Machine learning for user modeling

At first blush, user modeling appears to be a prime candidate for straightforward application of standard machine learning techniques. Observations of the user's behavior can provide training examples that a machine learning system can use to form a model designed to predict future actions. However, user modeling poses a number of challenges for machine learning that have hindered its application in user modeling, including: the need for large data sets; the need for labeled data; concept drift; and computational complexity. This paper examines each of these issues and reviews approaches to resolving them.

User-generated content and the changing news cycle

Blogs represent a major development in media consumption and practice.  The Pew Center in the United States reported in mid-2005 that about eight million Americans had created blogs and 32 million read them.  That's equivalent to two-thirds the number of people who read a daily newspaper during a week, a challenging giguew in the context of dwindling circulations.  Blogs represent the start of the 'personal media' revolution, but are only the tip of a range of new media developments.  This paper describes the blog phenomenon and notes its arrival via a series of major new stories.  It suggests we are seeing the emergence of a new news cycle, as blogs and other internet-based media usurp broadcast's role in breaking news.  The paper describes a range of emerging digital journalism forms that make up the 'personal media' revolution.  These include blogs delivered via mobile phones (moblogs); video-based blogs (v-logs); newspapers' use of podcasting to deliver content; and wikis, or peer-generated online content. The media's reaction to this new form of content is described, and the other concludes by looking at the forces driving this new form of journalism.

Automatic refinement of user requirements : a case study in software tool evaluation

This paper presents an assessment of system effectiveness in automatic requirements refinement by comparing results obtained from experts and novices with those achieved by the system. As the investigated system was a combination of a tightly inter-connected methods and a tool, the evaluation framework melded together a number of distinct methodological approaches structured into three empirical studies, which aimed at the construction of a case problem domain, calibrating the system using this defined domain elements and finally using the calibrated system to assess its effectiveness. In consequence, it was concluded that the evaluated methods and tools were effective in supporting requirements refinement.

User mobility prediction in hybrid and ad hoc wireless networks

Next Generation Networks will employ hybrid network architectures using both cellular and ad hoc networking concepts. The vision of real-time
multimedia services requires that mobility management be addressed in a proactive manner. If the user movements can be predicted accurately in a
hybrid network environment then handoff/cluster change, resource reservation and context transfer procedures can be efficiently completed as required by node mobility. In this work we propose a sectorized ad hoc mobility prediction scheme for cluster change prediction. Simulation study of the scheme shows it to be efficient in terms of prediction accuracy and prediction related control overhead despite randomness in user movement.

Toward highly available, self-healing, adaptable, grid-like and user friendly nondedicated clusters

The human body was used to illustrate an Autonomic Computing system that possesses self-knowledge, self-configuration, self-optimization, self-healing, and self-protection, knowledge of its environment and user friendliness properties. Autonomic Computing was identified by IBM as one of the Grand Challenges. Many researchers and research groups have responded positively to the challenge by initiating research around one or two of the characteristics
identified by IBM as the requirements for Autonomic Computing. One of the areas that could benefit from the comprehensive approach created by the Autonomic Computing vision is parallel processing on nondedicated clusters. This paper shows a general design of services and initial implementation of a system that moves parallel processing on clusters to the computing mainstream using the Autonomic Computing vision.

Mining sequential causal patterns with user-specified skeletons in multi-sequence of event data

The approaches proposed in the past for discovering sequential patterns mainly focused on single sequential data. In the real world, however, some sequential patterns hide their essences among multi-sequential event data. It has been noted that knowledge discovery with either user-specified constraints, or templates, or skeletons is receiving wide attention because it is more efficient and avoids the tedious selection of useful patterns from the mass-produced results. In this paper, a novel pattern in multi-sequential event data that are correlated and its mining approach are presented. We call this pattern sequential causal pattern. A group of skeletons of sequential causal patterns, which may be specified by the user or generated by the program, are verified or mined by embedding them into the mining engine. Experiments show that this method, when applied to discovering the occurring regularities of a crop pest in a region, is successful in mining sequential causal patterns with user-specified skeletons in multi-sequential event data.

End-user control in web-based electronic services : a case study

This paper reports a case study of end-user control in delivery of Web-based electronic services. The case study concentrates the adoption of a Web-based electronic system being implemented in processing student’s admission applications on a Web site. The end-user’s control interface provides information on the detail existing in the Web-based electronic service. This insight into end-user synthesis in developing effective control in Web service environment relates to ease of use in doing the task. To assume the leverage of end-user control strictly on the basis of the Web service usage would limit the purpose of understanding. Rather it is suggested that it would be better to develop an approach to study the end-user ease of use interface in doing the task with the user’s perception towards Web-based interactivity.

End-user experience with information in Web-based electronic service : a case study

End-user experience with information presumably considered as one of the prominent factors shaping the adoption of web-based electronic services. User interfacing with large amount of information the rationale is to deduce the effect in the current web-based task environment. Understanding user’s perception on the basis of the prior experience with information may provide insights into what constitutes in driving those perceptions and their effect in the current and future task in web-based electronic services. The paper lays the theoretical context of end-user experience with information and proceeds further in an attempt to distinguish the role in web-based electronic services.

The artist and the computer : understanding the creative user

This paper is focused on understanding the creative computer user for the purposes of informing the design of future creativity support systems and related software. We present an investigation of a successful Australian artist, Jill Lewis, who paints on canvas. In particular, we highlight the interesting part that existing digital technology plays in her creative practice, and we identify and describe in detail two specific uses of this technology. We terml these uses "electronic collaging" and "media switching". We go on to attempt to relate this artist's creative process to two theoretical models of the creative process.

A knowledge management approach to user support

This paper considers the problem of computer user support and workplace learning in general. Theoretically our work is influenced by ideas on knowledge management, expertise networks and communities of practice. Our approach seeks to tap into the powerful and situated learning potential of the collaborative support provided by colleagues. We consider that such support could be enhanced through the use of a collaborative support system. We outline our investigations into design issues, a generic model and various experiments related to the development of such a system. In particular, we emphasise the value of recorded demonstrations for representing computer-related practice. We present a number of design conclusions derived from our experiences, and warn that whereas active user participation is the essential ingredient in a support system it is perhaps the most difficult thing to achieve.

Sensor fusion based localization of a mobile user in a wireless network

This paper applies sensor fusion to the localization problem of a mobile user. We propose that the use of direction of arrival (DOA) estimations along with received signal strength measurements can increase the accuracy and robustness of location estimations. The DOA estimations are incapable of providing multi-dimensional positioning alone, while signal strength methods are prone to high uncertainties. A Robust Extended Kalman Filter (REKF) is used to derive the state estimate of the mobile user's position, and successfully track the mobile users with less system complexity, as it requires measurements from only one base station. Therefore, localization of mobile users can be performed at the single base station. Furthermore, the technique is robust against system uncertainties caused by the inherent deterministic nature of the mobility model. Through simulation, we show the accuracy of our prediction algorithm and the simplicity of its implementation.

Store names information signalling : a credibility perspective

This study is about store names as brand signals. Using the framework of Erdem and Swait (1998), hypotheses are developed regarding the effects of store names on consumers' expected product utility. It is relevant to study store names as brand signals because store names can act as additional signals in the consumer purchase decision process. The study focuses in particular on the effects of store name credibility on perceived risk, information costs and perceived product quality. The hypotheses will be tested on data that are currently being collected in a survey among two hundred students.