Anthony Jameson

Deutsches Forschungszentrum für Künstliche Intelligenz | DFKI · Intelligent User Interfaces

Planning a visit to Expo Milano 2015 or simply touring in Milan are activities that require a certain amount of a priori knowledge of the city. In this paper, we present the process of building such comprehensive knowledge bases that contain descriptions of events and activities, places and sights, transportation facilities as well as social activi...

Choice Architecture for Human-Computer Interaction focuses on systems that help people choose for themselves. Realizing this potential requires a well-founded understanding of the ways in which people make everyday choices and the design strategies and computing technologies that can be used to support these processes. This work offers a compact sy...

Following up on work presented at IESD 2012 introducing the paradigm of multifocal exploration of semantic data, the present paper reports on two user studies of prototypes that instantiate parallel faceted browsing---a generalization of faceted browsing that enables multiple interrelated queries and their results to be displayed at the same time....

The widely used paradigm of faceted browsing is limited by the fact that only one query and result set are displayed at a time. This demonstrator introduces an interaction design for parallel faceted browsing that makes it easy for a user to construct and view the results of multiple interrelated queries. The paradigm offers general benefits for a...

Algorithms for learning the conditional probabilities of Bayesian networks with hidden variables typically operate within a high-dimensional search space and yield only locally optimal solutions. One way of limiting the search space and avoiding local optima is to impose qualitative constraints that are based on background knowledge concerning the...

In the NETCARITY project, we conducted several complementary investigation activities with elderly people revolving around the design of technology for the home environment. In this paper, we investigate the potential impact of virtual characters in making the interaction with the technology-enhanced home more effective and engaging. We briefly dis...

This editorial introduction explains the motivation and origin of the TiiS special issue on Highlights of the Decade in Interactive Intelligent Systems and shows how its five articles exemplify the types of research contribution that TiiS aims to encourage and publish.

Users of computing technology are constantly making choices about how to use the technology which are "preferential" in the sense that there is no correct or incorrect option. We argue that HCI should devote more attention to helping users to make better preferential choices, tapping into the vast pool of relevant psychological research. After offe...

Research in the semantic web community has given rise to some pow-erful methods for visualizing events and related media—mostly in terms of inter-active timelines—and for enabling users to interact with these visualizations. The present paper aims to advance this line of research in two ways: (a) by devel-oping interactive visualizations of event h...

One of the central questions addressed in the project READY was that of how a system can automatically recognize situationally determined resource limitations of its user—in particular, time pressure and cognitive load. This chapter summarizes most of the work done in READY on this topic, presenting as well some previously unpublished results. We f...

Even the most sophisticated automatic recognition of events must of-ten be paired with an appropriate design of the users' interaction with those events. This paper presents three presumably typical use cases and associated interaction design proposals, which illustrate (a) how untrained users can benefit from the organization of media in terms of...

This short paper is the first step in a line of research that aims to deepen understanding of the difficulties that users often have with option setting interfaces: those parts of a system that allow the user to set parameters that influence the system’s behavior and appearance. On the basis of a theoretical distinction of three things that users m...

Especially in mobile systems, one important part of the context of use involves psychological variables like cognitive load and time pressure. This paper looks at one possible way of capturing such aspects of context: the analysis of the features of the users' speech. In a replication and extension of an earlier study of our group, we created four...

The goal of this full-day workshop is to arrive at a synthesis of knowledge that will help people who work with intelligent user interfaces to predict and explain how users' attitudes and behavior toward aspects of such systems (a) differ from one user to the next and (b) change over time.

This paper discusses some general results from an in-situ study of the use of a tabletop system for card playing that differs in several ways from most tabletop systems: 1. It was designed primarily for use by senior citizens with little or no computer experience. 2. It is a single-user system, though social interaction with nearby persons during i...

Proper usability evaluations of spoken dialogue systems are costly and cumbersome to carry out. In this paper, we present a new approach for facilitating usability evaluations which is based on user error simulations. The idea is to replace real users with simulations derived from empirical observations of users' erroneous behavior. The simulated e...

This paper reports on extensions to a decision-theoretic location-aware shopping guide and on the results of user studies that have accompanied its de- velopment. On the basis of the results of an earlier user study in a mock-up of a shopping mall, we implemented an improved version of the shopping guide. A new user study with the improved system i...

We have implemented and tested a PDA-based system that gives a shopper directions through a shopping mall on the basis of (a) the types of products that the shopper has expressed an interest in, (b) the shopper's current location, and (c) the purchases that the shopper has made so far. The system uses decision-theoretic planning to compute a policy...

We have implemented and tested a PDA-based system that gives a shopper directions through a shopping mall on the basis of (a) the types of prod- ucts that the shopper has expressed an interest in, (b) the shopper's current lo- cation, and (c) the purchases that the shopper has made so far. The system uses decision-theoretic planning to compute a po...

We are exploring a class of decision-theoretic handheld systems that give a user personalized advice about how to explore an indoor area in search of products or information. An initial user test in a simple mockup of a shopping mall showed that even novice PDA users accepted the system immediately and were able to achieve their shopping goals fast...

In an experimental environment, we simulated the situation of a user who gives speech input to a system while walking through an airport. The time pressure on the subjects and the requirement to navigate while speaking were manipulated orthogonally. Each of the 32 subjects generated 80 utterances, which were coded semi-automatically with respect to...

Users of computing devices are increasingly likely to be subject to situationally determined distractions that produce exceptionally high cognitive load. The question arises of how a system can automatically interpret symptoms of such cognitive load in the user's behavior. This paper examines this question with respect to systems that process speec...

