1	From Information Retrieval to Information Interaction Gary Marchionini University of North Carolina at Chapel Hill march@ils.unc.edu European Conference on Information Retrieval ’04 Sunderland University April 5-7, 2004
2	Content-Centered Retrieval as Matching Document Representations to Query Representations
3	Trend 1: Content Content Features (queries too) Not only text Statistics, images, music, code, streams, biochemical Multimedia, multilingual Dynamic Temporal (e,g., blogs, wikis, sensor streams) Conditional (e.g., computed links, recommendations) Content Relationships Hyperlinks, new metadata, aggregations Digital Libraries, personal collections Content acquires history
4	IR Responses to Trend 1 TREC tracks Link analysis Multiple sources of evidence (fusion) Authors’ words (e.g., full text IR) Indexer/abstractor words (e.g., OPACs) Authors’ citations/links (e.g., ISI, Google) Readers’ search paths (e.g., recommenders, opinion miners) Machine generated features and relationships Two key challenges: What new relationships can we leverage (human and machine)? How can we integrate multiple sources of evidence?
5	Trend 2: Include People Technical advances and technical literacy allows us to leverage information seeker intelligence Rather than sole dependence on matching algorithms, focus on flow of representations and actions in situ as people think with these new tools and information resources Web has legitimized browsing as human-controlled information seeking To leverage human intelligence and effort, people must assume responsibilities: beyond the two-word, single query
6	IR Responses to Trend 2 Relevance feedback Query expansion User modeling/profiles, SDI services Recommender systems Explicit and implicit models Capture everything (e.g., Lifebits) User Interfaces Dynamic queries Agile views
7	An Expanded Model: Think of IR from the perspective of an active human with an information need and powerful IR resources
8	User-Centered Information-Seeking Process: Current State
9	Examples of getting people involved in continuous decision making and interaction with information resources: dynamic queries and the agile views interaction framework
10	Open Video Example www.open-video.org Open access digital library of digital video for education and research 2000+ video segments: MPEG1, MPEG-2, MPEG-4, QuickTime Agile Views Design Framework Different types of views Overviews, previews, shared views Multiple examples of views Dynamic control mechanisms
11	Alternative Overviews of Result Sets
12	Alternative Previews for a Specific Video Segment
13	Relation Browser Example www.idl.ils.unc.edu/rave A general purpose dynamic query interface for databases with a small number of facets (~10) and a small number of categories in each facet (~10). Easy to look ahead (overviews and previews) Latest version combines interactive partitioning with string query
14	Relation Browser Start State for Energy Information Admin Website
15	Mousing over “Coal” under the “Fuel type” category reveals the distribution of coal related web pages to other categories
16	Click on Natural Gas and Mouse over Residential Sector
17	RB++ showing ‘hous’ typed in title field
18	Some Interaction Principles and Caveats in these examples Principles Look ahead without penalty Minimize scrolling and clicking Alternative ways to slice and dice Minimize delays Caveats Scalability (getting metadata to client side) Metadata crucial We are working on automatically creating partitions
19	The Long View: Requirements for Seamless Interaction with Information Improved I/O and control mechanisms Information need articulation (e.g., paste, voice, gesture) Mobile displays (AR glasses, projected) Context management The world (time, space, other people) The information seeker (history, privacy) Information resources (ubiquitous) Evaluation methods and metrics
20	Long Term Paradigm: Information Interaction as Core Life Process My examples represent early ways to get the information seeker more involved in the IR process—there is plenty more to do. Like eating we have varying expectations, invest different levels of effort, and use diverse and ubiquitous infrastructures. IR R&D provides the resources and tools for helping people work and learn in the emerging cyberinfrastructure
21	Thank You! Questions and Discussion