Hans H. K. Andersen

Trust in information sources: seeking information from people, documents, and virtual agents

Abstract The notion of trust has been virtually absent from most work on how people assess and choose their information sources. Based on two empirical cases this study shows that software engineers and users of e-commerce websites devote a lot of attention to considerations about the trustworthiness of their sources, which include people, documents, and virtual agents. In the project-based software engineering environment trust tends to be a collaborative issue and the studied software engineers normally know their sources first-hand or have them recommended by colleagues. Outside this network people are cautious and alert to even feeble cues about source trustworthiness. For example, users of e-commerce websites—generally perceived as single-user environments—react rather strongly to the visual appearance of virtual agents, though this is clearly a surface attribute. Across the two cases people need access to their sources in ways that enable them to assess source trustworthiness, access alone is not enough.

Scrutinising usability evaluation: does thinking aloud affect behaviour and mental workload?

Thinking aloud is widely used for usability evaluation. The validity of the method is, however, debatable because it is generally used in a relaxed way that conflicts with the prescriptions of the classic model for obtaining valid verbalisations of thought processes. This study investigates whether participants that think aloud in the classic or relaxed way behave differently compared to performing in silence. Results indicate that whereas classic thinking aloud has little or no effect on behaviour apart from prolonging tasks, relaxed thinking aloud affects behaviour in multiple ways. During relaxed thinking aloud participants took longer to solve tasks, spent a larger part of tasks on general distributed visual behaviour, issued more commands to navigate both within and between the pages of the websites used in the experiment, and experienced higher mental workload. Implications for usability evaluation are discussed.

Evaluation and validation of a conversational agent embodied in a bookstore

This work presents an agent-based interface that is not merely reactive to some user request, but is proactive since it is capable of engaging in a goal-directed conversation with the user, e.g., by taking the initiative to recommend new products. The naturalness of interaction, especially for casual users, is enhanced by appropriate 2D facial models. The proactiveness of the agent is based on a recommendation engine that combines content-based retrieval, which exploits user profiles based on content features extracted from the dialogue and descriptions of items that users find relevant, with collaborative filtering, which clusters users according to their expressed taste to generate recommendations within these virtual communities. The proposed system has been evaluated and validated by using a top-down approach, focusing on the system/user interaction.

User profiling and virtual agents: a case study on e-commerce services

The main contribution of this work is the design of an application framework based on both conversational agents and user profiling technologies for the development of e-commerce services. User profiles are exploited by conversational agents to help customers in retrieving potentially interesting products from a catalogue. Three techniques were used for collecting data for a usability test: eye-movement tracking, questionnaire, and recording the user-system dialogue. The main outcomes of the experimental sessions are: (1) the dialogue capabilities of the agent facilitate the interaction between the user and the e-commerce site; and, (2) user profiles improve the retrieval capabilities of the agent. Finally, some limitations of the user profiling techniques adopted in the framework are discussed and a more sophisticated content-based profiling technique is proposed.

A methodological approach for designing and evaluating intelligent applications for digital collections

The rapid evolution of Internet services has led to a constantly increasing number of Web sites and to an increase in the available information. The main challenge is to support Web users in order to facilitate navigation through Web sites and to improve searching among the extremely large Web repository, such as digital libraries, online product catalogues, or other generic information sources. The complexity of todays services could be lowered by means of proactive support or advice from the system. The proactiveness could be achieved using dialoguing agents that exploit user profiles to provide personal recommendations. In this paper, we will present a general methodology to cover the entire process of designing advanced solutions for online services. The methodology has been adopted to elicit user requirements for the system developed in the COGITO project, and to evaluate the performance of the final prototype.

Studying Operator Behaviour During a Simple But Safety Critical Task

A loss of sufficient Situation Awareness may lead to human errors, possibly resulting in accidents. Situation Awareness is often conceptually described in terms of operators’ correct perception and understanding of a situation. It is though becoming increasingly clear, however, that team SA is an important concept as well. An initial idea for a continuous measure of Team Situation Awareness was tried out in a small technical pilot study conducted in the nuclear reactor control room at Riso. In our present study we seek to develop integrative methods combining eye-movement tracking data with other behavioral data. The study described in this paper is a pilot study, which seeks to establish the feasibility of applying these methods of measurement and analysis, not their validity.

Use of the CANTOR system for collaborative learning in medical visual object recognition

This paper reports from a user requirement, design and evaluation study on supporting collaborative learning by visual perception in the medical education domain. The CANTOR (Converging Agreement by Networking Telematics for Object Recognition) system can briefly be described as a tool that support collaborative consensus making when classifying sets of medical images or objects in medical images An evaluation experiment showed that using CANTOR seems to give a better learning effect than by using traditional methods.