information personalization, and the predictions are generally generated using each user’s profile. The personalization is related to the way the information and the provided services can be adjusted to the specific necessities of a user or community. This dissertation describes a Recommender System for scientific articles stored in digital libraries. This system is geared towards the Computer Science scientific community. Technologically, the proposed system was developed under the Semantic Web perspective, as it explores its emergent technologies such as: use of standard metadata for document description - Dublin Core, use of the XML standard for users’ profile description - Lattes Curriculum Vitae, and services and data providers (OAI) involved on the recommendations generation process. In addition, this work presents and discusses some experimental results; the experiments are based on quantitative and qualitative evaluations of recommendations generated by the system.

This thesis investigates the area of preference learning and recommender systems. We concentrated recommending on small e-commerce vendors and efficient usage of implicit feedback. In contrast to the most published studies, we focused on investigating multiple diverse implicit indicators of user preference and substantial part of the thesis aims on defining implicit feedback, models of its combination and aggregation and also algorithms employing them in preference learning and recommending tasks. Furthermore, a part of the thesis focuses on other challenges of deploying recommender systems on small e-commerce vendors such as which recommending algorithms should be used or how to employ third party data in order to improve recommendations. The proposed models, methods and algorithms were evaluated in both off-line and on-line experiments on real world datasets and on real e-commerce vendors respectively. Datasets are included to the thesis for the sake of validation and further research. Powered by TCPDF (www.tcpdf.org)

Configuração modelo de features é conhecida por ser uma atividade complexa, demorada e propensa a erros. Esta atividade torna-se ainda mais complicada quando envolve múltiplas partes interessadas no processo de configuração. Trabalhos de pesquisa têm proposto abordagens para ajudar na configuração de modelo de features, mas elas dependem de processos sistemáticos que restringem as decisões de alguns dos stakeholders. Neste trabalho, propomos uma nova abordagem para melhorar o processo de configuração multi-stakeholder, considerando as preferências dos stakeholders expressas através de restrições duras e brandas. Com base em tais preferências, recomendamos diferentes configurações de produto utilizando diferentes estratégias da teoria da escolha social. Nossa abordagem é implementada em uma ferramenta chamada SACRES, que permite criar grupos de stakeholders, especificar preferências dos stakeholders sobre uma configuração e gerar as configurações ideais. Realizamos um estudo empírico para avaliar a eficácia de nossas estratégias no que diz respeito à satisfação individual e justiça entre todos os stakeholders. Os resultados obtidos provem evidência de que estratégias em particular possuem melhor performance em relação à satisfação de grupo, chamadas average e multiplicative considerando as pontuações atribuídas pelos participantes e complexidade computacional. Nossos resultados são relevantes não só no contexto de Linha de Produto de Software, mas também para a Teoria da Escolha Social, dada a instanciação de estratégias de escolha social em um problema prático. / Feature model con guration is known to be a hard, error-prone and timeconsuming activity. This activity gets even more complicated when it involves multiple stakeholders in the con guration process. Research work has proposed approaches to aid multi-stakeholder feature model con guration, but they rely on systematic processes that constraint decisions of some of the stakeholders. In this dissertation, we propose a novel approach to improve the multi-stakeholder con guration process, considering stakeholders' preferences expressed through both hard and soft constraints. Based on such preferences, we recommend di erent product con gurations using di erent strategies from the social choice theory. Our approach is implemented in a tool named SACRES, which allows creation of stakeholder groups, speci cation of stakeholder preferences over a con guration and generation of optimal con guration. We conducted an empirical study to evaluate the e ectiveness of our strategies with respect to individual stakeholder satisfaction and fairness among all stakeholders. The obtained results provide evidence that particular strategies perform best with respect to group satisfaction, namely average and multiplicative, considering the scores given by the participants and computational complexity. Our results are relevant not only in the context software product lines, but also in the context of social choice theory, given the instantiation of social choice strategies in a practical problem.

O objetivo deste trabalho é estudar o efeito dos sistemas de recomendação em um site de vinhos, verificando se os resultados estão de acordo com a teoria long tail. Esta proposição prevê que em mercados online, os produtos de nicho podem representar uma parcela significativa do resultado de uma empresa. Uma das formas de explorar estas fontes de receitas é pelo uso adequado de sistemas de recomendação que auxiliem o consumidor a encontrar o que deseja. Neste trabalho são efetuados dois estudos de caso, o primeiro utiliza o coeficiente Gini para comparar a distribuição das vendas de duas empresas, sendo uma delas de comércio eletrônico, o segundo estudo de caso seleciona quatro tipos de sistemas de recomendação e compara seus desempenhos na sugestão de vinhos. Os resultados indicam que ocorre um comportamento do tipo long tail nas vendas da loja virtual e que os sistemas de recomendação baseados nos gostos de outras pessoas são os preferidos. / Submitted by Marcelo Teixeira (mvteixeira@ucs.br) on 2014-05-20T19:24:51Z No. of bitstreams: 1 Dissertacao Antonio Regis Nodari.pdf: 1570446 bytes, checksum: 4592a5c6268d0bfe3c10cd8a58315c8f (MD5) / Made available in DSpace on 2014-05-20T19:24:51Z (GMT). No. of bitstreams: 1 Dissertacao Antonio Regis Nodari.pdf: 1570446 bytes, checksum: 4592a5c6268d0bfe3c10cd8a58315c8f (MD5)

