Text Classification on Twitter Data Using Machine Learning Algorithm

Classification of text is the major challenge faced by the industries so that they can extract the required information from that data. With the advent of machine learning, it becomes a lot easier for the engineers to classify the data as per requirement. Writing an effective code and algorithm is required to classify the data accurately. In this paper, we have tried to solve a problem where we have taken a raw dataset which contains tweets by users where the name of the disease in every tweet begins with a hashtag (‘#’) symbol. These disease names are extracted and stored it in a new column preceding to every tweet with the help of python.