This study examines the current research on educational data mining, educational learning support services, personalized learning services, and personalized learning paths in education. The authors aim to integrate personalized learning concepts into traditional support services by drawing on the latest theoretical and practical research. Using…

When text datasets are very large, manually coding line by line becomes impractical. As a result, researchers sometimes try to use machine learning algorithms to automatically code text data. One of the most popular algorithms is topic modeling. For a given text dataset, a topic model provides probability distributions of words for a set of…

In this thesis, we study the importance of background knowledge in relation extraction systems. We not only demonstrate the benefits of leveraging background knowledge to improve the systems' performance but also propose a principled framework that allows one to effectively incorporate knowledge into statistical machine learning models for…

A recently developed cost-effectiveness model for on-line retrieval systems is discussed through use of an example utilizing performance results collected from several independent sources and cost data derived for a recently completed study for the American Psychological Association. One of the primary attributes of the model rests in its great…

Describes an information system interface that allows specification of uncertain queries and combines evidence about the relevance of documents to produce an overall ranking. Results of an experiment that addressed some of the cognitive aspects of such an interface are also reported. (22 references) (Author/MES)

Based on systematic observations of five experienced online searchers, this model compares two searching styles: operationalist, which aims at optimal strategies to achieve precise retrieval and uses a large range of system capabilities, and conceptualist, which analyzes the request by seeking to fit it into a faceted structure. (13 references)…

Describes probabilistic document retrieval systems as a sequential learning process, in which the system learns the parameters of probability distributions describing the frequencies of feature occurrences in relevant and nonrelevant documents. Several techniques for estimating the parameters of distributions are described and the results of tests…

Discusses general issues of computer and human understanding; contrasts three paradigms of information retrieval methodology, including statistical, deep semantic or natural language, and smart Boolean; describes CONIT, a knowledge-based intermediary retrieval assistance system; and examines system evaluation procedures, including a…

Presents an interaction model and an experimental method for information retrieval. This automated method helps identify which user and system variables are relevant, which are independent of other variables, and which ranges of the variables are most important. Results show that relevance feedback consistently improves retrieval performance. (AEF)

Presents a stratified model of information retrieval interaction that views interaction as a dialog between participants (user and computer) through an interface. Discusses traditional and interaction models, and extension to relevance, user modeling, search term selection, and types of feedback in information retrieval. (AEF)

Reports results from a study exploring the information retrieval (IR) and types of interactive feedback during mediated IR. Five types of interactive feedback were identified, extending the interactive IR model to include relevance, magnitude, and strategy interactive feedback. Implications for further research investigating the nature and models…

Proposes a "Model of Querying" for users of office filing facilities and discusses its motivation, aspects, attributes, and advantages. A review of current information systems and attempts to combine information retrieval, artificial intelligence, and database management techniques leads to conclusion that no resultant system is adequate…

This paper discusses the complexity of explanation activity in human-human goal-directed dialogue and suggests that this complexity ought to be taken into account in the design of explanation in human-computer interaction. A general model of clarity in human-computer systems is proposed, incorporating explanation as one component. On the basis of…

The contradictory nature of the phrase user-oriented interface (UOI) as commonly applied to retrieval systems is discussed, and a different approach to the problem made feasible through improvements in the technology is described. (Author/JPF)

Introduces a generic, application-independent model of human-computer information-seeking dialog, the Conversational Roles (COR) Model, and reviews the theoretical background. COR is represented as a recursive state-transition-network that determines legitimate types and possible sequences of dialog acts, and categorizes dialog acts on the basis…