Decision-theoretic optimization is becoming a popular tool in the user interface community, but creating accurate cost (or utility) functions has become a bottleneck --- in most cases the numerous parameters of these functions are chosen manually, which is a tedious and error-prone process. This paper describes ARNAULD, a general interactive tool for eliciting user preferences concerning concrete outcomes and using this feedback to automatically learn a factored cost function. We empirically evaluate our machine learning algorithm and two automatic query generation approaches and report on an informal user study.

We describe an intelligent personal assistant that has been developed to aid a busy knowledge worker in managing time commitments and performing tasks. The design of the system was motivated by the complementary objectives of (1) relieving the user of routine tasks, thus allowing her to focus on tasks that critically require human problem-solving skills, and (2) intervening in situations where cognitive overload leads to oversights or mistakes by the user. The system draws on a diverse set of AI technologies that are linked within a Belief-Desire-Intention (BDI) agent system. Although the system provides a number of automated functions, the overall framework is highly user centric in

Abstract not found

We have developed a prototype to-do list called TaskVista that enables a user to create to-do items by typing or by drag-and-drop of files or email messages. TaskVista allows the user to promote items into Activities in our Activity-Centered Task Assistant (ACTA). Activities are prestructured containers that are created inside the email folder hierarchy to support PIM. Specialized subfolders called Components within each ACTA Activity automatically organize and present information appropriately for aspects of the activity at hand. ACTA is designed to create a more efficient PIM environment with the ultimate goal of providing context metadata for machine learning and automation techniques.

to design an automated personal assistant to support a busy high-level knowledge worker. Operating in an inherently dynamic and uncertain domain, CALO relies on constraint technology in several components of its architecture. We outline the challenges and opportunities presented by constraint solving in the presence of change and uncertainty, embodied in CALO’s personalized time management and task reasoning and execution systems. 1

We discuss experiences from evaluating the learning performance of a user-adaptive personal assistant agent. We discuss the challenge of designing adequate evaluation and the tension of collecting adequate data without a fully functional, deployed system. Reflections on negative and positive experiences point to the challenges of evaluating user-adaptive AI systems. Lessons learned concern early consideration of evaluation and deployment, characteristics of AI technology and domains that make controlled evaluations appropriate or not, holistic experimental design, implications of “in the wild” evaluation, and the effect of AI-enabled functionality and its impact upon existing tools and work practices.

We believe that AI has much to offer HCI, in particular allowing for the quick construction of personalized and personalizable interfaces. In this position paper, we report on our experience from four recent

For decades, researchers have debated the pros and cons of adaptive user interfaces with enthusiastic AI practitioners often confronting skeptical HCI experts (Shneiderman & Maes, 1997). This paper summarizes the SUPPLE project’s

To have value for an individual tasked with arranging a meeting, a scheduling tool must actively account for the individual’s scheduling preferences, especially when the meeting request must be relaxed. We develop a preference model designed to capture user scheduling preferences for overconstrained meeting requests between multiple people, and a methodology for preference elicitation to initially populate this model. The model is built around a 2-order Choquet integral representation. We explain a natural-language-based elicitation of the meeting request details and constraints, and outline the solving of the resulting constrained scheduling problem (with preferences). We then describe the display of solutions to the scheduling problem to the user, as candidate scheduling options with explanations, and detail unobtrusive learning of revisions to the preference model from the user’s choices among the candidates. We report on initial assessment of the efficacy of such a preference model in terms of elicitation, learning, and reasoning.

In a world of electronic calendars, the prospect of intelligent, personalized time management assistance seems a plausible and desirable application of AI. PTIME (Personalized Time Management) is a learning cognitive assistant agent that helps users handle email meeting requests, reserve venues, and schedule events. PTIME is designed to unobtrusively learn scheduling preferences, adapting to its user over time. The agent allows its user to flexibly express requirements for new meetings, as they would to an assistant. It interfaces with commercial enterprise calendaring platforms, and it operates seamlessly with users who do not have PTIME. This article overviews the system design and describes the models and technical advances required to satisfy the competing needs of preference modeling and elicitation, constraint reasoning, and machine learning. We further report on a multifaceted evaluation of the perceived usefulness of the system.