The need to educate a competitive workforce is a global problem. In the US, for example, despite billions of dollars spent to improve the educational system, approximately 35% of students never finish high school. The drop rate among some demographic groups is as high as 50-60%. At the college level in the US only 30% of students graduate from…

This paper proposes a learning based method that can automatically determine how likely a student is to give a correct answer to a problem in an intelligent tutoring system. Only log files that record students' actions with the system are used to train the model, therefore the modeling process doesn't require expert knowledge for identifying…

Describes the "Knowledge Board," a comprehensive integrated writing environment for professionals who write complex documents. Program functions, including navigational capabilities, an automated note card file, information sorting, information weaving, a function to organize information logically, and a revision function are examined.…

Online museums could benefit from digital "lifelike" characters in order to guide users to virtual tours and to customize the tour information to users' interests. Digital characters have been explored in online museum web sites with different degrees of interaction and modes of communication. Such research, however, does not explore…

A museum can talk to its audience through a variety of channels, such as Web sites, help desks, human guides, brochures. A considerable effort is being made by museums to integrate these different means. The Web site can be designed to be reachable or even updateable from visitors inside the museum via touchscreen and wireless devices. But these…

Describes ECAL (extended computer-assisted learning) which was designed to incorporate artificial intelligence ideas to extend traditional CAL tools. Intelligent tutoring systems are discussed; authoring tasks in CAL and intelligent computer-assisted instruction (ICAI) are described; and the general architecture of the system is explained. (8…

This paper examines the evolution of computer software programs designed to support the qualitative research process; the differences between existing qualitative software and Metamorph(TM); and the use of Metamorph(TM) for qualitative research. The paper begins by presenting an overview of computer use in qualitative research, which includes a…

Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…

This paper describes how a language for building information systems that is being developed by the Office for Research at OCLC can be linked to an artificial intelligence environment, Poplog. The demonstration system--ISIS (Intelligent Support for Interface systems)--shows how Poplog could provide some intelligent support for a D interface,…

Discusses knowledge acquisition and dissemination in a network environment. Obstacles to the electronic exchange of knowledge and functional requirements for knowledge acquisition, dissemination, and management are summarized. A prototype intelligent Internet interface that mediates knowledge acquisition and dissemination and preliminary test…

Education delivery systems have evolved from content delivery mechanisms to collaborative environments. The next step in this evolution is to provide greater support for asynchronous learners, those that progress through course material with little or no support from the instructional team. The integration of Web technologies with artificial…

This paper outlines work on a class of systems called Personal Information Management Assistants (PIMAs). PIMAs observe user interaction with everyday applications and use these observations to anticipate a user's information needs. They then automatically fulfill these needs by accessing Internet information sources, filtering the results, and…

Describes a study of users' document selection behavior that was conducted to build a tentative cognitive model of document selection behavior to be used in designing intelligent information retrieval systems. Topics addressed include studies of relevance and of decision making; value judgments; and document information elements considered during…

The growing volume of heterogeneous and distributed information on the World Wide Web has made it increasingly difficult for existing tools to retrieve relevant information. To improve the performance of these tools, this paper suggests how to handle two aspects of the problem. The first aspect concerns a better representation and description of…

Many researchers are attempting to develop automated instructional development systems to guide subject matter experts through the lengthy and difficult process of courseware development. Because the targeted users often lack instructional design expertise, a great deal of emphasis has been placed on the use of artificial intelligence (AI) to…