User-Tailored Planning of Mixed Initiative Information-Seeking Dialogues

Stein, Adelheit; Gulla, Jon Atle; Thiel, Ulrich

doi:10.1007/978-94-017-1118-0_9

Cited by 8 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, its principles and methods could be used in research designs for information searching. Examples of studies applying task analysis to various degrees in information searching are Belkin, Marchetti, and Cool (1993), Belkin, Cool, Stein, and Theil (1995), Pejtersen (1990), and Stein, Gulla, and Theil (1999).…”

Section: Conceptions Of Tasksmentioning

confidence: 99%

Task‐based information searching

Vakkari

2003

Annual Review Info Sci & Tec

293

232

View full text Add to dashboard Cite

IntroductionThe rationale for using information systems is to find information that helps us in our daily activities, be they tasks or interests. Systems are expected to support us in searching for and identifying useful information. Although the activities and tasks performed by humans generate information needs and searching, they have attracted little attention in studies of information searching. Such studies have concentrated on search tasks rather than the activities that trigger them. It is obvious that our understanding of information searching is only partial, if we are not able to connect aspects of searching to the related task. The expected contribution of information to the task is reflected in relevance assessments of the information items found, and in the search tactics and use of the system in general. Taking the task into account seems to be a necessary condition for understanding and explaining information searching, and, by extension, for effective systems design. Scope and ApproachIn this chapter, I shall review studies on the relationship between task performance and information searching by end-users. I focus mainly on 41 3 414 Annual Review of information Science and Technology information searching in electronic environments, especially in information retrieval (IR) systems. The process of information searching is cyclical, but it can be broken down into the following components:The kind of information that is needed and searched forThe query formulation process, including the choice of search terms and operators Search tacticsThe use of search support tools Relevance and utility judgments regarding the information found Several approaches to characterizing tasks in the literature are in use. In the studies I have found on information searching, tasks have been either characterized as a process consisting of several stages, or this aspect has been left open. In the latter case, the task has been treated as a given and left without characterization; only its context being described. A typical example is observing university students searching for information for study purposes without explicating those purposes. In these studies, the point of departure is searching, not the work task that produces it.Only a limited number of studies relate tasks to searching. Because of this, I take into account studies based on natural search goals, insofar as they further our understanding of task-based searching. I also review a few studies based on assigned search goals. In general, the models and findings are scattered and difficult to integrate into the framework of task-based searching.Ideally, a study should connect the task with the search process in order to analyze their interaction (Belkin, 1990). This sort of study typically requires a longitudinal research design. Due to the rarity of such process analyses, studies that analyze the relation between tasks and searching synchronously are also included. I focus principally on the literature published after 1990 simply because the number of empir...

show abstract

Section: Conceptions Of Tasksmentioning

confidence: 99%

Task‐based information searching

Vakkari

2003

Annual Review Info Sci & Tec

293

232

View full text Add to dashboard Cite

show abstract

“…** Stein et al (1999) focused on providing mixed-initiative capabilities in the context of information retrieval interactions, where users often opportunistically change their goals and strategies. Cesta and D'Aloisi (1999) considered issues of mixed-initiative interaction in the context of delegation-based agent systems (e.g.…”

Section: Interactionmentioning

confidence: 99%

Untitled

Zukerman

Litman

2001

User Modeling and User-Adapted Interaction

View full text Add to dashboard Cite

Abstract. The ¢elds of user modeling and natural language processing have been closely linked since the early days of user modeling. Natural language systems consult user models in order to improve their understanding of users' requirements and to generate appropriate and relevant responses. At the same time, the information natural language systems obtain from their users is expected to increase the accuracy of their user models. In this paper, we review natural language systems for generation, understanding and dialogue, focusing on the requirements and limitations these systems and user models place on each other.We then propose avenues for future research.

show abstract

“…Elsewhere (cf. Belkin et al 1995, Stein et al 1999 we have proposed to tackle this problem in a two-tiered approach: While a logic-based retrieval method should replace simple matching procedures by inferences which take into account domain-specific rules, thesauri, and other knowledge sources, the query processing should be integrated into a flexible human-machine dialogue, allowing for interactive query construction and modification, inspection of interpretations found for ambiguous queries, and convenient exploration of result lists (cf. Thiel et al 1996, Stein et al 1997.…”

Section: Retrieval Support In Digital Libraries: Specific Demandsmentioning

confidence: 99%

Can Rule-Based Indexing Support Concept-BasedMultimedia Retrieval in Digital Libraries? Some Experimental Results∗

Thiel

Everts

Lutes

et al. 1999

Electronic Workshops in Computing

Self Cite

View full text Add to dashboard Cite

The emerging conception of a "digital library" as an information environment in which distributed information sources are made available in an integrated way implies new requirements for indexing and retrieval methods. Therefore, one important research topic in the field of digital libraries is the design of task-specific methods for very precise searching. In addition, we have to anticipate highly dynamic information bases which change continually. This paper outlines an approach which addresses both problems. Rule-based indexing can be used to support highly precise searches in dynamic information bases. The method enables users to perform conceptual searches in image collections, thus going far beyond contemporary content-based retrieval methods for pictorial material. The paper concludes with a discussion of the empirical results obtained so far.

show abstract

User-Tailored Planning of Mixed Initiative Information-Seeking Dialogues

Cited by 8 publications

References 23 publications

Task‐based information searching

Task‐based information searching

Untitled

Can Rule-Based Indexing Support Concept-BasedMultimedia Retrieval in Digital Libraries? Some Experimental Results∗

Contact Info

Product

Resources

About