Personalized recommender systems aim to assist users in retrieving and accessing interesting items by automatically acquiring user preferences from the historical data and matching items with the preferences. In the last decade, recommendation services have gained great attention due to the problem of information overload. However, despite recent advances of personalization techniques, several critical issues in modern recommender systems have not been well studied. These issues include: (1) understanding the accessing patterns of users (i.e., how to effectively model users' accessing behaviors); (2) understanding the relations between users and other objects (i.e., how to comprehensively assess the complex correlations between users and entities in recommender systems); and (3) understanding the interest change of users (i.e., how to adaptively capture users' preference drift over time). To meet the needs of users in modern recommender systems, it is imperative to provide solutions to address the aforementioned issues and apply the solutions to real-world applications. The major goal of this dissertation is to provide integrated recommendation approaches to tackle the challenges of the current generation of recommender systems. In particular, three user-oriented aspects of recommendation techniques were studied, including understanding accessing patterns, understanding complex relations and understanding temporal dynamics. To this end, we made three research contributions. First, we presented various personalized user profiling algorithms to capture click behaviors of users from both coarse- and fine-grained granularities; second, we proposed graph-based recommendation models to describe the complex correlations in a recommender system; third, we studied temporal recommendation approaches in order to capture the preference changes of users, by considering both long-term and short-term user profiles. In addition, a versatile recommendation framework was proposed, in which the proposed recommendation techniques were seamlessly integrated. Different evaluation criteria were implemented in this framework for evaluating recommendation techniques in real-world recommendation applications. In summary, the frequent changes of user interests and item repository lead to a series of user-centric challenges that are not well addressed in the current generation of recommender systems. My work proposed reasonable solutions to these challenges and provided insights on how to address these challenges using a simple yet effective recommendation framework.

User profiling has wide applications such as personalization, intrusion detection, and online customer analysis in e-business environments. In the past decade, most of past research on user profiling focused on factual profile construction and applications. A few researchers studied application-oriented behavioral profiling problems. In light of the advantages of behavioral profiles over their factual counterparts and the importance of fundamental understanding of them, this dissertation probes into the theoretical foundation, modeling and data-mining-based heuristic techniques for constructing behavioral profiles.We first propose a research framework for behavioral profiling and define the fundamentals. We build an optimization model for describing and solving a general type of behavioral profile construction problem. The analysis of the optimization model's analytic properties found a strong connection between the feasible solution to the model and the independent dominating set in a graph derived from the input of the model. Based on this finding, we employed two solution searching approaches: brute-force and Genetic Algorithm, and performed numerical analysis on a synthetic small-sized profiling problem. The results demonstrate the effectiveness of Genetic Algorithm for producing approximate optimal solution to the CH optimization problem.We propose an innovative data-mining-based heuristic approach - hierarchical characteristic pattern mining to find solutions to the profile construction optimization problem. This approach builds behavioral profiles based on a new type of pattern - characteristic pattern and is appropriate for large-scale problems. Experiments using relatively large amounts of synthetic data were conducted to test the performance of this approach. The results show that the data-mining-based approach outperforms the Genetic Algorithm when the characteristic patterns exist. Finally, a particular user behavioral profile application - web user identification is introduced to present problems and solutions when applying the data-mining-based behavioral profile construction approach into a real-world profile application. The experiments performed on a real-world dataset produced positive results of our approach in terms of effectiveness, efficiency, and interpretability.The main contributions of the dissertation are: (1) proposing a comprehensive profiling research framework; (2) building an optimization model for solving a general type of profile construction problem; and (3) developing an innovative data-mining based heuristic approach to building behavioral profiles.

