To help individuals or companies make a systematic and more accurate decisions, sentiment analysis (SA) is used to evaluate the polarity of reviews. In SA, feature selection phase is an important phase for machine learning classifiers specifically when the datasets used in training is huge. Whale Optimization Algorithm (WOA) is one of the recent metaheuristic optimization algorithm that mimics the whale hunting mechanism. However, WOA suffers from the same problem faced by many other optimization algorithms and tend to fall in local optima. To overcome these problems, two improvements for WOA algorithm are proposed in this paper. The first improvement includes using Elite Opposition-Based Learning (EOBL) at initialization phase of WOA. The second improvement involves the incorporation of evolutionary operators from Differential Evolution algorithm at the end of each WOA iteration including mutation, crossover, and selection operators. In addition, we also used Information Gain (IG) as a filter features selection technique with WOA using Support Vector Machine (SVM) classifier to reduce the search space explored by WOA. To verify our proposed approach, four Arabic benchmark datasets for sentiment analysis are used since there are only a few studies in sentiment analysis conducted for Arabic language as compared to English. The proposed algorithm is compared with six well-known optimization algorithms and two deep learning algorithms. The comprehensive experiments results show that the proposed algorithm outperforms all other algorithms in terms of sentiment analysis classification accuracy through finding the best solutions, while its also minimizes the number of selected features.

Improved whale optimization algorithm for feature selection in Arabic sentiment analysis

The available classical ontology-based systems are inadequate and limit the information extraction from the internet.An ontology with fuzzy logic is effective technology for precise information extraction from blurred data environment.We proposed fuzzy domain ontology with SVM to extract feature's opinion from reviews and to compute polarity.The result of opinion mining by using SVM with FDO for online large data set is better than SVM-based existing systems.The proposed system thoroughly explains the feature extraction and polarity computation. With the explosion of Social media, Opinion mining has been used rapidly in recent years. However, a few studies focused on the precision rate of feature review's and opinion word's extraction. These studies do not come with any optimum mechanism of supplying required precision rate for effective opinion mining. Most of these studies are based on Naive Bayes, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and classical ontology. These systems are still imperfect for classifying the feature reviews into more degrees of polarity terms (strong negative, negative, neutral, positive and strong positive). Further, the existing classical ontology-based systems cannot extract blurred information from reviews; thus, it provides poor results. In this regard, this paper proposes a robust classification technique for feature review's identification and semantic knowledge for opinion mining based on SVM and Fuzzy Domain Ontology (FDO). The proposed system retrieves a collection of reviews about hotel and hotel features. The SVM identifies hotel feature reviews and filter out irrelevant reviews (noises) and the FDO is then used to compute the polarity term of each feature. The amalgamation of FDO and SVM significantly increases the precision rate of review's and opinion word's extraction and accuracy of opinion mining. The FDO and intelligent prototype are developed using Protege OWL-2 (Ontology Web Language) tool and JAVA, respectively. The experimental result shows considerable performance improvement in feature review's classification and opinion mining.

Opinion mining based on fuzzy domain ontology and Support Vector Machine

Sentiment analysis (SA) is one of the most useful natural language processing applications. Literature is flooding with many papers and systems addressing this task, but most of the work is focused on English. In this paper, we present “Mazajak”, an online system for Arabic SA. The system is based on a deep learning model, which achieves state-of-the-art results on many Arabic dialect datasets including SemEval 2017 and ASTD. The availability of such system should assist various applications and research that rely on sentiment analysis as a tool.

/pdf/mazajak-an-online-arabic-sentiment-analyser-qrme7129mx.pdf

Mazajak: An Online Arabic Sentiment Analyser

A review of sentiment analysis research in Arabic language

Twitter Sentiment to Analyze Net Brand Reputation of Mobile Phone Providers

Social networks have become one of our daily life activities not only in socializing but in e-commerce, e-learning, and politics.  However, they have more effect on the youth generation all over the world, specifically in the Middle East.  Arabic slang language is widely used on social networks more than classical Arabic since most of the users of social networks are young-mid age.  However, Arabic slang language suffers from the new expressive (opinion) words and idioms as well as the unstructured format.  Mining Arabic slang language requires efficient techniques to extract youth opinions on various issues, such as news websites.  In this paper, we constructed a Slang Sentimental Words and Idioms Lexicon (SSWIL) of opinion words is built. In addition, we propose a Gaussian kernel SVM classifier for Arabic slang language to classify Arabic news’ comments on Facebook. To test the performance of the proposed classifier, several Facebook news’ comments are used, where 86.86% accuracy rate is obtained with precision 88.63 and recall 78.

Sentiment Analysis of Arabic Slang Comments on Facebook

In this paper, a new method is proposed for the frequencyresponse evaluations of switched-capacitor networks of any topology. It relies on reducing the z -transform impulse response of the SCN into a rational function form. Closed-form expressions for the coefficients of the rational expansion, as well as its degree, are given. Illustrative examples showing the merits of this new approach over the existing one .are also included.

http://ieeexplore.ieee.org/iel5/31/23595/01086216.pdf

A method for frequency-domain analysis of switched-capacitor filters

As e-commerce is increasingly becoming popular, the number of customer reviews that a product receives grows rapidly However, for popular products, many online product reviews exist but for other reviews product reviews are very few These online discussions about particular products may help other online users to make a decision in buying/ not buying those products, like in amazoncom1 and ebaycom2 Since an enormous number of unstructured and ungrammatical reviews on a product exist, opinion mining is getting a crucial research area for better decision making of buying products In this paper, we apply an opinion mining approach to summarize the unstructured and ungrammatical users' reviews, based on Support Vector Machine (SVM) Two levels of classification is applied: 1) Features classification and 2) Polarity classification for every feature class Our approach has been tested on Amazon data with dataset of 535 sentences, where a summary is obtained and analysis of precision (9315%) and recall (9241%) illustrate the accuracy of the proposed system

Utilizing support vector machines in mining online customer reviews

The application of wireless sensor networks is widely spread through the last years as it is well known in many fields and multiple applications. Localization of nodes within wireless sensor networks is one of the important topics in studying and managing these networks. The presented new localization technique combines the received signal strength indicator method which limits the communications between nodes to the range of accessible radiated signal, with a new trend which is social network analysis that deals with relationships between nodes in any network with metrics and layouts. By using mixed metric between degree and closeness, we will maintain the suitable elected seeds that will be anchors for around nodes inside the network. Trilateration calculations will be applied between optimized elected nodes with higher centrality to localize the target nodes.

A New Localization Technique for Wireless Sensor Networks Using Social Network Analysis

The present paper derives a fast recursive least squares algorithm for the design of impedance matching network to any complex termination. Starting from any non-zero initial values, and for any topology, the network components are derived iteratively in a manner that optimizes the network's insertion loss characteristics. The strategy used is to minimize a weighted sum of the error between ideal time response and the network's time response. The main feature of the proposed technique is its very quick convergence, as it involves time computation at very small number of points. Besides, the proposed method has the flexibility of incorporating any frequency domain characteristics in the objective function to he minimum.

https://ieeexplore.ieee.org/iel3/3992/11483/00551610.pdf

M. M. Doss

Papers

Sentiment Analysis of Arabic Slang Comments on Facebook

A method for frequency-domain analysis of switched-capacitor filters

Utilizing support vector machines in mining online customer reviews

A New Localization Technique for Wireless Sensor Networks Using Social Network Analysis

A fast adaptive technique for impedance matching networks