1. Interaction LBSC 796/INFM 718R Douglas W. Oard Week 4, October 1, 2007

2. Moore’s Law transistors speed storage... 195019902030 computer performance

3. Human Cognition 1990 195019902030 human performance

4. Where is the bottleneck? Slide idea by Bill Buxton system vs. human performance

5. Interaction Points Source Selection Search Query Selection Ranked List Examination Documents Delivery Documents Query Formulation Resource source reselection System discovery Vocabulary discovery Concept discovery Document discovery Help users decide where to start Help users formulate queries Help users make sense of results and navigate information space

6. Information Needs RIN 0 PIN 0 PIN m r0r0 r1r1 q0q0 … q1q1 q2q2 q3q3 rnrn qrqr Stefano Mizzaro. (1999) How Many Relevances in Information Retrieval? Interacting With Computers, 10(3), 305-322. Real information needs (RIN) = visceral need Perceived information needs (PIN) = conscious need Request = formalized need Query = compromised need

7. Anomalous State of Knowledge Belkin: Searchers do not clearly understand –The problem itself –What information is needed to solve the problem The query results from a clarification process Dervin’s “sense making”: Need GapBridge

8. Q0 Q1 Q2 Q3 Q4 Q5 A sketch of a searcher… “moving through many actions towards a general goal of satisfactory completion of research related to an information need.” Bates’ “Berry Picking” Model

9. Broder’s Web Query Taxonomy Navigational (~20%) –Reach a particular site (“known item”) Informational (~50%) –Acquire static information (“topical”) Transactional (~30%) –Perform a Web-mediated activity (“service”) Andrei Broder, SIGIR Forum, Fall 2002

10. Some Desirable Features Make exploration easy Relate documents with why they are retrieved Highlight relationships between documents

11. Agenda  Query formulation Selection Examination Source selection Project 3

12. Query Formulation Command Language Form Fill-in Menu Selection Direct Manipulation Natural Language Ben Shneiderman, 1997

13. WESTLAW® Query Examples What is the statute of limitations in cases involving the federal tort claims act? –LIMIT! /3 STATUTE ACTION /S FEDERAL /2 TORT /3 CLAIM What factors are important in determining what constitutes a vessel for purposes of determining liability of a vessel owner for injuries to a seaman under the “Jones Act” (46 USC 688)? –(741 +3 824) FACTOR ELEMENT STATUS FACT /P VESSEL SHIP BOAT /P (46 +3 688) “JONES ACT” /P INJUR! /S SEAMAN CREWMAN WORKER Are there any cases which discuss negligent maintenance or failure to maintain aids to navigation such as lights, buoys, or channel markers? –NOT NEGLECT! FAIL! NEGLIG! /5 MAINT! REPAIR! /P NAVIGAT! /5 AID EQUIP! LIGHT BUOY “CHANNEL MARKER” What cases have discussed the concept of excusable delay in the application of statutes of limitations or the doctrine of laches involving actions in admiralty or under the “Jones Act” or the “Death on the High Seas Act”? –EXCUS! /3 DELAY /P (LIMIT! /3 STATUTE ACTION) LACHES /P “JONES ACT” “DEATH ON THE HIGH SEAS ACT” (46 +3 761)

14. Form-Based Query Specification Credit: Marti Hearst

15. Direct Manipulation Spec. VQUERY (Jones 98) Credit: Marti Hearst

16. The “Back” Button Behavior is counterintuitive to many users A B D C You hit “back” twice from page D. Where do you end up?

17. PadPrints Tree-based history of recently visited Web pages –History map placed to left of browser window –Node = title + thumbnail –Visually shows navigation history Zoomable: ability to grow and shrink sub- trees

18. Visual Browsing History in PadPrints

19. PadPrints Thumbnails

20. Alternate Query Modalities Spoken queries –Used for telephone and hands-free applications –Reasonable performance with limited vocabularies But some error correction method must be included Handwritten queries –Palm pilot graffiti, touch-screens, … –Fairly effective if some form of shorthand is used Ordinary handwriting often has too much ambiguity

21. Agenda Query formulation  Selection Examination Source selection Project 3

22. A Selection Interface Taxonomy One dimensional lists –Content: title, source, date, summary, ratings,... –Order: retrieval status value, date, alphabetic,... –Size: scrolling, specified number, score threshold Two dimensional displays –Construction: clustering, starfield, projection –Navigation: jump, pan, zoom Three dimensional displays –Contour maps, fishtank VR, immersive VR