Abstract INDIVIDUAL-TECHNOLOGY FIT: MATCHING INDIVIDUAL CHARACTERISTICS AND FEATURES OF BIOMETRIC INTERFACE TECHNOLOGIES WITH PERFORMANCE By ADRIANE B. RANDOLPH MAY 2007 Committee Chair: Dr. Melody Moore Jackson Major Department: Computer Information Systems The term biometric literally means “to measure the body”, and has recently been associated with physiological measures commonly used for personal verification and security applications. In this work, biometric describes physiological measures that may be used for non-muscularly controlled computer applications, such as brain-computer interfaces. Biometric interface technology is generally targeted for users with severe motor disabilities which may last long-term due to illness or injury or short-term due to temporary environmental conditions. Performance with a biometric interface can vary widely across users depending upon many factors ranging from health to experience. Unfortunately, there is no systematic method for pairing users with biometric interface technologies to achieve the best performance. The current methods to accommodate users through trial-and-error result in the loss of valuable time and resources as users sometimes have diminishing abilities or suffer from terminal illnesses. This dissertation presents a framework and methodology that links user characteristics and features of biometric interface technologies with performance, thus expediting the technology-fit process. The contributions include an outline of the underlying components of capturing and representing individual user characteristics and the impact on the performance of basic interaction tasks using a methodology called biometric user profiling. In addition, this work describes a methodology for objectively measuring an individual’s ability to control a specific biometric interface technology such as one based on measures of galvanic skin response or neural activity. Finally, this work incorporates these concepts into a new individual-technology fit framework for biometric interface technologies stemming from literature on task-technology fit. Key words: user profiles, biometric user profiling, biometric interfaces, fit, individual-technology fit, galvanic skin response, functional near-infrared, brain-computer interface

In this thesis, a content recommendation system has been developed. The system makes recommendations based on the preferences of the users on some aspects of the content and also preferences of similar users. The preferences of a user are extracted from the choices of that user made in the past. Similarities between users are defined by the similarities of their preferences. Such a system requires both qualified content and user information. The proposed system uses semantic user and content profiles to more effectively define the relationships between the two and make better inferences. An ontology is defined using the existing domain ontologies and the semi-structured data on the web. The system is implemented mainly for the movie domain in which well-defined ontologies and user information are easier to access.

Software defined networking (SDN) is a relatively new paradigm that decouples individual network elements from the control logic, offering real-time network programmability, translating high level policy abstractions into low level device configurations. The framework comprises of the data (forwarding) plane incorporating network devices, while the control logic and network services reside in the control and application planes respectively. Operators can optimize the network fabric to yield performance gains for individual applications and services utilizing flow metering and application-awareness, the default traffic management method in SDN. Existing approaches to traffic optimization, however, do not explicitly consider user application trends. Recent SDN traffic engineering designs either offer improvements for typical time-critical applications or focus on devising monitoring solutions aimed at measuring performance metrics of the respective services. The performance caveats of isolated service differentiation on the end users may be substantial considering the growth in Internet and network applications on offer and the resulting diversity in user activities. Application-level flow metering schemes therefore, fall short of fully exploiting the real-time network provisioning capability offered by SDN instead relying on rather static traffic control primitives frequent in legacy networking. For individual users, SDN may lead to substantial improvements if the framework allows operators to allocate resources while accounting for a user-centric mix of applications. This thesis explores the user traffic application trends in different network environments and proposes a novel user traffic profiling framework to aid the SDN control plane (controller) in accurately configuring network elements for a broad spectrum of users without impeding specific application requirements. This thesis starts with a critical review of existing traffic engineering solutions in SDN and highlights recent and ongoing work in network optimization studies. Predominant existing segregated application policy based controls in SDN do not consider the cost of isolated application gains on parallel SDN services and resulting consequence for users having varying application usage. Therefore, attention is given to investigating techniques which may capture the user behaviour for possible integration in SDN traffic controls. To this end, profiling of user application traffic trends is identified as a technique which may offer insight into the inherent diversity in user activities and offer possible incorporation in SDN based traffic engineering. A series of subsequent user traffic profiling studies are carried out in this regard employing network flow statistics collected from residential and enterprise network environments. Utilizing machine learning techniques including the prominent unsupervised k-means cluster analysis, user generated traffic flows are cluster analysed and the derived profiles in each networking environment are benchmarked for stability before integration in SDN control solutions. In parallel, a novel flow-based traffic classifier is designed to yield high accuracy in identifying user application flows and the traffic profiling mechanism is automated. The core functions of the novel user-centric traffic engineering solution are validated by the implementation of traffic profiling based SDN network control applications in residential, data center and campus based SDN environments. A series of simulations highlighting varying traffic conditions and profile based policy controls are designed and evaluated in each network setting using the traffic profiles derived from realistic environments to demonstrate the effectiveness of the traffic management solution. The overall network performance metrics per profile show substantive gains, proportional to operator defined user profile prioritization policies despite high traffic load conditions. The proposed user-centric SDN traffic engineering framework therefore, dynamically provisions data plane resources among different user traffic classes (profiles), capturing user behaviour to define and implement network policy controls, going beyond isolated application management.

