Valerie L. Shalin

Effectiveness of expert semantic knowledge as a navigational aid within hypertext

Hypertext systems parse documents into content nodes connected by machine supported links or relationships. Many hypertext researchers claim that the node-link relationships of hypertext provide an information organization that models the structure of human knowledge and should therefore facilitate information access (Fiderio 1988). Yet, failures of information access occur when users lack an understanding of the overall scope and organization of a hypertext system (Gay and Mazur 1991). To support this understanding, the present research incorporated expert-based domain semantics in the design of prosthetic devices for hypertext navigation. The task domain was documentation for a word processing system. In the first experiment, the pathfinder algorithm (Schvaneveldt 1990) and cluster analysis were used to identify a set of expertbased semantic relationships between word-processing concepts. The results from these analyses contributed to the design of two prostheses to assist hypertext navigation: A hierar...

What kind of #conversation is Twitter? Mining #psycholinguistic cues for emergency coordination

The information overload created by social media messages in emergency situations challenges response organizations to find targeted content and users. We aim to select useful messages by detecting the presence of conversation as an indicator of coordinated citizen action. Using simple linguistic indicators drawn from conversation analysis in social science, we model the presence of coordination in the communication landscape of Twitter using a corpus of 1.5 million tweets for various disaster and non-disaster events spanning different periods, lengths of time, and varied social significance. Within replies, retweets and tweets that mention other Twitter users, we found that domain-independent, linguistic cues distinguish likely conversation from non-conversation in this online form of mediated communication. We demonstrate that these likely conversation subsets potentially contain more information than non-conversation subsets, whether or not the tweets are replies, retweets, or mention other Twitter users, as long as they reflect conversational properties. From a practical perspective, we have developed a model for trimming the candidate tweet corpus to identify a much smaller subset of data for submission to deeper, domain-dependent semantic analyses for the identification of actionable information nuggets for coordinated emergency response.

Everyday Expertise: Cognitive Demands in Diabetes Self-Management

Objective: To assess the relationship between decision making and successful diabetes self-management. Background: Patients with type II diabetes make routine but critical self-management decisions. Method: We conducted cognitive task analysis interviews with 18 patients to examine problem detection, functional relationships, problem-solving strategies, and types of knowledge used to make self-management decisions. We expected that these decision processes would be related to behavioral adherence and glycemic control. Results: Verbal reports displaying problem detection skills, knowledge of functional relationships, and effective problem-solving strategies were all related to better adherence. Problem detection skill was linked to greater glycemic control. Participants differed in declarative and applied knowledge. Conclusion: Diabetes self-management draws on the same cognitive skills found in experts from diverse professional domains. Considering diabetes self-management as a form of expertise may support adherence. Application: Human factors approaches that support professional expertise may be useful for the decision making of patients with diabetes and other chronic diseases.

The impact of medical record technologies on collaboration in emergency medicine

PURPOSE Electronic medical records (EMR) promise potential benefits for the practice of medical care. However, individual technologies such as EMR must interact with the work system as a whole - including people, technology and work practices - to enable or hinder the coordination of dynamic work demands. Based on this extended perspective, we address in this paper how support technologies (should) impact the coordination of work across multiple agents, controlling a dynamic domain with multiple, interacting processes. The technology we address is the medical record and the dynamic domain is emergency medicine as it is practiced in the U.S. METHOD We performed 500 hours of naturalistic observations of physicians in two different hospital emergency departments in the Midwestern U.S differing in their reliance on paper or electronic medical records. RESULTS AND CONCLUSIONS An analysis of work practice across the two hospitals revealed the role of medical records in facilitating or hindering the coordination of time sensitive and context dependent distributed work, as well as the specific influence of EMR. Recognizing that work practice compensates for the limitations of technology, we suggest four requirements for the design of EMR to promote workplace efficiency: facilitation of locally customized data presentations; support for integration of hitherto fragmented record systems and data formats; support for effective multi-user coordination of control tasks; and guidance for standardizing a level of detail in planning and documenting care.

