Rasel, Annajiat AlimKarim, Dewan ZiaulAhmed, FoysalKhan, Md ShahriarArafin, MD EmonAl Abir, AbdullahBegum, Mumtahina2023-08-012023-08-0120232023-01ID: 19101535ID: 22241119ID: 22241120ID: 22241118ID: 19101306http://hdl.handle.net/10361/19234Cataloged from PDF version of thesis.Includes bibliographical references (pages 17-18).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.Bangla, or Bengali, is one of the world’s most spoken languages, with hundreds of millions of native speakers worldwide. Thousands of books are written in the Bangla language every year, and millions of people register in Bangla daily. But there are only a few researches conducted on Bangla Grammar and Spelling correction because of the lack of Bangla resources and the complexity of the Bangla language. This paper is concerned with implementing a Machine Learning based model to detect grammar and spelling errors in Bangla writing. There are many machine learning algorithms to see mistakes in writing. This research uses Levenshtein distance and Double Metaphone algorithms to detect spelling errors. For grammar, Recurrent Neural Network based sequential model is used with an accuracy of 89%. We have created a Bangla monolingual corpus containing three hundred thousand sentences for this paper. Therefore, we expect this research to make Bangla writing easier and more fascinating for everyone.18 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Bangla languageMachine learningBangla grammar and spellingCheckerDouble metaphoneBangla corpusNeural networkMachine LearningThesis