Azreen Azman

Detecting deceptive reviews using lexical and syntactic features

Deceptive opinion classification has attracted a lot of research interest due to the rapid growth of social media users. Despite the availability of a vast number of opinion features and classification techniques, review classification still remains a challenging task. In this work we applied stylometric features, i.e. lexical and syntactic, using supervised machine learning classifiers, i.e. Support Vector Machine (SVM) with Sequential Minimal Optimization (SMO) and Naive Bayes, to detect deceptive opinion. Detecting deceptive opinion by a human reader is a difficult task because spammers try to write wise reviews, therefore it causes changes in writing style and verbal usage. Hence, considering the stylometric features help to distinguish the spammer writing style to find deceptive reviews. Experiments on an existing hotel review corpus suggest that using stylometric features is a promising approach for detecting deceptive opinions.

Quranic-based concepts: Verse relations extraction using Manchester OWL syntax

In recent years, there is global demand for Islamic knowledge by both Muslims and non-Muslims. This has brought about number of automated applications that ease the retrieval of knowledge from the holy books. However current retrieval methods lack semantic information they are mostly base on keywords matching approach. In this paper we have proposed a Model that will make use of semantic Web technologies (ontology) to model Quran domain knowledge. The system will enhance Quran knowledge by enabling queries in natural language.

Query translation using concepts similarity based on Quran ontology for cross-language information retrieval.

In Cross-Language Information Retrieval (CLIR) process, the translation effects have a direct impact o n the accuracy of follow-up retrieval results. In diction ary-based approach, we are dealing with the words t hat have more than one meaning which can decrease the retrieval performance if the query translation retur n an incorrect translations. These issues need to be ove rcome using efficient technique. In this study we p roposed a Cross-Language Information Retrieval (CLIR) method based on domain ontology using Quran concepts for disambiguating translation of the query and to improve the dictionary-based query translation. For experimentation, we use Quran ontology written in E nglish and Malay languages as a bilingual parallelcorpora and Quran concepts as a resource for cross- language query translation along with dictionary-ba sed translation. For evaluation, we measure the perform ance of three IR systems. IR 1 is natural language query IR, IR 2 is natural language query CLIR based on dictionary (as a Baseline) and IR 3 is the retrieval of this research proposed method using Mean Average Precision (MAP) and average precision at 11 points of recall. The experimental result shows that our prop osed method brings significant improvement in retri eval accuracy for English document collections, but defi cient for Malay document collections. The proposed CLIR method can obtain query expansion effect and improve retrieval performance in certain language.

Wavelet packet entropy for heart murmurs classification.

Heart murmurs are the first signs of cardiac valve disorders. Several studies have been conducted in recent years to automatically differentiate normal heart sounds, from heart sounds with murmurs using various types of audio features. Entropy was successfully used as a feature to distinguish different heart sounds. In this paper, new entropy was introduced to analyze heart sounds and the feasibility of using this entropy in classification of five types of heart sounds and murmurs was shown. The entropy was previously introduced to analyze mammograms. Four common murmurs were considered including aortic regurgitation, mitral regurgitation, aortic stenosis, and mitral stenosis. Wavelet packet transform was employed for heart sound analysis, and the entropy was calculated for deriving feature vectors. Five types of classification were performed to evaluate the discriminatory power of the generated features. The best results were achieved by BayesNet with 96.94% accuracy. The promising results substantiate the effectiveness of the proposed wavelet packet entropy for heart sounds classification.

Ontology semantic approach to extraction of knowledge from Holy Quran

With the continued demand for Islamic knowledge, which is mainly based on the Quran as a source of knowledge and wisdom, systems that facilitate an easy search of the content of the Quran remain a considerable challenge. Although in recent years there have been tools for Quran search, most of these tools are based on keyword search, meaning that the user needs to know the correct keywords before being able to retrieve the content of Quran. In this paper, we propose a system that supports the end user in querying and exploring the Quran ontology. The system comprises user query reformulation against the Quran ontology stored and annotated in the knowledge base. The Quran ontology c ons i s t s of n oun concepts ident i f i ed in a l - Quran, and the relationship that exists between these concepts. The user writes a query in the natural language and the proposed system reformulates the query to match the content found in the knowledge base in order to retrieve the relevant answer. The answer is represented by the Quranic verse related to the user query.

Diagnosis of heart valve disorders through trapezoidal features and hybrid classifier.

Numerous studies are being conducted in recent years focusing on phonocardiographic (PCG) signals due to their capability to characterize heart sounds. These characteristics can be exploited in developing computer-aided auscultation system as a complementary tool for clinicians in diagnosis of cardiovascular disorders. This study proposes a new type of features to distinguish five categories of heart sounds, including normal, mitral stenosis, mitral regurgitation,aortic stenosis, and aortic regurgitation. PCG signals were collected from online resources and training CDs. Wavelet packet transform was utilized for heart sound analysis as opposed to discrete wavelet transform that has been extensively used in the previous studies. Then, trapezoidal function was calculated for deriving feature vectors. A hybrid classifier was designed composing of three types of classifiers, multilayer perceptron (MLP) artificial neural network, k-nearest neighbor (KNN), and support vector machine (SVM), to classify feature vectors.The promising results demonstrate the effectiveness of the proposed trapezoidal features and hybrid classifier for heart sound classification.

A review on the cross-lingual information retrieval

Information retrieval involves finding some required information in a collection of information or in database. The collection not necessarily be in one language only as information does not limited to language. The simplest way to search for the information is to look at every item in the collection and when the need to translate the languages being used arises, this is where the techniques and methods that were being developed for the cross-lingual retrieval system will take place. This article reviews some recent researches focusing on topics in cross-lingual information retrieval and their role in current research directions in the wide area of information retrieval.

Evaluation of Quranic text retrieval system based on manually indexed topics

This paper investigates the effectiveness of a state of the art information retrieval (IR) system in the verse retrieval problem for Quranic text. The evaluation is based on manually indexed topics of the Quran that provides both the queries and the relevance judgments. Furthermore, the system is evaluated in both Malay and English environment. The performance of the system is measured based on the MAP, the precision at 1, 5 and 10, and the MRR scores. The results of the evaluation are promising, showing the IR system has many potential for the Quranic text retrieval.

An effective fusion model for image retrieval

In the past decade, the popular Bag of Visual Words approach has been applied to many computer vision tasks, including image classification, video search, robot localization, and texture recognition. Unfortunately, most approaches use intensity features and discard color information, an important characteristic of any image that is motivated by human vision. Besides, if background colors are higher than foreground ones, Dominant Color Descriptor (DCD) retrieves images that contain similar background colors correctly. On the other hand, just color feature extraction is not sufficient for similar objects with different color descriptors (e.g. white dog vs. black dog). To solve these problems, a new Salient DCD (SDCD) color descriptor is proposed to extract foreground color and add semantic information into DCD based on the color distances and salient object extraction methods. Besides, a new fusion model is presented to fuse SDCD histogram and PHOW MSDSIFT histogram. Performance evaluation on several datasets proves that the new approach outperforms other existing, state-of-the-art methods.

English and Malay cross-lingual sentiment lexicon acquisition and analysis

Sentiment analysis finds opinions, sentiments or emotions in user-generated contents. Most efforts are focusing on the English language, for which a large amount of sources and tools for sentiment analysis are available. The objective of this paper is to introduce a cross-lingual sentiment lexicon acquisition method for the Malay and English languages and further being test on a set of news test collections. Several part of speech tags are being experimented using the Word Score Summation technique in order to classify the sentiment of the news articles. This method records up to 50% as experimental accuracy result and works better for verbs and negations in both the English and Malay news articles.