A cognitive perspective on manual assembly

Abstract Trends in manufacturing suggest that manual assembly will change from routine assembly line work to small-batch, non-routine work involving teams and incorporating quality control. The changing role of manual assembly in manufacturing reinforces the long-standing need to understand the properties of work that are compatible with human capabilities and limitations. Although methods engineering and principles for economizing human motion provide helpful approaches to the characterization of physical work demands, they provide limited insight into the properties of manual assembly work affecting the information processing and learning so important in non-routine work. In this paper several alternative task description models are reviewed and applied to an assembly task to illustrate its cognitive properties. The authors focus on a symbolic, computational representation of assembly task knowledge to suggest that current trends towards small-batch manufacturing place demands on workers to extend their...

Evaluating the influence of interface styles and multiple access paths in hypertext

No specific guidelines exist to assist in designing usable hypertext systems. In this paper, we discuss three experiments to study usability issues in hypertext design. In the first experiment, we investigated usability of four types of hypertext interfaces: graphical with labeled links (GL), graphical with unlabeled links (GU), textual with embedded links (TE), and textual with a separate list of related items/links (TS). The results favored GL interface for novice users. However, most subjects suggested incorporating multiple access pathways to facilitate search. To determine how hypertext designers could establish, a priori, these multiple structures, we extracted organization schemes from domain experts in the second experiment. Distinctly different organization structures emerged from experts with different professional backgrounds. Therefore, we modified the hypertext to incorporate multiple organization structures. In experiment 3, we compared subjects’ performance using multiple and single organization structures. Multiple structures, contrary to previous evidence, enhanced search performance. The benefits of multiple structures, however, diminished over time. These experiments provide empirical evidence in favor of GL interfaces and incorporation of multiple organization structures to improve hypertext usability.

The roles of humans and computers in distributed planning for dynamic domains

The requirements and issues associated with computational representations for planning extend beyond those apparent in real-time control, where a substantial, existing research literature informs designers. To assist in the identification of requirements for planning representations, this paper provides two resources: (1) a theoretical foundation drawn from computer science and (2) illustrations of representations and corresponding work practice for real-time control and planning for the US Shuttle program. Together, these resources illustrate the human role in the planning process, and the need for work practices and information that combine to assist human operators in interpreting a representation that is loosely coupled to the physical world while shared among and modified by multiple participants in the planning process.

Functions of expertise in a medical intensive care unit

This paper examines physician expertise in a hospital medical intensive care unit and illustrates three functions that expert physicians perform : (1) pursuit of ill-structured goals ; (2) treatment of dynamic disease processes in individual patients ; and (3) detection and ownership of problematic circumstances. These functions of medical expertise are illustrated using examples from videotapes of physician activities collected over five days in an inner city teaching hospital, providing the basis for the following hypotheses. Goal-directed reasoning in this domain extends beyond the technical foundations of medicine to the cultural values that acknowledge its expertise (Agnew et al. 1994). The treatment of dynamic disease processes depends on the adaptation of accepted methods to individual differences among patients, according to known symptoms and diagnoses. Diagnosis is a subgoal to treatment, pursued at multiple levels of abstraction, and only when it is not superseded by more urgent treatment goals...

A formal analysis of machine learning systems for knowledge acquisition

Abstract Machine learning techniques can be of great value for automating certain aspects of knowledge acquisition. Given the potential of machine learning for knowledge acquisition, we have begun a systematic investigation of how one might map the functions of knowledge-based systems onto those machine learning systems that provide the required knowledge. The goal of our current research is to provide a general characterization of machine learning systems and their respective application domains.

Learning plans for an intelligent assistant by observing user behavior

A critical requirement of intelligent automated assistants is a representation of actions and goals that is common to both the user and the automated assistant. Updating the intelligent systems knowledge base by observing user behavior is a convenient method for acquiring this common representation. We are developing an explanation based learning system to automate the acquisition of new plans for a large pilot-aiding expert system. We have developed a planning/learning shell that is based on the TWEAK planning system and DeJongs explanation based learning system. We are applying this shell to the pilot-aiding problem in a joint industry/university research effort involving Honeywell, Lockheed, ISX, Search Technology, and the Universities of Illinois and Michigan.