Method and apparatus for sociological data analysis

• US 7,519,589 B2
• Filed: 07/31/2006
• Issued: 04/14/2009
• Est. Priority Date: 02/04/2003
• Status: Expired due to Term

• Current Assignee: Adobe Inc.
• Original Assignee: Cataphora Incorporated
• Inventors: Charnock, Elizabeth, Roberts, Steven L., Bothra, Arpit, Brouk, Roman, Nystrom, Jonathan D., Espanol, Joanes C., Schon, Keith, Thompson, Curtis
• Primary Examiner(s): LEWIS, CHERYL RENEA
• Application Number:
  US11/497,199
• Publication Number:
  US 20060271526A1
• Time in Patent Office: 988 Days
• Field of Search: 707/10, 707/100, 707/104.1, 707 2- 5, 715200-201, 715/210
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A method to enable improved analysis and use of sociological data, the method comprising identifying causal relationships between a plurality of documents, identifying a plurality of characteristics of a communication, including a modality used, actors involved, proximate events of relevance, and enabling a user to query based on all of the characteristics available.

Claims

1. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, proximate events of relevance and a tone used by an actor in the communication; and

enabling a user to query based on all of the characteristics available.

2. The method of claim 1, wherein the characteristics further comprise a predominant tone used in a discussion.

3. The method of claim 1, further comprising:

determining a percentage of communication with respect to a topic which utilizes a tone; and

tagging the communication with an appropriate indicator to illustrate a predominant tone.

4. The method of claim 1, further comprising:

identifying a pattern of tonal usage on the part of an individual actor with respect to other actors; and

identifying deviations from the pattern of tonal usage; and

associating specific topics, actors, events of importance, or changes in communications patterns associated with the deviation.

5. The method of claim 4 further comprising:

identifying unusual quotes or capitalization as indications of sarcasm.

6. The method of claim 4, further comprising:

classifying an item as hot or worthy of special examination, based on a tone associated with the item.

7. The method of claim 4, further comprising:

displaying overall tonal content per time period for an actor, to identify anomalies.

8. The method of claim 7, wherein the display is a matrix, with years displayed along the Y-axis, to enable a comparison on a seasonal basis.

9. The method of claim 1, further comprising:

identifying, for a particular actor, divergence in tones in communications with different actors on a particular topic within a given timeframe.

10. The method of claim 1, further comprising:

illustrating a range of tones used in communications between two actors over time, for sending and receiving messages.

11. A method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

determining a tone used in communication between actors; and

adjusting the determination based on communication modality.

12. A method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

identifying the modality of the communication when displaying a discussion.

13. The method of claim 12, further comprising:

establishing an actor heartbeat based on an activity level, the activity level differentiated between the modalities of communication.

14. The method of claim 13, further comprising:

utilizing the actor heartbeat to identify periods of vacation, illness, or business travel.

15. The method of claim 13, further comprising:

utilizing the actor heartbeat to identify missing activities or abnormally low activities to identify deletions.

16. The method of claim 13, wherein the modalities include:

telephone;

instant messaging, calendar, in-person meetings, creation of documents, editing of documents.

17. A method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

evaluating actor behavior over time, to create a threshold behavior for the actor; and

identifying deviations from the threshold behavior.

18. The method of claim 17, further comprising:

relating the deviation from the threshold behavior to relevant events.

19. The method of claim 17, wherein the behavior includes one or more of the following:

a reply cycle to communications, tone used, communications modality used.

20. The method of claim 17, further comprising:

displaying an average length and a total number of discussions for a topic selected by a user, as well as the number of discussions that ended in a meeting event.

21. The method of claim 20, further comprising:

highlighting deviations from a normal number of such interactions for a particular occurrence of the topic.

22. A method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

identifying potential meeting events which may or should have occurred based on data in the corpus of documents; and

classifying the meeting event in one or more of the following categories;

ad hoc, scheduled, cancelled, shortened, lengthened, calendared, rescheduled, requested, declined, attended remotely.

23. The method of claim 22, further comprising:

determining if a particular actor was present at the meeting event.

24. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance; and

enabling a user to query based on all of the characteristics available;

wherein identifying causal relationships further comprises associating text of a supportive document with a meeting event, ensuring that the meeting event is retrieved for queries including terms in the supportive document.

25. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

identifying mixed type discussions which have at least one meeting event.

26. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

calculating a probability of a meeting event occurring in a conversation, and depicting the probabilities for various discussions.

27. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

analyzing communications to identify normal paths of communication between actors; and

identifying a communication to which, according to the normal paths of communication, a particular actor should have been invited but was not.

