Development of data-to-text (D2T) on generic data using fuzzy sets

Data-to-Text (D2T) is an option for translating non-linguistic data into textual form. However, along with technological developments, the various fields of data and the variety of users are one of the focuses that must be considered in the development of D2T. This study aims to develop a D2T system with input in the form of general data so that it can receive data from any field or domain, whether the data have header information, data types, rules or not. Then fuzzy rule based systems are used to interpret data in general. The system developed can produce information in the form of data summaries, newest data information, and predictive information. It is carried out in the R programming language by utilizing several available packages. Experiments are carried out by measuring the level of readability of the news generated, computation time, and comparing the results with related research. The experimental results show that the information generated is proven to represent the data provided and can be understood by the level of students even at the elementary school level, and the computation time is quite good.