This award provides support for the "Workshop on Task-based Information Search Systems", to be held March 14-15, 2013 in Chapel Hill, NC with the goal to discuss challenges of designing a new generation of information search systems that go beyond simple searches and can support people in resolving a underlying need or task. While contemporary search engines are good at helping people resolve simple look-up tasks, they are not as useful in helping people engaged in more complex tasks whose resolution might require multiple search sessions and multiple search strategies. Most search environments are tailored to support a small set of basic search tasks and provide searchers with few options to search and interact with information, and little to help them synthesize and integrate information across session. Participants of the workshop, leading researchers in interactive information retrieval from academia and industry will discuss challenges of incorporating task models into systems and tools to support complex, multi-search and multi-session tasks. The goal of this workshop is to enumerate, discuss, and document these issues into a research agenda that can help guide work in this field. Specifically, this workshop is focusing on the following topics: (1) identification, elicitation, modeling and tracking of tasks, processes and states, including the identification of frameworks for conceptualizing task and relevance models; (2) creation of task-specific and task-aware search environments, including the development of interfaces, tools, features, indexing techniques and search algorithms; and (3) development of methods and measures for studying user behavior and evaluating task-based search systems, including session-based measures.
The workshop will outline directions for short, mid-, and long-term research, seed interdisciplinary and international collaborations and generate a unified and multidisciplinary bibliography for researchers and students interested in working in this area. Workshop will include junior and underrepresented attendees in order to broaden participation in computer science. Workshop results will be summarized in a report that will be disseminated via the workshop web site (http://ils.unc.edu/taskbasedsearch) and various publications. In addition, it is expected that general users of search tools will benefit from resulting advances in technology that will provide better tools and services to support task-based retrieval across multiple search sessions.
When people seek information, they typically do so in order to resolve some underlying need or task, such as finding a bus schedule to plan travel, finding a recipe to make a dish for a potluck dinner, or finding the homepage of an author of a recently read book to see what other books she has published. While contemporary search engines are good at helping people resolve these types of look-up tasks, they are not as useful in helping people engaged in more complex tasks whose resolution might require multiple search sessions and multiple search strategies. Instead, search engines are optimized for particular types of tasks (e.g., look-up tasks and commerce tasks such as travel and shopping), for particular types of search behaviors (i.e., enter a query, review snippets, make a transaction) and for particular types of searchers (i.e., those who want to quickly find a single piece of information). Search engines are not optimized for tasks that require sustained interaction and engagement with information, the use of multiple, diverse search approaches to finding information or for searchers who want to cultivate a deeper, internalized understanding of a problem or topic. This 2-day workshop gathered leading researchers in information retrieval, human-computer interaction and information behavior to discuss challenges and opportunities associated with the development of information search systems and tools to support people involved with complex, multi-search and multi-session search tasks. Such task-based search systems present many challenges, and the goal of this workshop was to enumerate, discuss and document these challenges into a research agenda to guide future research. Major research frontiers identified during the workshop included the development of domain-neutral modeling techniques to represent tasks, task properties and task-related search behaviors, interface support tools to assist with a variety of task-related information behaviors and the identification of techniques and tools to evaluate task-based search systems. The most critical need identified was the development of task models; this was viewed as essential for addressing the challenges of tools and evaluation measures.
