With the explosive growth of internet, there are a big amount of data being collected in terms of text document, that attracts many researchers in text mining. Traditional data mining methods are found to be trapped while dealing with the scale of text data. Such large scale data can be handled by using parallel computing frameworks such as: Hadoop and MapRedue etc. However, they are also not away from challenges.On the other hand, Naive Bayes (NB) and its variant Multinomial Naive Bayes (MNB) plays an important role in text mining for their simplicity and robustness but if anything or everything from number of words, documents and labels go beyond the linear scaling, then MNB is intractable and will soon be out of memory while dealing in a single computer. Looking into the high dimensional sparse nature of the documents in text datasets, a scalable sparse generative Naive Bayes (SGNB) classifier is also proposed to develop a good text classification model. Unlike parallelization, SGNB reduces the time complexity non-linearly and hence expected to provide best results. In this paper, an efficient Lovins stemmer in combination with snowball based stopword calculation and word tokenizer is proposed for text pre-processing. The extensive experiments conducted on publicly available very well known text datasets opines the effectiveness of the proposed approach in terms of accuracy, F-score and time in comparison to many baseline methods available in the recent literature.

Development of advanced technology has increased the size of data and has also created different categories of data. Classifying these different categories of data is the need of the era. We have proposed a method of classifying the image database containing four categories of images like human face, airplane, cup and butterfly. Our approach involves steps like feature extraction, bag of feature creation, histogram representation and classification using decision tree. For feature extraction SIFT (Scale Invariant Feature Transform) algorithm is used since it is invariant to rotation, change of scale, illumination etc. After extracting the features the bag of features concept is used to group the features using k-means clustering algorithm. Then a histogram is plotted for each image in the image database which represents the distributions of data in different clusters. In the final step the most robust, simple and flexible decision tree algorithm is applied on the table created from the histogram plots to obtain the classification result. The experimental observations and the calculated accuracy proves that this method of classification works well for classifying an image dataset having different categories of images.