As the amount of information captured about users increased over the last decade, interest in personalized user interfaces has surged in the HCI and IS communities. Personalization is an effective means for accommodating for differences between individuals. The fundamental idea behind personalization rests on the notion that if a system can gather useful information about the user, generate a relevant user model and apply it appropriately, it would be possible to adapt the behavior of a system and its interface to the user at the individual level. Personal-ization of a user interface features can enhance usability. With recent technological advances, personalization can be achieved automatically and unobtrusively. A user interface can deploy a NeuroIS technology such as eye-tracking that learns from the user's visual behavior to provide users an experience most unique to them. The advantage of eye-tracking technology is that subjects cannot consciously manipulate their responses since they are not readily subject to manipulation. The objective of this dissertation is to develop a theoretical framework for user personalization during reading comprehension tasks based on two machine learning (ML) models. The proposed ML-based profiling process consists of user's age characterization and user's cognitive load detection, while the user reads text. To this end, detection of cognitive load through eye-movement features was investigated during different cognitive tasks (see Chapters 3, 4 and 6) with different task conditions. Furthermore, in separate studies (see Chapters 5 and 6) the relationship between user's eye-movements and their age population (e.g., younger and older generations) were carried out during a reading comprehension task. A Tobii X300 eye tracking device was used to record the eye movement data for all studies. Eye-movement data was acquired via Tobii eye tracking software, and then preprocessed and analyzed in R for the aforementioned studies. Machine learning techniques were used to build predictive models. The aggregated results of the studies indicate that machine learning accompanied with a NeuroIS tool like eye-tracking, can be used to model user characteristics like age and user mental states like cognitive load, automatically and implicitly with accuracy above chance (range of 70-92%). The results of this dissertation can be used in a more general framework to adaptively modify content to better serve the users mental and age needs. Text simplification and modification techniques might be developed to be used in various scenarios.

With the evolution of Web 2.0, most social-networking sites let their members participate in content generation. Users can label items with tags in these websites. A tag can be anything but it is actually a short description of the item. Because tags represent the reason why a user likes an item, but not how much user likes it / they are better identifiers of user profiles than ratings, which are usually numerical values assigned to items by users. Thus, the tag-based contextual representations of music tracks are concentrated in this study. Items are generally represented by vector space models in the content based recommendation systems. In tag-based recommendation systems, users and items are defined in terms of weighted vectors of social tags. When there is a large amount of tags, calculation of the items to be recommended becomes hard, because working with huge vectors is a time-consuming job. The main objective of this thesis is to represent individual tracks (songs) in lower dimensional spaces. An approach is described for creating music recommendations based on user-supplied tags that are augmented with a hierarchical structure extracted for top level genres from Dbpedia. In this structure, each genre is represented by its stylistic origins, typical instruments, derivative forms, sub genres and fusion genres. In addition to very large vector space models, insufficient number of user tags is another problem in the recommendation field. The proposed method is evaluated with different user profiling methods in case of any insufficiency in the number of user tags. User profiles are extended with multi-domain information. By using multi-domain information, the goal of making more successful and realistic predictions is achieved.

