Development of a content summary model for an effective synoptic generation system

The exponential growth of digital content on the internet and organizational repositories has significantly increased the demand for systems that can efficiently summarize large text documents. In academia, governance, business, and journalism, decision-makers are often overwhelmed with extensive textual data, making it essential to extract relevant summaries automatically. This study aims to develop a content summary for an effective synoptic generation system. In the modeling process, the formulation of a CSM is undertaken using an extractive summary technique. The CSM is designed and implemented using the Python programming language as the front-end engine and MySQL server as the back-end engine. The study reviews theories and related literature and formulates a CSM for an effective content summary generation using the following features: word frequency, maximum word frequency, sentence weight, normalized word frequency, maximum sentence weight, and compression rate. The CSM is tested using a dataset provided by Document Understanding Conferences. The CSM is evaluated for robustness and reliability using precision, recall and F-measure. The study achieved significant outcomes with 87% precision, 90% Recall and 86% F1-score in values demonstrating the model's effectiveness and reliability in content summary generation.