Search

One of the attempts to understand the meaning and content of the Quran, the central religious text of Islam, is the topic classification of Quranic verses. Verse topic classification aims to help the reader, so he can easily and quickly find information or knowledge contained in the Quran. In this paper, we build a classification model for the topics of English- translated Quranic verses using Support Vector Machine (SVM). The problem of classification of topics of Quranic verses is categorized as a multi-label classification problem. Hence, we design an SVM-based classifier to solve the multi-label classification of topics of Quranic verses. We also implement several techniques such as preprocessing, feature extraction, and dimensionality reduction to solve this problem. Then, we use Hamming Loss as a performance measure to evaluate our proposed classifier model. We find that our proposed model yields outstanding results.

We conducted a semantic similarity study of semantic concepts in the context of the Holy Book Quran. Semantic similarity examines the degree of likeness and shared common properties of two concepts. For example, the Quranic concept of Allah and God will result in a high score of semantic similarity, whereas hell and paradise will yield in a low score because of its extremely different attributes and semantic features. Apart from that, we also delivered the Quranic concept semantic similarity standard dataset which consists of some pairs of Quranic concept along with its similarity score, which was manually annotated by human raters. This dataset resulted in the score of inter-annotator agreement 0.63, not far from the the ones yielded by some well-known datasets such as WordSim and Simlex. Furthermore, to measure the semantic similarity score, we chose the knowledge-based approach by utilizing lexical database properties such as the length and depth of a synonym set (synset). We then applied it to Yuhua Li equation, which has been considered to be the baseline among researchers within the problem of semantic similarity. In terms of the result, our system gained Pearson's correlation 0.33 and Spearman's 0.19. By considering inter-annotator agreement 0.63 that our Quranic standard dataset has as the upper bound score, there are still quite large room for improvement to better mimicking Muslim's intuition to measure the degree of similarity of concepts within the domain of Quran.

Quran is an eternal miracle for depicting its linguistic perfection, truth, and validating of the latest scientific research. Every Muslims must conceive and implement the commandments, also avoid the prohibitions mentioned in the Quran. Each verse of the Quran has a different meaning, and one verse in the Quran can depict one or more topics of class that can be studied. To ease learning and to understand the verses of Quran, each of them needs to be classified appropriately on its different topics. In this research, the model of classification was built that is able to identify the topics classes of each verse of Quran by multi-label classification approach. The model was built using Tree Augmented Naive Bayes (TAN). In order to improve performance, Mutual Information (MI) is employed to select dependent variables. The results show that the classification model built using TAN with MI obtained best performance with average Hamming Loss of 0.1121, while the model built using TAN without MI obtained average Hamming Loss of 0.1208.

News topic classification in this research is categorizing or distinguishing news, in textual data format, into a particular category based on information contained in the news. One of methods that can be used for this task is Bayesian Network that is one of uncertainty reasoning methods that uses probabilistic and directed acyclic graph to model conditional dependencies among variables. However, a textual data normally contains a considerable amount of variables and it could be problem for Bayesian Network since a large number of variables results high complexity, especially time complexity, in learning of Bayesian Network both structure and parameters. In addition, a considerable amount of variables could degrade accuracy since some variables might be irrelevant. In this research, we used Mutual Information as text feature selection method to provide relevant features for Bayesian Network classifier. Based on the conducted research, Mutual information as feature selector is able to improve classification performance of Bayesian Network. The highest classification rate obtained by employing Mutual Information is 75.34%, meanwhile the classification rate without Mutual Information is 45.95%, both in micro-average F1-score.

Al-Quran is the holy book as well as guidance for Muslims around the world. Each verse of Quran contains meaning and wisdom that can usually be classified into more than one topic of discussion. This research was conducted on the issue of classification of Quranic verses that can be classified into more than one topic as a multi-label classification problem. Multi-label classification is different from single-label classification, therefore this research provided a new model of classifier to handle multi-label classification. The system was developed using Multinomial Naive Bayes with several stages of preprocessing data such as case folding, tokenization, and stemming. The system also used bag of words as feature extraction method. The best Hamming loss obtained from this research is 0.1247.

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 Naive 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%.

Microarray Technology is one of technology which able to read the structure of gen. The analysis is important for this technology. It is for deciding which attribute is more important than the others. Microarray technology is able to get cancer information to diagnose a person's gen. Preparation of microarray data is a huge problem and takes a long time. That is because microarray data contains high number of insignificant and irrelevant attributes. So, it needs a method to reduce the dimension of microarray data without eliminating important information in every attribute. This research uses Mutual Information to reduce dimension. System is built with Machine Learning approach specifically Bayes Theorem. This theorem uses a statistical and probability approach. By combining both methods, it will be powerful for Microarray Data Classification. The experiment results show that system is good to classify Microarray data with highest F1-score using Bayesian Network by 91.06%, and Naive Bayes by 88.85%.