Implementing decision tree algorithm in developing text summarizing tool

Chan, Lek Ho (2016) Implementing decision tree algorithm in developing text summarizing tool. Project Report. Melaka, Malaysia, Universiti Teknikal Malaysia Melaka. (Submitted)

Text (Full Text) Implementing decision tree algorithm in developing text summarizing tool.pdf - Submitted Version Download (1MB)

Abstract

This project proposed a decision tree algorithm to summarize text documents and also to implement that particular algorithm in developing a text summarizing tool. There are a lot of researches out there that has proven decision tree algorithm is effective in generating a summary and among the variations of decision trees, C4.5 also known as J48 in Weka, is proven to be one of the better ones. This projects chooses C4.5 decision tree algorithm to produce a training model using DUC 2002 dataset and the rules are later translated in php, as the tool that is proposed is a web-based application. The features extraction is developed using php and the features scores will be saved into database. The decision rules from the training model are applied to the features score in database and each sentences are classified into summary and not-summary. Later this decision tree model is evaluated using ROUGE. The result is later analyzed and the strengths and weaknesses of the tool and decision tree model are also identified.

Actions (login required)

View Item