SVM-Based Supervised Classification

The second method that you can use for training purposes is Support Vector Machine (SVM) classification. SVM is a type of machine learning algorithm derived from statistical learning theory. A property of SVM classification is the ability to learn from a very small sample set.

Using the SVM classifier is much the same as using the Decision Tree classifier, except for the following differences:

• In the call to CTX_CLS.TRAIN, use the SVM_CLASSIFIER preference instead of the RULE_CLASSIFIER preference. (If you do not want to modify any attributes, use the predefined CTXSYS.SVM_CLASSIFIER preference.)

• Use the NOPOPULATE keyword if you do not want to populate the CONTEXT index on the table. The classifier uses it only to find the source of the text, by means of datastore and filter preferences, and to determine how to process the text through lexer and sectioner preferences.

• In the generated rules table, use at least the following columns:

  cat_id number, type number, rule blob;

As you can see, the generated rule is written into a BLOB column. It is therefore opaque to the user, and unlike Decision Tree classification rules, it cannot be edited or modified. The trade-off here is that you often get considerably better accuracy with SVM than with Decision Tree classification.

With SVM classification, allocated memory has to be large enough to load the SVM model; otherwise, the application built on SVM incurs an out-of-memory error. Here is how to calculate the memory allocation:

Minimum memory request (in bytes) = number of unique categories x number of features
                                    example: (value of MAX_FEATURES attributes) x 8

If necessary to meet the minimum memory requirements, increase one of the following memories:

• SGA (if in shared server mode)

• PGA (if in dedicated server mode)