Atorn Nuntiyagul. Text categorization & retrieval for thai item bank using patterned keyword in phrase (PKIP) . Doctoral Degree(Science and Technology Education). Mahidol University. : Mahidol University, 2006.
Text categorization & retrieval for thai item bank using patterned keyword in phrase (PKIP)
Abstract:
In this study, a feature selection approach, Patterned Keyword in Phrase
(PKIP), to categorize text for educational item banks is proposed. An item bank is a
collection of textual question items consisting of short sentences. These sentences
rarely contain enough relevant words for direct categorization by the traditional
approaches. Therefore, PKIP was designed to categorize such question items using
only available keywords and their patterns. These keywords are extracted by using the
feature selection technique. The support vector machine approach was adopted as well
to be used in the categorization process.
Moreover, the PKIP system, an adaptable learning assistant tool for managing
question items in item banks, is presented. PKIP is not only able to automatically
assist educational users to categorize the question items into predefined categories by
their content but also to correctly retrieve the items by specifying the category and/or
the difficulty level. PKIP adapts the ‘‘categorization learning model’’ to improve the
system’s categorization performance using the incoming question items.
In the trial procedures, PKIP was designed and implemented to manage Thai
high primary mathematics question items. PKIP was tested and evaluated in terms of
both system accuracy and user satisfaction. The evaluation results showed that the
system accuracy is acceptable and PKIP satisfies the need of users