Submitted by Maria Medeiros (maria.dilva1@ufcg.edu.br) on 2018-05-24T13:28:45Z No. of bitstreams: 1 IARA PEREIRA RIBEIRO - DISSERTAÇÃO (PPGCC) 2016.pdf: 3942904 bytes, checksum: 107850ca0aaa80f6bdae5254492eed99 (MD5) / Made available in DSpace on 2018-05-24T13:28:45Z (GMT). No. of bitstreams: 1 IARA PEREIRA RIBEIRO - DISSERTAÇÃO (PPGCC) 2016.pdf: 3942904 bytes, checksum: 107850ca0aaa80f6bdae5254492eed99 (MD5) Previous issue date: 2016 / Capes / O aumento da demanda por recursos nos últimos anos e a provável escassez destes em um futuro próximo vem gerando um novo tipo de preocupação na sociedade de como utilizar estes recursos de forma mais eficiente. Um dos recursos onde essa preocupação se tornou mais evidente é o consumo elétrico devido ao uso de fontes não renováveis para a geração de energia elétrica, como por exemplo, as termoelétricas que utilizam o carvão mineral. No Brasil onde a maioria da demanda energética é suprida através de fontes renováveis, atualmente 73.1% da energia é gerada a partir de fontes renováveis, outros fatores como mudanças climáticas e períodos de estiagem podem alterar no total de energia gerado tornando necessário o uso de formas alternativas para geração de energia e consequentemente tornando mais caro o preço final para o consumidor. Surge então a necessidade nesse contexto de desenvolver ferramentas e opções que ajudem a tornar o consumo mais eficiente e a reduzir a produção de energia elétrica de forma a beneficiar tanto as concessionárias como os consumidores finais. Uma opção para solucionar esse problema seria tornar o consumo residencial mais eficiente, dado que no Brasil o consumo residencial é o terceiro maior. Este trabalho propõe uma solução que utiliza mapeamento entre conceitos de sistemas de recomendação e conceitos de eficiência energética para promover a redução do consumo elétrico, propondo algoritmos de Filtragem Colaborativa e de Conteúdo, usando nesse processo dados de uma pesquisa de comportamento entre voluntários, dados do governo, voluntários e um software que simula o consumo elétrico residencial. Após a experimentação concluiu-se que existem índicos da eficiência dos algoritmos propostos para o contexto de eficiência energética. A partir dos resultados podemos concluir que, por ser uma área nova ainda existem muitos conceitos a serem explorados no uso de técnicas de análise de dados para a eficiência energética e que o estudo realizado apresenta contribuições importantes para trabalhos futuros. / The recent increase in demand for resources, and the imminent potential shortage of these has created a new kind of societal concern which spawned an emphasis for more efficient methods on how to use these resources. One resource, in particular, is electricity and the glaring concern for how it is consumed; mainly due to the use of non-renewable way for generating electricity, E.G. thermal power using coal. Currently, in Brazil, 73.1% of the country’s energy is generated from renewable sources. Other factors such as climate change and extended periods of drought may impact the total amount of energy being generated, thus making the use of alternative methods for power generation a necessity – which in turn inflates the costs for the consumer. Within this context comes the need to develop tools and ideas which help to make the consumption of energy more efficient by reducing the production of electricity which will be beneficial to both the dealers and end consumers. One option to solve this problem would be to focus on the consumption in residential areas, as in Brazil, the residential sector is the third largest consumer of energy, consuming on average 24.78% of the total power generated in the country. This paper proposes a solution which uses mapping between energy efficient concepts and concepts of recommender systems to help promote the reduction of electrical consumption. The proposed algorithms combined with Collaborative Filtering and Content has used the processed data from behavioral surveys among volunteers, data government and software to stimulate the residential electricity consumption. From the results, we can conclude that with this relatively new ambit of discovery comes many concepts yet to be explored in the use of data analysis techniques for energy efficiency, and the importance of the application to future work.