James Schaffer

  • Citations Per Year
Learn More
In many of today's online applications that facilitate data exploration, results from information filters such as recommender systems are displayed alongside traditional search tools. However, the effect of prediction algorithms on users who are performing open-ended data exploration tasks through a search interface is not well understood. This paper(More)
The web has evolved in a scale free manner, with available information about different entities developing in different forms, different locations, and at massive scales. This paper addresses the cognitive limitations that information analysts typically experience as they approach the boundaries where automated analysis algorithms are sorely needed. An(More)
Explanation and dynamic feedback given to a user during the recommendation process can influence user experience. Despite this, many real-world recommender systems separate profile updates and feedback, obfuscating the relationship between them. This paper studies the effects of what we call hypothetical recommendations. These are recommendations generated(More)
OBJECTIVE We investigated how increases in task-relevant information affect human decision-making performance, situation awareness (SA), and trust in a simulated command-and-control (C2) environment. BACKGROUND Increased information is often associated with an improvement of SA and decision-making performance in networked organizations. However, previous(More)
Hybrid recommender systems combine several different sources of information to generate recommendations. These systems demonstrate improved accuracy compared to single-source recommendation strategies. However, hybrid recommendation strategies are inherently more complex than those that use a single source of information, and thus the process of explaining(More)
This paper discusses and evaluates the impact of visualization and interaction strategies for extracting quality information from data in complex networks such as microblogs. Two different approaches to interactive visual representations of data are discussed: an interactive node-link graph and a novel approach where content is separated into interactive(More)
Massive open online courses (MOOCs) have high potential for improving education worldwide, but understanding of student behavior and situations is difficult to achieve in online settings. Network analytics and visualizations can assist instructors with supporting understanding of student behavior as courses unfold. In this work, we perform a visual(More)
We define an entrance examination to be a test given during the traditional final exam period that is associated with a course the student will take in the following semester. In our model, entrance exams replace final exams and offer several advantages. First, they reduce the problem associated with compartmentalization of knowledge. Entrance exams will be(More)
28 Background: Value based payment reforms which improve the outcome to cost ratio (paying for outcomes not for services) require detailed information on both elements. Although the digitalization of medicine via the EHR may facilitate data collection, the imprecise ICD9 and ICD10 schemas hinder analysis (eg: all breast cancers are ICD9 174.9). A more(More)