Open ended question analysis system and method

• US 4,958,284 A
• Filed: 12/06/1988
• Issued: 09/18/1990
• Est. Priority Date: 12/06/1988
• Status: Expired due to Term

• Current Assignee: Ipsos-Insight, Inc. (Ipsos SA)
• Original Assignee: The NPD Group, Inc. (Information Resources Incorporated)
• Inventors: Ziegler, George, Bishop, Lawrence C.
• Primary Examiner(s): Smith, Jerry
• Assistant Examiner(s): Huntley, David
• Application Number:
  US07/280,670
• Time in Patent Office: 651 Days
• Field of Search: 364/401, 364/419, 455/2, 434/322, 434/353
• US Class Current: 434/353
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A method and system for data processing open-ended respondent answers to open-ended questions provides reproducible categorized dynamically variable coding of the open-ended respondent answers to the open-ended questions. The data processor (200) has an updateable retrievable word dictionary fo words stored therein with the open-ended answers comprising words. The open-ended answers are input to the data processor (102,106) and classified (108) into corresponding word types such as keywords, modifiers, skip words, connectors, and negative words, with the combined keywords and associated modifiers forming key phrases. The input words are convered (112) into corresponding binary coded words for providing a binary defined sentence corresponding to the input open-ended respondent answer. The binary defined sentence is scanned and any keywords and associated modifiers are extracted (114) to create a retrievable file comprising key phrases formed from the extracted keywords and associated modifiers, and the keywords per se (116). The key phrases are sorted in the created file (118) and the occurrences of the sorted key phrases are counted and duplicates eliminated in order to provide a net key phrase file (120). The net key phrase file is displayed to the operator (122) who then groups the displayed net key phrases into a coding structure (124) which is stored and can be updated or modified under control of the operator.

Claims

1. A method for processing in a data processor having an associated display means open-ended respondent answers to open-ended questions for providing reproducible categorized dynamically variable coding of said open-ended respondent answers to said open-ended questions, said data processor having a retrievable word dictionary of words stored therein, said open-ended answers comprising words, said method comprising the steps of inputting said words comprising an open-ended respondent answer to said data processor, classifying said words comprising said input open-ended respondent answer into corresponding word types selected from a group of word types comprising keywords, modifier words, skip words, connector words and negative words, said keywords comprising words which are keys to conveying a true meaning of said input open-ended respondent answer, said modifier words comprising words attached to said keywords in said input open-ended respondent answer to form key phrases, said skip words comprising words unimportant to said conveying of said true meaning of said input open-ended respondent answer, said connector words comprising words which are conjunctions which connect said key phrases within said input open-ended respondent answer, said negative words comprising words which turn said key phrases into negative statements in said input open-ended respondent answers;

updating said word dictionary;

converting said words comprising said input open-ended respondent answer into corresponding binary coded words, said word dictionary comprising dictionary words stored as corresponding binary coded words, said converting step comprising the step of converting said input words into said corresponding binary coded words corresponding to said binary coded words stored as said updated dictionary words for providing a binary defined sentence corresponding to said input open-ended respondent answer;

scanning said corresponding binary defined sentence and extracting said keywords and said modifier words associated with said keywords in said corresponding binary defined sentence;

creating a retrievable file comprising key phrases formed from said extracted keywords and said extracted associated modifier words, and said keywords per se;

sorting said key phrases in said created file;

counting occurrences of said sorted key phrases and eliminating duplicates in said sorted key phrases for providing a net key phrase file;

displaying said net key phrase file on said associated display means;

grouping said displayed net key phrases into a coding structure; and

storing said coding structure in said data processor.

2. A method in accordance with claim 1 further comprising the step of updating said stored coding structure in said data processor for providing an accumulative coding structure for said input open-ended respondent answers.

3. A method in accordance with claim 2 further comprising the step of varying the coding structure of at least one of said net key phrases.

4. A method in accordance with claim 1 comprising performing said classifying step, dictionary updating step converting step, scanning step, file creating step, sorting step, counting step, displaying step, grouping step, and coding structure storing step, for each of a plurality of said open-ended respondent answers input to said data processor for providing an accumulative coding structure for said plurality of input open-ended respondent answers.

5. A method in accordance with claim 4 further comprising the step of updating said stored coding structure in said data processor for each input open-ended respondent answer for providing said accumulative coding structure.

6. A method in accordance with claim 5 further comprising the step of varying the coding structure of at least one of said net key phrases.

7. A method in accordance with claim 4 further comprising the step of varying the coding structure of at least one of said net key phrases.

