Sentiment Performance Analysis of Supervised Machine Learning Techniques

Sentiment Performance Analysis of Supervised Machine Learning Techniques

Introduction:

The widespread use of the Internet and web applications, such as feedback systems, make people smarter. In these applications, the towns used to give their comments about movies, products, services, etc. through which they have gone, and this feedback is publicly available for future reference. It is a tedious task for the machines to identify the types of comments, and: and positive or negative. And here the techniques of machine learning have a fundamental role to train the machine and make it intelligent so that the machine can identify the type of feedback that can give more advantages and features for those web applications and users. There are many supervised machine learning techniques available, so it is a difficult task to choose the best.

In this project, we have compiled film review data sets of different sizes and selected some of the machine learning algorithms supervised and popularly used for model formation. So that the model can classify the revision. The Python NLTK package, along with Win Python and Spyder, is used to process movie reviews. Next, the Python sklearn package is used to train the model and find the model's accuracy.

Conclusion:

In this article, a simple but innovative approach is carried out on the analysis of the feelings of movie reviews using promising 07:00 supervised algorithms of automatic learning. The results obtained conclude SVC / SVM linear as the best classifier among others to achieve 100% accuracy for a large number of movie reviews. In the future, we will try to investigate their effectiveness by considering large datasets using unsupervised and semi-supervised auto-learning techniques.

Login here to download Sentiment Performance Analysis of Supervised Machine Learning Techniques


Account Login


New users must register now. For Forgot password click here.