28. The method of claim 27, wherein the communication is a meeting event.

29. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

using colorful indicators for relevant occurrences to ensure that the indicator is visible in a thumbnail image size.

30. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

time slicing data by creating substantially equal increments of time within a time interval of interest specified by the user, and creating a snapshot image for each time increment to provide a depiction of data for the user.

31. The method of claim 30, wherein the snapshots are presented as one of the following:

a set of thumbnail images, a matrix of images aligned vertically by time period, or in a sequential fashion as a movie.

32. A method to enable improved analysis and use of sociological data, the method of comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

depicting communications between a plurality of actors using communication lines between the actors; and

enabling graphical queries based on selecting the communication lines between actors.

33. The method of claim 32, wherein the communications lines identify the communication as in-person, via telephone, via email, via TM, via fax, via pager, via conference call.

34. The method of claim 32, wherein the communications depicted by communication lines include meeting events.

35. The method of claim 32, further comprising:

enabling a user to access documents associated with a communication line via the communications graph.

36. The method of claim 32, wherein the communications line reflects one or more separate communications, and further comprising:

itemizing the one or more communications on mouse over of the communications line.

37. The method of claim 32, further comprising:

displaying the communications graph to illustrate communications between a set of actors, in response to a search query; and

displaying a special icon for a meeting event between more than two actors.

38. The method of claim 37, wherein the meeting event is selected from among:

an in-person meeting, and telephone conference.

39. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

overlaying an organization chart over a communications graph displaying communication between actors, to enable a user to see unusual communications patterns.

40. The method of claim 39, further comprising:

highlighting a missing link, indicating that a particular actor had a substantially different level of communication with another actor compared to equivalently positioned actors.

41. The method of claim 39, further comprising:

highlighting an “

extra”

link, indicating that a particular actor that is outside of channels was included in the communication.

42. The method of claim 39, further comprising:

identifying a boundary between groups within the organization; and

highlighting communications which cross the boundary.

43. The method of claim 39, further comprising:

enabling the overlaying for searches and graphical queries, to enable the identification of anomalies by topic, relevant event, time period.

44. The method of claim 39, further comprising:

generating a graph of a spread of knowledge regarding an issue through actors in an organization, based on utilization of identifiers for the issue.

45. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

depicting communications between a plurality of actors using communication lines between the actors in relationship with a structural relationship chart.

46. The method of claim 45, further comprising:

highlighting abnormal levels of communication between actors.

47. The method of claim 45, further comprising:

enabling a user to select actor characteristics for this depiction, wherein the characteristics may include;

race, religion, gender, national origin, length of time at company.

48. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

identifying instruction relaying by identifying instruction language in communication, and identifying an instruction giver and an interpreter; and

displaying a communication graph based on instruction relaying.

49. The method of claim 48, further comprising:

differentiating between a real instruction and a mere forward.

50. The method of claim 49, further comprising:

measuring actor proximity based on interactions, including the use of mere forwards.

51. The method of claim 49, further comprising:

separately highlighting real instruction giver, mere forwarding instruction giver, interpreter of forwarding instruction, and interpreter of real instruction.

52. The method of claim 48, further comprising:

in the communication graph, highlighting actors as givers and interpreters based on reaching a threshold level.

53. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

extracting formulas from spreadsheets; and

identifying a basis for differences between the spreadsheets including differences in manually entered information and differences in formulas to assist in determining whether the spreadsheets are related.

54. The method of claim 53, further comprising:

identifying whether the formulas are the same and identifying if the formulas are supersets, and if so, determining that the spreadsheet is related.

55. The method of claim 53, further comprising:

identifying a number of cells that differ because of the formulas and because of the manually entered information; and

if a number of non-formulaic changes is small, determining that the spreadsheets are related as families.

56. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

enabling a user to select multiple matters, and perform queries across the multiple matters.

57. The method of claim 56, further comprising:

enabling a user to conjoin information from the multiple matters to form a new discussion.

58. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

a timeline view to depict one or more items related to a discussion in parallel along a timeline, to enable a user to see overlapping items, as well as the duration of each item.

59. The method of claim 58, wherein the item shown in the timeline view comprises one or more of the following:

email, IM, SMS, phone call activity, journal entries, travel status of actors, notes, external events of importance, and calendar entries.

60. The method of claim 58, wherein the timeline view further comprises indicators for a start time and stop time associated with a relevant subpoena.

61. The method of claim 58, further comprising:

visually differentiating work and non-work times, relative to a determined work habit of an actor.

