Page 45 - DLIS002_KNOWLEDGE ORGANIZATION CLASSIFICATION AND CATALOGUING THEORY
P. 45

Knowledge Organization: Classification and Cataloguing Theory




                    Notes
                                     Step 1: Information Retrieval for extraction title article and categories keywords content
                                     from Wikipedia, usingcalculated weight keywords.
                                     Step 2: Using DDC-MR for classification Wikipedia keywords.
                                     Step 3: Calculated percentage DDC-MR classes.
                                     Step 4: Display percentage DDC-MR classes with Radar graph.

                                     Step 5: Calculated X, Y point of Article Wikipedia with sum vector.
                                     Step 6: Display X, Y point of Article Wikipedia with Scatter plot.
                                     Step 7: Calculated angle degree of Article Wikipedia.
                                     Step 8: Display angle degree of Article Wikipedia with Scatter plot.

                                     Last step: Compare Wikipedia DDC-MR Classes with Library Book DDC Classes.
                                     Illustrates the steps of processing classification model of Wikipedia start from reading the
                                     Article title and Category keyword from Article Wikipedia. Then, using the Article Title
                                     and Category Keyword to be classified as the Dewey Decimal Classification Multiple
                                     Relations (DDC-MR) and calculated the percentage of each classes DDC-MR in Eq. (1) to
                                     store in the database.

                                         N  × 100
                                     P  =  n
                                      n    9
                                          ∑ N n                                                          ...(1)
                                          n0
                                           =
                                      P = Classes Percentage
                                       n
                                     N = Keywords Number
                                       n
                                       n = Classes Number




                                     Notes  N is Keywords number of classes form Article Wikipedia.
                                     n is order of classes divide into 10 value as follow:

                                     000 class is order of class equaling 0,
                                     100 class is order of class equaling 1,
                                     200 class is order of class equaling 2,

                                     300 class is order of class equaling 3,
                                     400 class is order of class equaling 4,
                                     500 class is order of class equaling 5,
                                     600 class is order of class equaling 6,
                                     700 class is order of class equaling 7,

                                     800 class is order of class equaling 8,
                                     900 class is order of class equaling 9
                                     P is percentage of class from Keywords number.
                                                                                                         Contd....



          40                                LOVELY PROFESSIONAL UNIVERSITY
   40   41   42   43   44   45   46   47   48   49   50