8. A method in accordance with claim 4 wherein each input open-ended respondent answer is associated with a respondent identification code.

9. A method in accordance with claim 8 further comprising the step of inputting respondent closed-end respondent answers to said data processor, each of said closed-end respondent answers being associated with a respondent identification code.

10. A method in accordance with claim 9 further comprising the step of merging said input closed-end answer with said coded input respondent open-ended answers in accordance with said associated respondent identification codes for accumulatively processing both said open-ended and closed-ended respondent answers.

11. A method in accordance with claim 10 wherein said input closed-end respondent answers comprise pre-coded responses.

12. A method in accordance with claim 1 further comprising the step of varying the coding structure of at least one of said net key phrases.

13. A method in accordance with claim 1 wherein said extracting step comprises the step of extracting said keywords and said associated modifier words in said corresponding binary defined sentence in accordance with a pre-defined rule structure for interpreting said sentence.

14. A method in accordance with claim 13 wherein said extracting step further comprises the step of dynamically modifying said pre-defined rule structure for overriding said pre-defined rule structure for extracting said keywords and said associated modifier words in accordance with said dynamically modified rule structure.

15. A method in accordance with claim 13 wherein said pre-defined rule structure comprises a rule that every sentence must have at least one of said keywords.

16. A method in accordance with claim 15 wherein said pre-defined rule structure further comprises a rule that skip words and words which are unknown from said dictionary are ignored.

17. A method in accordance with claim 16 wherein said pre-defined rule structure further comprises a rule that two of said keywords may not exist next to each other and must be separated by at least one modifier word or connector word.

18. A method in accordance with claim 17 wherein said pre-defined rule structure further comprises a rule that a key phrase may comprise one keyword, O-n preceding modifier words and a preceding negative word.

19. A method in accordance with claim 18 wherein said pre-defined rule structure further comprises a rule that a connector word must have a key phrase on the left and right of said connector word.

20. A method in accordance with claim 19 wherein said pre-defined rule structure further comprises a rule that any trailing modifier words are attached to the preceding keyword.

21. A method in accordance with claim 20 wherein said extracting step further comprises the step of dynamically modifying said pre-defined rule structure for overriding said pre-defined rule structure for extracting said keywords and said associated modifier words in accordance with said dynamically modified rule structure.

22. A method in accordance with claim 20 comprising performing said classifying step, dictionary updating step converting step, scanning step, file creating step, sorting step, counting step, displaying step, grouping step, and coding structure storing step, for each of a plurality of said open-ended respondent answers input to said data processor for providing an accumulative coding structure for said plurality of input open-ended respondent answers.

23. A method in accordance with claim 22 further comprising the step of updating said stored coding structure in said data processor for each input open-ended respondent answer for providing said accumulative coding structure.

24. A method in accordance with claim 20 wherein each input open-ended respondent answer is associated with a respondent identification code.

25. A method in accordance with claim 24 further comprising the step of inputting respondent closed-end respondent answers to said data processor, each of said closed-end respondent answers being associated with a respondent identification code.

26. A method in accordance with claim 25 further comprising the step of merging said input closed-end answer with said coded input respondent open-ended answers in accordance with said associated respondent identification codes for accumulatively processing both said open-ended and closed-ended respondent answers.

27. A method in accordance with claim 36 wherein said input closed-end respondent answers comprise pre-coded responses.

28. A method in accordance with claim 24 all commas are replaced by the AND connector word.

29. A method in accordance with claim 28 further comprising the step of inputting respondent closed-end respondent answers to said data processor, each of said closed-end respondent answers being associated with a respondent identification code.

30. A method in accordance with claim 29 further comprising the step of merging said input closed-end answer with said coded input respondent open-ended answers in accordance with said associated respondent identification codes for accumulatively processing both said open-ended and closed-ended respondent answers.

31. A method in accordance with claim 30 wherein said put closed-end respondent answers comprise pre-coded responses.

32. A method in accordance with claim 19 wherein said pre-defined rule structure comprising a rule that all commas are replaced by the AND connector word.

33. A method in accordance with claim 32 wherein said extracting step further comprises the step of dynamically modifying said pre defined rule structure for overriding said pre-defined rule structure for extracting said keywords and said associated modifier words in accordance with said dynamically modified rule structure.

34. A method in accordance with claim 32 comprising performing said classifying step, dictionary updating step converting step, scanning step, file creating step, sorting step, counting step, displaying step, grouping step, and coding structure storing step, for each of a plurality of said open-ended respondent answers input to said data processor for providing an accumulative coding structure for said plurality of input open-ended respondent answers.

