Book•
User Modeling and User Profiling in Adaptive
01 Dec 2008-
TL;DR: This theoretical excursion into the field of adaptive user modeling systems allows us to come up with a new approach based on a service-oriented architecture as an ideal candidate to implement as user modeling system.
Abstract: It is essential for user-adaptive systems to have information about the user. Without any user information an adaptive system is not able to adapt itself to the user's characteristics and preferences. The required information is stored and managed in form of user models. Thus, a user model represents the system's beliefs of the user. This work starts by giving the reader and overview of available and well-founded user modeling methods, standards and existing systems. This theoretical excursion into the field of adaptive user modeling systems allows us to come up with a new approach based on a service-oriented architecture. Service-oriented architecture with its main advantages of modularity and flexibility is and ideal candidate to implement as user modeling system as these are exactly the two main characteristics which we are looking for in such a systems. The technical part of this work compares several service-oriented frameworks and finally describes a service-oriented implementation of a user modeling system.
Citations
More filters
TL;DR: A novel user model is built that helped in achieving significant reduction in system complexity, sparsity, and made the neighbor transitivity relationship hold, and computational results reveal that they outperform the classical approach.
Abstract: The main strengths of collaborative filtering (CF), the most successful and widely used filtering technique for recommender systems, are its cross-genre or 'outside the box' recommendation ability and that it is completely independent of any machine-readable representation of the items being recommended However, CF suffers from sparsity, scalability, and loss of neighbor transitivity CF techniques are either memory-based or model-based While the former is more accurate, its scalability compared to model-based is poor An important contribution of this paper is a hybrid fuzzy-genetic approach to recommender systems that retains the accuracy of memory-based CF and the scalability of model-based CF Using hybrid features, a novel user model is built that helped in achieving significant reduction in system complexity, sparsity, and made the neighbor transitivity relationship hold The user model is employed to find a set of like-minded users within which a memory-based search is carried out This set is much smaller than the entire set, thus improving system's scalability Besides our proposed approaches are scalable and compact in size, computational results reveal that they outperform the classical approach
178 citations
Cites background from "User Modeling and User Profiling in..."
...However, recent researchers (Froschl, 2005; Koch, 2000) differentiate between them according to the level of sophistication....
[...]
...Depending on the content and the amount of information about the user, which is stored in the user profile, a user can be modeled (Froschl, 2005; Koch, 2000)....
[...]
09 Sep 2010
TL;DR: A comparison experiment was performed on MovieLens data set, and the result shows methodology proposed in this paper performs better than conventional collaborative filtering in recommendation accuracy and scalability.
Abstract: Collaborative filtering is the most widely used and successful technology for building recommender systems. However it faces challenges of scalability and recommendation accuracy. Collaborative filtering can be divided into memory based and model based. The former is more accurate while the latter performs better in scalability. This paper proposes a hybrid user model. The recommender system based on this model not only holds the advantage of recommendation accuracy in memory-based method, but also has the scalability as good as model-based method. The user model is constructed based on item combination feature and demographic information, and it focuses on searching for set of neighboring users shared with same interest, which helps to improve system scalability. To enhance recommendation accuracy, each feature in user model is given a different weight when computing the similarity between users. Genetic algorithm is adopted to learn the weight values of features. A comparison experiment was performed on MovieLens data set, and the result shows methodology proposed in this paper performs better than conventional collaborative filtering in recommendation accuracy and scalability.
28 citations
Cites methods from "User Modeling and User Profiling in..."
...USER MODEL Constructing user model is a crucial part for the collaborative filtering algorithm[16]....
[...]
01 Jan 2011
TL;DR: This chapter illustrates the vision about the evolution of search engines, dealing with some emerging questions related to the social role of the user on the Web and to the actual approach to access the information.
Abstract: In this chapter we illustrate our vision about the evolution of search engines, dealing with some emerging questions related to the social role of the user on the Web and to the actual approach to access the information. In this scenario, is ever more evident the need to redefine the information paradigm bringing the information to the user and not more the user to the information, with search engines able to provide results without direct questions from users, anticipating their needs. A Web in service of the user, automatically informed by the system with suggested resources related with his life style and his common behavior without the need to ask for them. This approach will be applied to a project named A Semantic Search Engine for a Business Network where the development of a business network creates a point of contact between the academic and the research world and the productive one by the introduction of Natural Language Processing, user profiling, automatic information classification according to users’ personal schemas, contributing in such a way to redefine the vision of information and delineating processes of Human-Machine Interaction.
18 citations
TL;DR: This research gives an insight of the various existing techniques that contribute to the improvement of the learning mechanism through proposing a real time monitoring system using image processing and eye detection techniques.
Abstract: Nowadays, we are living in a world where information is readily available and being able to provide the learner with the best suited situations and environment for his/her learning experiences is of utmost importance In most learning environments, information is basically available in the form of written text According to the eye-tracking technology, eye movements, scanning patterns and pupil diameter are indicators of thought and mental processing involved during visual information extraction Hence, learners can be supported and guided throughout their learning journey by the real-time information of the precise position of gaze and of pupil diameter A proper interpretation and consequently an efficient monitoring or supervision of learners' eye movements by different methods of eye tracking may lead to an enhanced learning process and experience This research gives an insight of the various existing techniques that contribute to the improvement of the learning mechanism through proposing a real time monitoring system using image processing and eye detection techniques To portray such a robust mechanism, a multipronged eye tracking approach has been envisioned The system is deployed with a first identification of the user's eyes followed by the detection of the iris and pupil movements of the latter Subsequently, the information about the eyes and pupil movements were analysed and graphs were generated that helps in determining the interest and behaviour of the user To evaluate the accuracy of the system, some user tests and various scenarios in different application domains have been performed by computing the tracking error rate and as a result it has been noticed that these tests yield to an acceptable efficiency rate and a True Acceptance Rate (TAR) of around 75 % Moreover, the proposed system is a low cost system and can be compatible with any computer or laptop equipped with an ordinary web camera
15 citations
01 Jan 2011
TL;DR: The proposed system exploits sensor mining methodologies to profile user behaviors patterns in an intelligent workplace based in the assumption that users' habit profiles are implicitly described by sensory data, which explicitly show the consequences of users’ actions over the environment state.
Abstract: The proposed system exploits sensor mining methodologies to profile user behaviors patterns in an intelligent workplace. The work is based in the assumption that users’ habit profiles are implicitly described by sensory data, which explicitly show the consequences of users’ actions over the environment state. Sensor data are analyzed in order to infer relationships of interest between environmental variables and the user, detecting in this way behavior profiles. The system is designed for a workplace equipped in the context of Sensor9k, a project carried out at the Department of Computer Science of Palermo University.
14 citations
Cites methods from "User Modeling and User Profiling in..."
...The acquired user information can be used to build appropriate user models which can be considered as representation of the system’s beliefs about the user [2]....
[...]