AUTOMATE SENTIMENTAL ANALYIS OF TEXTUAL COMMENTS AND FEEDBACK
International Research Journal of Modernization in Engineering Technology and Science · 2023
Now a days everything is Automated.We watch movies and most of us give the feedback about the movie and also, many people believe in the reviews given in the review websites like Twitter and so on.The reviews may be going towards good things or bad things, some people say good some say, bad but knowing overall true review is difficult.Some people may use irrelevant words, unwanted data also.This should not happen.Reading all the reviews is difficult, and finding the relevant words about the movie is also difficult.So, if we can make this easy to the audience (People) it would be very nice and it would be great thing.So, we collect the reviews preprocess it so that redundancies are removed and data becomes consistent.Then, vectorizing the content takes place so that model can easily process the data.Now, we start building the model and we split the dataset to train and test the model accuracy.To analyze the model results we will have the accuracy plot, we also try to make a function which takes text as an input and gives the sentiment of the review (positive or negative).At last, we can see the reviews sentiment using Data Visualization by Using Naïve Baye's classifier we have achieved 94% accuracy.