62. The method of claim 61, further comprising:

in a discussion, visually differentiating the work and the non-work times based on a predominant actor'"'"'s work habits.

63. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

further including global controls available to a user to code a group of documents at the same time.

64. The method of claim 63, further comprising:

providing a control that promotes a state of an individual document to the global controls.

65. The method of claim 63, further comprising:

local controls enabling a user to override the code applied with the global controls on a per document basis.

66. The method of claim 65, wherein the local controls for an item are visible only when the item is coded differently from the global code.

67. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

displaying a plurality of controls for a current user interface display, the controls being defined by a document type currently being displayed.

68. The method of claim 67, further comprising:

adding the controls defined by the current document type to a list of available global controls if multiple items of the document type are part of a current collection of items.

69. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

enabling a user to categorize items for production;

providing an interface mechanism to enable a user to select certain content in a document and indicate a category for the content; and

enabling a user to indicate that the certain content places all other documents including that content in the same category.

70. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

further including a duplicate indicator to indicate when documents are one of the following;

true duplicates, near duplicates, or prior or subsequent versions, or different formats of the same document.

71. The method of claim 70, further comprising:

when displaying a document for review, indicating a tally of prior reviews of the document and near duplicate documents.

72. The method of claim 71, further comprising:

determining a level of unanimity of the prior reviews, and if the level of unanimity is above a threshold, labeling the item.

73. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

when displaying responsive data exchanges, displaying the exchanges in ascending or descending order.

74. The method of claim 73, further comprising:

in communications containing quoted text, enabling a user to hide redundant quoted text.

75. The method of claim 73, further comprising:

in communications containing quoted text, enabling a user to hide quoted text by author.

76. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

associating one or more electronic identities with each author; and

identifying human identified electronic identities separately from system-identified electronic identities.

77. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

in a search query enabling a user to associate communications with an actor that have one or more of the following features;

to an actor, from the actor, created by the actor, modified by the actor, and about the actor.

78. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

analyzing an actor'"'"'s communications over a determined time period;

displaying an actor information report, including a percentage communication devoted to a designated topic.

79. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

enabling a user to configurably highlight actor names, and any text that is attributable to them, on any basis.

80. The method of claim 79, further comprising:

enabling the user to select the actor names for highlighting based on any available actor characteristics.

81. The method of claim 80, wherein the characteristics may include one or more of the following criteria:

privileged status, actor group, one or more actors returned by a particular query, and individually identified actor.

82. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

identifying an item having an associated custodian identity which does not provide an exact match with a known actor name;

identifying edit distance between the custodian identity and the known actor names; and

ordering the available known actors based on an edit distance.

83. A method to enable improved analysis and use of sociological data to create a sociological relationship, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance; and

enabling a user to query based on all of the characteristics available;

wherein creating a sociological relationship comprises correctly identifying actors, and correctly identifying actors comprises;

enabling a user to correct automated actor identification by assigning an electronic identity to an actor or remove an electronic identity from an actor; and

enabling a user to add, remove, and modify attributes associated with an actor, the attributes including one or more of the following;

organizational membership, privileged status, and country of residence.

84. The method of claim 83, further comprising:

verifying the correction made by the user based on one or more of the following;

classification of actor-associated items by other users, linguistic fingerprinting, and number of documents already reviewed with the erroneous assignment.

85. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

building a discussion including interrelated collections of items; and

exploding the discussion when the discussion includes items that must be placed in different stages in a review workflow according to workflow rules, the exploding separating the discussion into discrete chunks.

86. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

enabling addition of new items to a discussion after review has been initiated and processing the new items by doing one or more of the following;

separating the new items into separate clusters and adding a notification to the discussion indicating the existence of the new items;

joining the new items to the discussion, but isolating the new items to enable easy examination, without reexamining the discussion;

joining new items to the discussion, but designating the discussions and individual new items with appropriate visual indicators;

joining new items to the discussion, and applying global settings to the new items if the new items are homogeneous with the discussion;

joining new items to the discussion, and analyzing the new items and system-calculated settings to the new items.

87. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

determining a personal proximity and a professional proximity and overall proximity between actors.

88. The method of claim 87, further comprising:

weighing one or more of the following to determine proximity between actors;

multi-topic communications, communications regarding attendance at social events, use of a large range of tones, use of different communications channels, use of short format messages, and use of salutation.

89. The method of claim 87 further comprising:

identifying divergence between the proximity between actors and a tone used in a communication between actors.

90. The method of claim 87, further comprising:

illustrating communications between two actors with a tone and proximity component.

91. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

analyzing sequential backups to identify old data which was also present in a previous backup, data that was in a previous backup and now is missing, data that was missing in a previous backup but is old data, and new data.

92. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

identifying named entities using application metadata, selected from among data in custom dictionaries and address books on users'"'"' system; and

determining common misspellings based on auto-correct settings in users applications.

93. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

identifying a baseline document lifecycle for a given type of document type, the document lifecycle is a set of stages that documents of the given type typically move through, from initial creation to ultimate abandonment.

94. The method of claim 93, further comprising:

identifying bursts of activity with respect to a document, the bursts of activity involving multiple activities in close time proximity.

95. The method of claim 94, further comprises:

assigning version numbers to a document for each lifecycle event, wherein major numbers are assigned by the burst of activity, and minor numbers by sequential user-saved changes.

96. The method of claim 94, further comprising:

comparing the life cycle events and the bursts of activity for documents related to the event for multiple occurrences of the event over time.

97. The method of claim 93, further comprising:

relating the lifecycle events for one or more documents related to an event to the event along a timeline.

98. The method of claim 97, further comprising:

relating the lifecycle events for a document to a workflow associated with documents of a given type.

99. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

providing an item information report to display a history of a particular item, including links to each actual version of the item available in the corpus.

100. The method of claim 99, wherein the item information report includes one or more of the following:

a list of custodians;

a list of actors that deleted the item;

sequential list of all dates and times that something occurred with the item;

, document lifecycle events;

actors who edited, sent, received the item; and

a list of actors who should have received the item but did not.

101. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

further comprising tools to enable an administrator to review logs of user actions and apply corrections to incorrect user actions.

102. The method of claim 101, further comprising:

enabling an authorized user to globally replace document classifications.

103. The method of claim 101, further comprising:

displaying clusters of documents based on classification, to flag heterogeneous clusters for additional review.

104. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

further correcting for email corruption based problems by

identifying emails based on hashes of header information;

creating frequency occurrence table based on content of emails; and

comparing frequency occurrence table, and identifying emails as identical, corrupted, or compared as a result of hash collision.

105. The method of claim 104, further comprising:

enabling a user to select a preferred copy of an email for future use.

106. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

enabling a search for individuals including actors and system users to determine who has seen, received, or acted on a particular document.

107. The method of claim 106, further comprising:

identifying system users who are also actors, and document review decisions made by system users upon their own work.

108. The method of claim 106, further comprising:

creating a batch of data and automatically batch assigning the data based on current reviewer performance characteristics of similar data-types.

109. The method of claim 108, further comprising:

projecting review completion time, based on a current number of documents, currently available reviewers, batch type assignments, and the current reviewer performance characteristics.

110. The method of claim 108, further comprising:

projecting review completion time based on a hypothetical scenario input by the user.

111. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

pre-tagging data based on determined topical content; and

performing a comparison between tagging and human reviewer decisions.

112. The method of claim 111, further comprising:

generating a report showing a time-per document, and a time-per pre-flagged document.

113. The method of claim 111, further comprising:

evaluating a disagreement between human reviewer decisions and pre-tagging decisions to correct pre-tagging mistakes and evaluate human reviewer performance.

114. The method of claim 113, further comprising:

creating a report noting differences in reviewer decisions for similar documents that do not have objectively different classifications.

115. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

enabling the creation of a hierarchy of folders to sort data from the corpus for research purposes.

116. The method of claim 115, further comprising:

defining a findings folder containing only items whose content is determined by a user to relate to a specific topic, and to providing a definitive conclusion regarding the specific topic.

117. The method of claim 116, wherein the definitive conclusion is:

true, false, or unknown, probably true, probably false.

118. The method of claim 117, further comprising:

enabling a user to create a decision tree to reach the definitive conclusion.

119. The method of claim 116, further comprising:

identifying multiple findings folders which contain significantly overlapping data sets, and alerting users of the overlap to ensure that duplication of work is minimized.

120. The method of claim 116, further comprising:

enabling a user to construct a query by selecting a subset of the hierarchy of folders.

121. The method of claim 116, further comprising:

enabling a user to assign priorities to findings folders; and

enabling de-duplication of an item between findings folders, where the findings folder with the highest priority receives the item.

122. The method of claim 121, further comprising:

enabling a user to highlight an item or data within a document as being of high interest relative to the issues of the findings folder; and

enabling the addition of notes to the highlight; and

creating a separate object from the highlighted data for storage in the folder.

