Deteksi dan Koreksi Kesalahan Pengetikan Berbasis KBBI Menggunakan Algoritma Peter Norvig

With the advent of the digital age, there has been an explosion in the volume of written material; however, this increase has also been accompanied by an alarmingly high error rate. These typos are serious because they alter the intended meaning of the message and make it appear less credible than it actually is. Therefore, this study aims to design and develop a spelling detection and correction system (spelling checker) for Indonesian text that strictly adheres to the Kamus Besar Bahasa Indonesia (KBBI). The system is built using an architecture that integrates KBBI lexicon matching with probabilistic calculations via Peter Norvig’s algorithm. This integration forms the foundation of the system’s design. Methodologically, the system checks text against the KBBI database and also breaks down irrelevant terms into tokens (tokenizing). To ensure the most accurate correction suggestions are provided when detecting non-standard or misspelled words, Peter Norvig’s method determines the edit distance and the maximum likelihood value. The research results show that this system is capable of detecting spelling errors and providing efficient correction recommendations in real time, as demonstrated through testing on a web interface built using the Laravel framework. Finally, an effective method for preparing Indonesian-language texts while maintaining their scientific quality is provided through the integration of the KBBI database with the flexibility of Peter Norvig’s algorithm.