| dc.description.abstract | Communicating in English is a common thing in day-to-day life since it is influential to understand the tone or the idea of English sentences. There will be misunderstandings regarding the attitude, sentiments, and point of view of the speaker or writer if we are unable to identify the appropriate sentence tone. Therefore, the objective of this study is to propose a machine learning (ML) based ensemble approach for identifying the tone of the English sentences automatically. Here we collected around 1000 English sentences as the input data. This approach uses lowercasing, stop word removal, lemmatization, and tokenization as preprocessing techniques. Then Term Frequency-Inverse Document Frequency (TF-IDF) feature vector extraction method was used to extract features from the sentences. For classification first applied five different individual ML algorithms namely Nave Bayes, Support Vector Machine (SVM), Logistic Regression, Random Forest, and Decision tree. Then, a n ensemble learning algorithm was applied by combining those five algorithms through average probability method. The experimental results show that the ensemble learning algorithm outperforms the individual algorithms in terms of accuracy (96.9%), precision (97.2%), f-measure (96.9%), recall (96.9%) as well as Mean Absolute Error (MAE)(0.0113) and Root Mean Square Error (RMSE) (0.0163) for measuring error. The study introduces a ML based ensemble method, incorporating preprocessing techniques and TF-IDF feature extraction, which outperforms individual algorithms in classifying English sentences based on their tone. | en_US |
