<![CDATA[This research aims to develop a Data-to-Text system with input in the form of streaming data in batch form, to generate news in general. The development of a Data-to-Text system model is carried out by applying Machine Learning to overcome Streaming data, with the Piecewise Linear Approximation technique using the Least Square method. The developed system produces data summary information, current data information, and prediction information. System development is carried out in the R programming language by utilizing several available packages. The experiment was conducted by measuring the Readability level of the news raised, Computation Time, and comparing the results withrelated research. The experimental results show that the information produced is proven to represent the data provided and can be understood by the student level or above, and the computational time is quite good. The system can generate information based on meteorological data, climatological data, and financial data.]]>
Copyrights © 2024
