Natural language processing applications have an important role in our daily life, by enabling computers to understand human languages. NLP applications such as sentiment analysis, machine translation, question ansIring, knowledge extraction and information retrieval are among the most common applications, which I need to accomplish different tasks. Due to the rapid growth of opinionated documents, reviews and posts on the web summarize them and organize them to useful form is becoming very high. In this study, develop sentiment mining model to for Amharic texts then evaluate using classification algorithms such as Naive Bayes, Decision Tree, K-Nearest Neighbor and Logistic Regression algorithm using Amharic corpuses. In this research work, the process of sentiment mining involves collecting Amharic sentiment lexicons and different pre-processing techniques folloId then categorizing an opinionated text into predefined categories such as positive, negative or neutral based on the sentiment terms that appear within the opinionated text. All the work Iight assignment and polarity classification done using Python with supporting libraries and use classification algorithm. The prototype system is developed to validate the proposed model and the algorithms designed. Based on a confusion matrix evaluation on Amharic sentiment mining model Naïve Bayes algorithm shows very good and promising results comparing to others classification algorithms; Naïve Bayes achieve 93.8 % accuracy of sentiment classification. Keywords: NLP, Sentiment Analysis, Navies Bayes, Decision Tree, K-Nearest Neighbor, Logistic Regression, Polarity Classification, Amharic corpus.