23. Google: KeyWord In Context (KWIC) Query: University of Maryland College Park

24. Summarization

25. Indicative vs. Informative Terms often applied to document abstracts –Indicative abstracts support selection They describe the contents of a document –Informative abstracts support understanding They summarize the contents of a document Applies to any information presentation –Presented for indicative or informative purposes

26. Selection/Examination Tasks “Indicative” tasks –Recognizing what you are looking for –Determining that no answer exists in a source –Probing to refine mental models of system operation “Informative” tasks –Vocabulary acquisition –Concept learning –Information use

27. Generated Summaries Fluent summaries for a specific domain Define a knowledge structure for the domain –Frames are commonly used Analysis: process documents to fill the structure –Studied separately as “information extraction” Compression: select which facts to retain Generation: create fluent summaries –Templates for initial candidates –Use language model to select an alternative

28. Extraction-Based Summarization Robust technique for making disfluent summaries Four broad types: –Query-biased vs. generic –Term-oriented vs. sentence-oriented Combine evidence for selection: –Salience: similarity to the query –Specificity: IDF or chi-squared –Emphasis: title, first sentence

29. Goldilocks and the Three Summaries… The entire document: too much! The exact answer: too little! The surrounding paragraph: just right… It occurred on July 4, 1776. What does this pronoun refer to? Jimmy Lin, Dennis Quan, Vineet Sinha, Karun Bakshi, David Huynh, Boris Katz, and David R. Karger. (2003) What Makes a Good Answer? The Role of Context in Question Answering. Proceedings of INTERACT 2003.

30. Ask: Suggested Query Refinements

31. Open Directory Project http://www.dmoz.org

32. SWISH List Interface Category Interface Query: jaguar Hao Chen and Susan Dumais. (2000) Bringing Order to the Web: Automatically Categorizing Search Results. Proceedings of CHI 2000.

33. Text Classification Problem: automatically sort items into bins Machine learning approach –Obtain a training set with ground truth labels –Use a machine learning algorithm to “train” a classifier kNN, Bayesian classifier, SVMs, decision trees, etc. –Apply classifier to new documents System assigns labels according to patterns learned in the training set

34. Machine Learning label 1 label 2 label 3 label 4 Text Classifier Supervised Machine Learning Algorithm Unlabeled Document label 1 ? label 2 ? label 3 ? label 4 ? Testing Training Training examples Representation Function

35. k Nearest Neighbor (kNN) Classifier

36. kNN Algorithm Select k most similar labeled documents Have them “vote” on the best label: –Each document gets one vote, or –More similar documents get a larger vote How can similarity be defined?

37. Cat-a-Cone

38. Key Ideas: –Separate documents from category labels –Show both simultaneously –Link the two for iterative feedback –Integrate searching and browsing Distinguish between: –Searching for documents –Searching for categories

39. Collection Retrieved Documents Category Hierarchy browse query terms search Cat-a-Cone Architecture

40. The Cluster Hypothesis “Closely associated documents tend to be relevant to the same requests.” van Rijsbergen 1979

41. Vivisimo: Clustered Results http://www.vivisimo.com

42. Kartoo’s Cluster Visualization http://www.kartoo.com/

43. Clustering Result Sets Advantages: –Topically coherent document sets are presented together –User gets a sense for the themes in the result set –Supports browsing retrieved hits Disadvantages: –May be difficult to understand the theme of a cluster based on summary terms –Clusters themselves might not “make sense” –Computational cost

44. Visualizing Clusters Centroids

45. Hierarchical Agglomerative Clustering

46. Another Way to Look at H.A.C. ABCDEFGHABCDEFGH

47. The H.A.C. Algorithm Start with each document in its own cluster Until there is only one cluster: –Determine the two most similar clusters c i and c j –Replace c i and c j with a single cluster c i  c j The history of merging forms the hierarchy

48. Cluster Similarity Assume a similarity function that determines the similarity of two instances: sim(x,y) –What’s appropriate for documents? What’s the similarity between two clusters? –Single Link: similarity of two most similar members –Complete Link: similarity of two least similar members –Group Average: average similarity between members

49. K-Means Clustering Pick seeds Reassign clusters Compute centroids x x Reasssign clusters x x x x Compute centroids Reassign clusters Converged!