35. A method in accordance with claim 34 further comprising the step of updating said stored coding structure in said data processor for each input open-ended respondent answer for providing said accumulative coding structure.

36. A method in accordance with claim 1 wherein each input open-ended respondent answer is associated with a respondent identification code.

37. A method in accordance with claim 36 further comprising the step of inputting respondent closed-end respondent answers to said data processor, each of said closed-end respondent answers being associated with a respondent identification code.

38. A method in accordance with claim 37 further comprising the step of merging said input closed-end answer with said coded input respondent open-ended answers in accordance with said associated respondent identification codes for accumulatively processing both said open-ended and closed-ended respondent answers.

39. A method in accordance with claim 38 wherein said input closed-end respondent answers comprise pre-coded responses.

40. A method in accordance with claim 37 wherein said put closed-end respondent answers comprise pre-coded responses.

41. A data processor system for processing open-ended respondent answers to open-ended questions for providing reproducible categorized dynamically variable coding of said open-ended respondent answers to said open-end questions, said data processor system comprising display means for providing a display, means for retrievably storing a dictionary of words, said open-ended answers comprising words;

means for inputting said words comprising an open-ended respondent answer to said data processor;

means for classifying said words comprising said input open-ended respondent answer into corresponding word types selected from a group of word types comprising keywords, modifier words, skip words, connector words and negative words, said keywords comprising words which are keys to conveying a true meaning of said input open-ended respondent answer, said modifier words comprising words attached to said keywords in said input open-ended respondent answer to form key phrases, said skip words comprising words unimportant to said conveying of said true meaning of said input open-ended respondent answer, said connector words comprising words which are conjunctions which connect said key phrases within said input open-ended respondent answer, said negative words comprising words which turn said key phrases into negative statements in said input open-ended respondent answers;

means for updating said word dictionary means for converting said words comprising said input open-ended respondent answer into corresponding binary coded words, said word dictionary comprising dictionary words stored as corresponding binary coded words, said converting means comprising means for converting said input words into said corresponding binary coded words corresponding to said binary coded words stored as said updated dictionary words for providing a binary defined sentence corresponding to said input open-ended respondent answer;

means for scanning said corresponding binary defined sentence and extracting said keywords and said modifier words associated with said keywords in said corresponding binary defined sentence;

means for creating a retrievable file comprising key phrases formed from said extracted keywords and said extracted associated modifier words, and said keywords per se;

means for sorting said key phrases in said created file;

means for counting occurrences of said sorted key phrases and eliminating duplicates in said sorted key phrases for providing a net key phrase file, said net key phrase file being displayable on said associated display means;

means for grouping said displayed net key phrases into a coding structure; and

means for storing said coding structure in said data processor system.

42. A system in accordance with claim 41 further comprising means for varying the coding structure of at least one of said net key phrases.

43. A system in accordance with claim 41 wherein said means for extracting said keywords and said associated modifier words in said corresponding binary defined sentence comprises means for extracting said keywords and said associated modifier words in accordance with a pre-defined rule structure for interpreting said sentence.

44. A system in accordance with claim 43 wherein said pre-defined rule structure comprises a rule that every sentence must have at least one of said keywords.

45. A system in accordance with claim 44 wherein said pre-defined rule structure further comprises a rule that skip words and words which are unknown from said dictionary are ignored.

46. A system in accordance with claim 45 wherein said pre-defined rule structure comprises a rule that two of said keywords may not exist next to each other and must be separated by at least one modifier word or connector word.

47. A system in accordance with claim 46 wherein said pre-defined rule structure comprises a rule that a key phrase may comprise one keyword, O-n preceding modifier words and a preceding negative word.

48. A system in accordance with claim 47 wherein said pre-defined rule structure comprises a rule that a connector word must have a key phrase on the left and right of said connector word.

49. A system in accordance with claim 48 wherein said pre-defined rule structure comprises a rule that any trailing modifier words are attached to the preceding keyword.

50. A system in accordance with claim 49 wherein said pre-defined rule structure comprises a rule that all commas are replaced by the AND connector word.

51. A system in accordance with claim 43 wherein said pre-defined rule structure comprises a rule that further comprises means for inputting respondent closed-end answers to said data processor system, and means for merging said input respondent closed-end answers with said coded input respondent open-ended answers for accumulatively processing both said open-ended and closed-ended respondent answers.