Abstract: In this project first the data sets are read from the text file, after that file is processed and stored as datasets. First the data cleaning algorithm is executed with the help of stop words, special symbols and then clean data is obtained. After that the clean data into a set of words which will be represented as a wordized matrix. After that the word stream count of each of the words is found out. IDF and TF-IDF of each of the data set rows are obtained. Finally, the classification algorithm is executed and then class label is assigned to the event.
Keywords: IDF, TF-¬IDF, CNN