50. K-Means Each cluster is characterized by its centroid (center of gravity): Reassignment of documents to clusters is based on distance to the current cluster centroids

51. K-Means Algorithm Let d be the distance measure between documents Select k random instances {s 1, s 2,… s k } as seeds Until clustering converges: –Assign each instance x i to the cluster c j such that d(x i, s j ) is minimal –Update the seeds to the centroid of each cluster –For each cluster c j, s j =  (c j )

52. K-Means: Discussion How do you select k? Results can vary based on random seed selection –Some seeds can result in poor convergence rate, or convergence to sub-optimal clusters

53. symbols8 docs film, tv 68 docs astrophysics97 docs astronomy67 docs flora/fauna10 docs Clustering and re-clustering is entirely automated sports14 docs film, tv47 docs music7 docs stellar phenomena12 docs galaxies, stars49 docs constellations29 docs miscellaneous7 docs Query = “star” on encyclopedic text Scatter/Gather

54. Sustem clusters documents into “themes” –Displays clusters by showing: Topical terms Typical titles User chooses a subset of the clusters System re-clusters documents in selected cluster –New clusters have different, more refined, “themes” Marti A. Hearst and Jan O. Pedersen. (1996) Reexaming the Cluster Hypothesis: Scatter/Gather on Retrieval Results. Proceedings of SIGIR 1996.

57. Summary: Clustering Advantages: –Provides an overview of main themes in search results –Helps overcome polysemy Disadvantages: –Documents can be clustered in many ways –Not always easy to understand the theme of a cluster –What is the correct level of granularity? –More information to present

58. Recap Clustering –Automatically group documents into clusters Classification –Automatically assign labels to documents

59. Agenda Query formulation Selection  Examination Source selection Project 3

60. Examining Individual Documents

61. Document lens Robertson & Mackinlay, UIST'93, Atlanta, 1993

62. Distorting Reality Bifocal Perspective Wall Fisheye

63. 1-D Fisheye Menu http://www.cs.umd.edu/hcil/fisheyemenu/fisheyemenu-demo.shtml

64. 1-D Fisheye Document Viewer

65. SeeSoft [Eick 94]

66. Mainly about both DBMS and reliability Mainly about DBMS, discusses reliability Mainly about, say, banking, with a subtopic discussion on DBMS/Reliability Mainly about high-tech layoffs TileBars Topic: reliability of DBMS (database systems) Query terms: DBMS, reliability DBMS reliability DBMS reliability DBMS reliability DBMS reliability

67. U Mass: Scrollbar-Tilebar

68. Agenda Query formulation Selection Examination  Source selection Project 3

69. ThemeView Pacific Northwest National Laboratory http://www.pnl.gov/infoviz/technologies.html

70. WebTheme

71. Ben S’ ‘Seamless Interface’ Principles Informative feedback Easy reversal User in control –Anticipatable outcomes –Explainable results –Browsable content Limited working memory load –Query context –Path suspension Alternatives for novices and experts Scaffolding

72. My ‘Synergistic Interaction’ Principles –Interdependence with process (“interaction models”) Co-design with search strategy Speed –System initiative Guided process Exposing the structure of knowledge –Support for reasoning Representation of uncertainty Meaningful dimensions –Synergy with features used for search Weakness of similarity, Strength of language –Easily learned Familiar metaphors (timelines, ranked lists, maps)

73. Some Good Ideas Show the query in the selection interface –It provides context for the display Suggest options to the user –Query refinements, for example Explain what the system has done –Highlight query terms in the results, for example Complement what the system has done –Users add value by doing things the system can’t –Expose the information users need to judge utility

74. Agenda Query formulation Selection Examination Source selection  Project 3

75. Expertise@Maryland Goal –Create a system to help research administration identify faculty members with specific research interests Design Criteria –Maximize reliance on available information –Help the user, but don ’ t try to replace them –Offer immediate utility to untrained users

76. Faculty Activity Report Papers Grant proposals University database Multiple repositories List of papers Descriptive terms Expertise search engine

77. Faculty Activity DB Get faculty Publications Bibliographic Reference Extractor Extract publication author, title, journal,date from faculty activity DB entries PDFs from Web resources Obtain digital copies of publications from Library e-resources Format Conversion Extract content words from PDF Build Index Search Engine Use terms to find faculty members strongly connected to those terms Interface Enter search terms, examine “hit list”, refine search terms, … Automatically associate descriptive terms with faculty members

78. One Minute Paper When examining documents in the selection and examination interfaces, which type of information need (visceral, conscious, formalized, or compromised) guides the user’s decisions? Please justify your answer.