How can an adaptive intelligent interface decide what particular action to perform in a given situation, as a function of perceived properties of the user and the situation? Ideally, such decisions should be made on the basis of an empirically derived causal model. In this paper we show how such a model can be constructed given an appropriately lim...

Situationally determined limitations in users' "resources" (e.g., time and working memory) constitute an increasingly important challenge to adaptive interfaces---one which does not yield easily to straightforward solutions. This article gives an overview of a research program that emphasizes empirically based understanding of this problem and the...

An intelligent user interface sometimes needs to present a sequence of related recommendations to a user, in spite of being uncertain in advance as to whether (and with what success) the user will follow each recommendation. There are potential advantages to the use of decision-theoretic planning methods which yield an optimal policy for the situat...

One feature of intelligent user interfaces is an ability to make decisions that take into account a variety of factors, some of which may depend on the current situation. This article focuses on one general approach to such decision making: Predict the consequences of possible system actions on the basis of prior empirical learning, and evaluate th...

Models of computer users that are learned on the basis of data can make use of two types of informa- tion: data about users in general and data about the current individual user. Focusing on user models that take the form of Bayesian networks, we com- pare four types of model that represent different ways of combining these two types of data. Model...

An intelligent user interface sometimes needs to present a sequence of related recommendations to a user, in spite of being uncertain in advance as to whether (and with what success) the user will follow each recommendation. There are potential advantages to the use of decision-theoretic planning methods which yield an optimal policyfor the situati...

How can an adaptive intelligent interface decide what particular action to perform in a given situation, as a function of perceived properties of the user and the situation? Ideally, such decisions should be made on the basis of an empirically derived causal model. In this paper we show how such a model can be constructed given an appropriately lim...

Situationally determined limitations in users’ “resources” (e.g. time and working memory) constitute an increasingly important challenge to adaptive interfaces—one which does not yield easily to straightforward solutions. This article gives an overview of a research program that emphasizes empirically based understanding of this problem and the use...

We present issues and initial results of our research into methods for learning Bayesian networks for user modeling on the basis of empirical data, focusing on issues that are especially important in the context of user modeling. These issues include the treatment of theoretically interpretable hidden variables, ways of learning partial networks an...

Recent advances in user modeling technology have brought within reach the goal of having systems adapt to temporary limitations of the user , s available time and working memory capacity. We first summarize empirical research by ourselves and others that sheds light on the causes and consequences of these (continually changing) resource limitations...

S can predict O's expected evaluation shift if S assumes that it depends probabilisticallyon the first twovariables (e.g., that the most likely evaluation shift is determined by their product). If S later finds out what O's evaluation shift actually was, S can interpret this information, using Bayes' Rule to derive updated impressions of both varia...

This paper reports on research on the question of how a dialog system can recognize and adapt to the resource limitations of its user: specifically, limitations of time and working memory. The results of an exploratory study, together with other empirical research, yield a number of probabilistic causal relationships among relevant variables. It is...

In the context of dialog, one challenge for natural language generation is that of dealing with discourse obligations such as those created by questions, promises, and even silences. The present paper presents new methods for (a) representing discourse obligations, (b) determining which ones are created by a given dialog move, (c) determining how t...

Human dialog participants regularly predict the responses of their dialog partners by hypothetically assuming the partner's role. This strategy of using global anticipation feedback has seldom been approximated in dialog systems. In the system PRACMA, the technical prerequisites for this strategy have been fulfilled, and the system is being used as...

Human dialog participants regularly predict the responses of their dialog partners by hypothetically assuming the partner's role. This strategy of using global anticipation feedback has seldom been approximated in dialog systems. In the system PRACMA, the technical prerequisites for this strategy have been fulfilled, and the system is being used as...

. A rapidly growing number of user and student modeling systems have employed numerical techniques for uncertainty management. The three major paradigms are those of Bayesian networks, the Dempster-Shafer theory of evidence, and fuzzy logic. In this overview, each of the first three main sections focuses on one of these paradigms. It first introduc...

A system that reasons about the beliefs of a person must in general be able to ascribe a good deal of general background knowledge to that person, often in the absence of reliable evidence that the person possesses that knowledge. In some cases it is possible to make the necessary inferences within a logical framework, often as default inferences,...

Ways of achieving two desirable characteristics of pragmatically oriented dialog processing are discussed: (1) Flexible cooperation among the system's modules maximizes the system's exploitation of its knowledge and of its reasoning capabilities. (2) The ability to take either (or any) of the dialog roles in its domain enhances the system's ability...

Evaluation-oriented information provision is a function performed by many systems that serve as personal assistants, advisors, or sales assistants. Five general tasks are distinguished which need to be addressed by such systems. For each task, tech- niques employed in a sample of systems are dis- cussed, and it is shown how the lessons learned from...

The Natural Language system HAM-RPM simulates a dialogue partner conversing about one of several interchangeable scenes in colloquial German. The overall goals of the research have been twofold: simulating natural language dialogue behaviour by means of a computer is a promising and reliable method for establishing and testing theoretical models of...

HAM-RPM is a dialogue system which converses with a human partner in colloquial German about limited, but interchangeable scenes. The objective of this report is to give a detailed, complete and self-contained description of the system in its present state of implementation. After a discussion of the goals and methodological principles which guide...

An experiment (N=24) was conducted with a spoken dialogue system (a smart home system), in which the users carried out several tasks with the system and rated its usability. Users' interactions were analyzed from the perspective of human error research done in human factors and cognitive ergonomics, distinguishing between goal-, concept-, task-, an...

Although intelligent environments can tend to re- duce their users to passive consumers, they also generate in- formation that a system can leverage for the support of rich interpersonal communication. The CONVERSATIONPIECE project builds on research by the contributors and others on the construction of artificial personal memories, the shari ng of...