Customer Relationship Management (CRM) is one of the biggest problems for many companies today. By analyzing history records (profiles) of its customers, organization can effectively adapt its business activity to users needs and create better products and services. Proper analysis of customer profiles can help to predict the behaviour of the customers. After grouping customer profiles by similar attributes, company can easier handle its interactions with similar users. Such group profiling can also help to identify needs of new customers on their first interaction with the company. The biggest problem in implementing such systems is the management of a vast array of customer data. Data mining technologies can help to solve this problem and help the ebusinesses to better understand their e-customers. This work reviews data mining methods, such as Nearest Neighbors, Decision Trees and Association Rules, which can be effectively used for customers grouping and profiling. A new conceptual model of Users Recognition System is suggested. The new model uses profiles created from customer history records for identifying new customers. The suggested model has been tested experimentally and results prove the possibility of practical application of this model.

L'objectif principal de la thèse est de proposer une méthode de recommandation prenant en compte la vie privée des utilisateurs ainsi que l'évolutivité du système. Pour atteindre cet objectif, une technique hybride basée sur le filtrage par contenu et le filtrage collaboratif est utilisée pour atteindre un modèle précis de recommandation, sous la pression des mécanismes visant à maintenir la vie privée des utilisateurs. Les contributions de la thèse sont trois : Tout d'abord, un modèle de filtrage collaboratif est défini en utilisant agent côté client qui interagit avec l'information sur les éléments, cette information est stockée du côté du système de recommandation. Ce modèle est augmenté d’un modèle hybride qui comprend une stratégie basée sur le filtrage par contenu. En utilisant un modèle de la connaissance basée sur des mots clés qui décrivent le domaine de l'article filtré, l'approche hybride augmente la performance de prédiction des modèles sans élever l’effort de calcul, dans un scenario du réglage de démarrage à froid. Finalement, certaines stratégies pour améliorer la protection de la vie privée du système de recommandation sont introduites : la génération de bruit aléatoire est utilisée pour limiter les conséquences éventuelles d'une attaque lorsque l'on observe en permanence l'interaction entre l'agent côté client et le serveur, et une stratégie basée sur la liste noire est utilisée pour s’abstenir de révéler au serveur des interactions avec des articles que l'utilisateur considère comme pouvant transgresser sa vie privée. L'utilisation du modèle hybride atténue l'impact négatif que ces stratégies provoquent sur la performance prédictive des recommandations. / The main objective of this thesis is to propose a recommendation method that keeps in mind the privacy of users as well as the scalability of the system. To achieve this goal, an hybrid technique using content-based and collaborative filtering paradigms is used in order to attain an accurate model for recommendation, under the strain of mechanisms designed to keep user privacy, particularly designed to reduce the user exposure risk. The thesis contributions are threefold : First, a Collaborative Filtering model is defined by using client-side agent that interacts with public information about items kept on the recommender system side. Later, this model is extended into an hybrid approach for recommendation that includes a content-based strategy for content recommendation. Using a knowledge model based on keywords that describe the item domain, the hybrid approach increases the predictive performance of the models without much computational effort on the cold-start setting. Finally, some strategies to improve the recommender system's provided privacy are introduced: Random noise generation is used to limit the possible inferences an attacker can make when continually observing the interaction between the client-side agent and the server, and a blacklisted strategy is used to refrain the server from learning interactions that the user considers violate her privacy. The use of the hybrid model mitigates the negative impact these strategies cause on the predictive performance of the recommendations.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第20737号 / 情博第651号 / 新制||情||112(附属図書館) / 京都大学大学院情報学研究科社会情報学専攻 / (主査)教授 吉川 正俊, 教授 石田 亨, 教授 美濃 導彦, 准教授 馬 強 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM