Golam Rabbani

Abstract— The reading newspaper is a common habit in today’s life. Before reading news article all are focused on the news headline. Understanding the meaning of news headline everybody can easily identify the news types. That means the containing news article provides positive or negative news. Analysis of the sentiment of the news headline is a good solution for this kind of problem. Sentiment Analysis is a chief part of Natural Language Processing. It mines any kinds of opinion and set the sentiment of any text. We proposed a method for Bengali news headline sentiment measurement with different kinds of the supervised learning algorithm and their performance. Firstly, we set sentiment of each news headline then used the classification method to predicting the news headline which was containing a positive or negative headline. After all, Bengali is one of the most used languages in this world. A lot of research work done previously in a different language but very few in the Bengali language. So, increasing the Bengali language research resource need to develop different kinds of tools and technology. Keywords: Sentiment Analysis, Natural Language Processing, Opinion Mining, Bengali News Headline Sentiment

Abstract—In today’s world business are becoming online based. Companies sell their products and seek for consumer’s feedback. When all the consumer writes their review about that’s a product, It’s becomes difficult to say that product is good or not based on their review. That’s where Deep learning come. By using this, we can extract opinion or sentiment from the text which is written by the consumer. This is sentiment analysis. It can classify the emotional status of that review. Our project detects opinion from consumer’s review whether it is good or bad. We use SVM, Naive Bayes algorithm and some methods. We use the Naive Bayes algorithm because we want to know how often words occur in the document. And then we use SVM for classifying whether words are positive or negative. For our researching purpose, we use the Amazon consumer review data set, which was available online. Some methods that we are using for preprocessing and cleaned the document where just words are left. We trained our model so well with twenty-four thousand data. So, it will give us the best accuracy and we make this model with the best algorithm and after that, it gives the accuracy of 98.39%. This project will help us in real life when we are having trouble with product reviews. Our machine will help us to determine which review is good and which review is bad and make a category of a positive and negative review and saves our time. Keywords: NaïveBayes, SVM, KNN, Polarity, Sentiment, Positive, Negative, Word, Paragraph, Accuracy

Computer Science And Engineering