Naive Bayes Algorithm for Large Scale Text Classfication

Abstract

This paper proposed an improved Naïve Bayes Classifier for sentimental analysis from a large-scale dataset such as in YouTube. YouTube contains large unstructured and unorganized comments and reactions, which carry important information. Organizing large amounts of data and extracting useful information is a challenging task. The extracted information can be considered as new knowledge and can be used for decision-making. We extract comments from YouTube on videos and categorized them in domain-specific, and then apply the Naïve Bayes classifier with improved techniques. Our method provided a decent 80% accuracy in classifying those comments. This experiment shows that the proposed method provides excellent adaptability for large-scale text classification.