123. The method of claim 122, further comprising:

utilizing the separate object from the highlighted data for relevance searching.

124. The method of claim 116, further comprising:

profiling the findings folder based on the attributes of the items in the findings folder.

125. The method of claim 116, further comprising:

tagging each item that is in a findings folder with an attribute identifying it as “

important”

within a corpus, the attribute available for searches of the corpus elsewhere in the system.

126. The method of claim 115, further comprising:

automatically organizing the hierarchy of folders based on a degree of overlap between the folders.

127. The method of claim 126, further comprising:

generating a report illustrating the degree of overlap between findings folders.

128. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

clustering content of a folder; and

creating reports on groups of items in the folder which share user-selected attributes.

129. The method of claim 128, wherein the report includes a timeline illustrating a period of time that is covered by each group of items.

130. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

providing a configurable query window to enable a user to specify a set of items to include in the query, including an actual query, and a presentation style for showing results.

131. The method of claim 130, wherein the presentation styles comprise one of the following:

main view with query controls, main view, time elapsed style, thumbnail style and tabular.

132. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

enabling a user in a query window to construct a query and save the query for reuse.

133. The method of claim 132, further comprising:

providing fully-customizable controls that are part of a query specification, which may be customized through the query window itself.

134. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

wherein the corpus includes documents including items not originally in a text file form.

135. The method of claim 134, wherein items that were not originally in written form include audio data, video data, instant messaging (TM) data, calendar data, telephone record data, and database data.

136. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available; and

enabling an automatic selection of a subset of a corpus of documents for production.

137. The method of claim 136, further comprising:

presenting a user interface through which the user may review the automatic selection of. a subset of a corpus of documents for production.

138. The method of claim 137, further comprising:

allowing the user to modify parameters used in the automatic selection.

139. The method of claim 136, further comprising:

performing an initial classification of the subset of the corpus of documents into a relevant set of reviewable documents.

140. The method of claim 139, further comprising:

partitioning the corpus of documents in at least two sets.

141. The method of claim 140, further comprising:

one of the partitioned sets is a supra-responsive set designed to contain a majority of documents of interest from the corpus.

142. The method of claim 136, further comprising:

enabling a user to review of a sample of the automatically selected documents to ascertain the validity of the automatic selection.

143. The method of claim 142, wherein a sample is created by the use of a statistical sampling technique applied to a set of documents automatically selected.

144. The method of claim 136, further comprising:

distilling the automatic selection into a basis involving categorization components.

145. The method of claim 144, wherein a categorization component represents a set of documents grouped as a direct result of a categorization technique.

146. The method of claim 136, further comprising:

refining the accuracy by supervised review of the subset of corpus documents as chosen by an automatic selection.

147. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

utilizing a plurality of heterogeneous categorization mechanisms to automatically categorize documents in the corpus; and

arranging the heterogeneous categorization mechanisms to a partially ordered rule set to reduce a search space of possible combinations of the plurality of heterogeneous categorization mechanisms.

148. The method of claim 147, further comprising:

providing a user interface to allow the user to alter an order of the heterogeneous categorization mechanisms in the partially ordered rule set.

149. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

utilizing a plurality of heterogeneous categorization mechanisms to automatically categorize documents in the corpus; and

analyzing and visualizing a relative performance, overlaps, and inconsistencies among the plurality of heterogeneous categorization mechanisms.

150. The method of claim 149, further comprising:

automatically breaking up poorly performing categorization mechanisms.

151. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

utilizing a plurality categorization mechanisms to automatically categorize documents in the corpus;

receiving categorization decisions from human reviewers; and

determining a best fit of the categorization mechanisms to the categorization decisions of the human reviewers.

152. A method to enable improved analysis and use of sociological data, the method comprising:

identifying causal relationships between a plurality of documents;

identifying a plurality of characteristics of a communication, including a modality used, actors involved, and proximate events of relevance;

enabling a user to query based on all of the characteristics available;

utilizing a plurality categorization mechanisms to automatically categorize documents in the corpus; and

utilizing a supervised sampling process, based on receiving categorization decisions from human reviewers, to increase accuracy of automated categorization of the documents.

153. The method of claim 152, wherein non-randomized sets are used to increase human performance.

154. The method of claim 152, wherein the categorization decisions from human reviewers may modify a category with an “

arguable”

modifier for decisions that are not certain.

155. The method of claim 152, further comprising:

projecting a final size of the documents in each of the categories, once categorized across the whole data set.

156. The method of claim 155, further comprising:

assessing a possible overfitting of categorization mechanisms to a particular sample, based on the final size projection.