Multi-Feature and Fuzzy Logic-Based News Text Summarization

PROJECT TITLE :

News Text Summarization Based on Multi-Feature and Fuzzy Logic

ABSTRACT:

Because the amount of data on the Internet is growing so quickly, automatic text summarization work has become increasingly important in the last 70 years. Automatic text summarization work can extract useful information and knowledge that users require, which can be easily handled by humans and used for a variety of purposes. News text is the form of text that most people are exposed to, especially in their daily lives. A new automatic summarzation model for news text is introduced in this work, which is based on fuzzy logic rules, multi-features, and the Genetic algorithm (GA). The most important feature is word features; we scored each word and extracted words that scored higher than the preset score as keywords. Because news text is a unique type of text that contains many unique elements such as time, place, and characters, these unique news elements can sometimes be extracted directly as keywords. The second category is sentence features, which are a linear mixture of features that represent the value of each sentence, with each feature being weighted by a Genetic algorithm. Finally, in order to achieve automatic summarization, we apply a fuzzy logic framework to generate the final score. The results of the suggested technique were compared to those of Msword, System19, System21, System 31, SDS-NNGA, GCD, SOM, and Ranking SVM on the DUC2002 dataset using the ROUGE assessment method, revealing that the proposed method outperforms the aforementioned methods.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here