Product reviews can provide great benefits for consumers and producers. Number of reviews could be ranging from hundreds to thousands and containing various opinions. These make the process of analyzing and extracting information on existing reviews become increasingly difficult. In this research, sentiment analysis was used to analyze and extract sentiment polarity on product reviews based on a specific aspect of the product. This research was conducted in three phases, such as data preprocessing which involves part-of-speech (POS) tagging, feature selection using Chi Square, and classification of sentiment polarity of aspects using Naïve Bayes. Based on evaluation results, it is known that the system is able to perform aspect-based sentiment analysis with its highest F1-Measure of 78.12%.

Cancer is one of the most deadly diseases in the world. The International Agency for Research on Cancer (IARC) noted 14.1 million new cancer cases and 8.2 million deaths from cancer in 2012. In the last few years, DNA microarray technology has increasingly been used to analyze and diagnose cancer. Analysis of gene expression data in the form of microarray allows medical experts to ascertain whether or not a person suffers from cancer. DNA microarray data has a large dimension that can affect the process and accuracy of cancer classification. Therefore, a classification scheme that includes dimension reduction is needed. In this research, a Principal Component Analysis (PCA) dimension reduction method that includes the calculation of variance proportion for eigenvector selection was used. For the classification method, a Support Vector Machine (SVM) and Levenberg-Marquardt Backpropagation (LMBP) algorithm were selected. Based on the tests performed, the classification method using LMBP was more stable than SVM. The LMBP method achieved an average 96.07% accuracy, while the SVM achieved 94.98% accuracy.

Network formed between users in a social media can be used to encourage information spreading among them. This research applied Social Network Analysis which further can be used to social media marketing to improve the marketing process effectively. Based on previous research, information spreading speed among the social media is affected by the users' activity connection which can be represented in centrality value. The centrality value itself is very affected by the graph structure and weights. This research applied degree and eigenvector centrality to observe the effect of centrality value for twitter data. The result shows that there is significant difference among 10 most influential users. This result will be used for the future research that will be focused in small and medium enterprise (SME) twitter data.

Polycystic Ovary Syndrome (PCOS) is an endocrine abnormality that occurred in female reproductive cycle. This paper designed an application to classify Polycystic Ovary Syndrome based on follicle detection using USG images. The first stage of this classification is preprocessing, which employs low pass filter, equalization histogram, binarization, and morphological processes to obtain binary follicle images. The next stage is segmentation with edge detection, labeling, and cropping the follicle images. The following stage is feature extraction using Gabor wavelet. The cropped follicle images are categorized into two groups of texture features: (1) Mean, (2) Mean, Entropy, Kurtosis, Skewness, and Variance. This result in 2 datasets prepared for classification process, i.e. (1) data set A has 40 images that consist of 26 normal images and 14 PCOS-indicated images. It counted by Mean texture feature and obtained 275 follicle images. (2) Dataset B has 40 images consist of 34 normal images and 6 PCOS-indicated images. It counted by Mean, Entropy, Kurtosis, Skewness, and Variance texture features then obtained 339 follicle images. The last stage is classification. It identifies the features of PCO and non-PCO follicles based on the feature vectors resulted from feature extraction. Here, three classification scenarios are designed: (1) Neural Network-Learning Vector Quantization (LVQ) method, (2) KNN - euclidean distance, and (3) Support Vector Machine (SVM) - RBF Kernel. The best accuracy gained from SVM-RBF Kernel on C=40. It shows that dataset A reach 82.55% while dataset B that obtained from KNN-euclidean distance classification on K=5 reach 78.81%.