Polarity Identification Research Articles

An Intelligent Data Analysis for Recommendation Systems Using Machine Learning

In recent times, selection of a suitable hotel location and reservation of accommodation have become a critical issue for the travelers. The online hotel search has been increased at a very fast pace and became very time-consuming due to the presence of huge amount of online information. Recommender systems (RSs) are getting importance due to their significance in making decisions and providing detailed information about the required product or a service. To acquire the hotel recommendations while dealing with textual hotel reviews, numerical ranks, votes, ratings, and number of video views have become difficult. To generate true recommendations, we have proposed an intelligent approach which also deals with large-sized heterogeneous data to fulfill the needs of the potential customers. The collaborative filtering (CF) approach is one of the most popular techniques of the RS to generate recommendations. We have proposed a novel CF recommendation approach in which opinion-based sentiment analysis is used to achieve hotel feature matrix by polarity identification. Our approach combines lexical analysis, syntax analysis, and semantic analysis to understand sentiment towards hotel features and the profiling of guest type (solo, family, couple etc). The proposed system recommends hotels based on the hotel features and guest type for personalized recommendation. The developed system not only has the ability to handle heterogeneous data using big data Hadoop platform but it also recommends hotel class based on guest type using fuzzy rules. Different experiments are performed over the real-world datasets obtained from two hotel websites. Moreover, the values of precision and recall and F-measure have been calculated, and the results are discussed in terms of improved accuracy and response time, significantly better than the traditional approaches.

Development of positioning system for Nuclear-fuel rod automated assembly

Abstract A heavy-water nuclear reactor requires five different types of nuclear-fuel rods assemble into bundles. Intelligent identification and positioning of these different types rods for automated bundle assembly remain a challenge owing to their extensive variations and minute distinctions. This paper presents an innovative machine-vision based nuclear-fuel rod positioning system that enables automated rod bundle assembly in a heavy-water nuclear reactor. The system is capable of identifying the type and polarity and adjusting the pose of rods by incorporating the following solutions: 1) a hypercentric imaging solution that is capable of capturing clear and complete images of the rod spacers, even for the rods with large straightness deviations; 2) a robust and noise-resistant multi-scale, multi-directional morphological edge extraction algorithm that features complete and accurate edge image extraction with minimum false edges; and 3) a rod body center at spacers deviation correction algorithm that contributes to a higher level of consistency with the true rod body center. The system is robust, as demonstrated by the following performance indices: a process capability Cpk of 1.14, which is translated into a process yield of 99.95%; 100% correct rod type identification; 100% correct rod polarity identification; and an average time of 8.92 s for positioning a single rod, meeting the required production cycle. The system has been successfully deployed in the North Nuclear Fuel Components Co., Ltd. (a subsidiary of China National Nuclear Corporation).

Novel Phenotypic Elements of Type IV Collagenopathy Revealed by the Drosophila Model

Type IV collagen is proposed to be a key molecule in the evolvement of multicellular animals by forming the architectural unit basement membrane, a specialized form of the extracellular matrix. Functions of the basement membrane include guiding organ regeneration, tissue repair, modulation of cell differentiation, apical–basal polarity identification, cell migration and adhesion, regulation of growth factor signaling gradients, maintenance of tissue architecture and compartmentalization. Type IV collagenopathy is a devastating systemic disease affecting the circulatory, renal and visual systems and the skeletal muscles. It is observed in patients carrying mutations in the COL4A1 gene, which codes for the ubiquitous basement membrane component. Col4a1 mouse mutants display the human symptoms of type IV collagenopathy. We chose the Drosophila melanogaster model as we recorded dominant, temperature-sensitive mutations in the cognate col4a1 gene of the fruit fly and demonstrated phenotypic elements which have not yet been explored in humans or in mouse models. In this paper we show a transition of the Z-discs, normally bordering each sarcomere, to the level of M-discs significantly penetrant in the mutants, uneven distribution of fused mitochondria in the Malpighian tubules of the excretory organ and a loss of sarcomere structure in the visceral muscles in the gut of mutants. Our observations demonstrate the systemic nature of the col4a1 mutations in the fruit fly. However, these traits are elements of the type IV collagen-associated pathology and may provide insights into approaches that can alleviate symptoms of the disease.

Development and testing of an efficient and cost-effective underwater propulsion system

Underwater vehicle propulsion performed by exploiting electrical motor is in general the most flexible solution and it is growing in popularity because of its high efficiency both at high and at low advance speed, quick and simple deployment, low costs, and encumbrance. In the present work, permanent magnet synchronous motors for underwater propulsion are proposed. In particular, advanced sensorless control techniques of permanent magnet synchronous motors permit reduced costs, high reliability, and performances. When dealing with small autonomous underwater vehicle propulsion, such devices are hard to find in the market. Hence, the authors focused the research in the development of a system able to perform a reliable rotational speed and torque sensorless estimation. The design and implementation of a complete solution for underwater propulsion are presented as well as a novel rotor polarity identification technique exploiting a high-frequency injection control. Pool tests for the identification of the performances and of the dynamic parameters of the propulsion system are presented. Finally, the possibility of operating a sensorless estimation of the thrust and torque exerted by the propeller and pool test measurements are presented. These features could be exploited to improve navigation accuracy and involves obvious benefits in terms of cost reduction and reliability of the system.

A Method of Sentiment Polarity Identification in Financial News using Deep Learning

In this research, sentiment polarity identification model for finance is developed using financial and economic corpus and deep learning. Specifically, “Japanese Economy Watchers Survey” is used for the corpus and our model accuracy is high. Then the model is applied to evaluate news sentiment for predicting stock return. Our results confirmed that our model captures more news sentiment compared to using common polarity dictionary.

Statistical inferences for polarity identification in natural language.

Information forms the basis for all human behavior, including the ubiquitous decision-making that people constantly perform in their every day lives. It is thus the mission of researchers to understand how humans process information to reach decisions. In order to facilitate this task, this work proposes LASSO regularization as a statistical tool to extract decisive words from textual content in order to study the reception of granular expressions in natural language. This differs from the usual use of the LASSO as a predictive model and, instead, yields highly interpretable statistical inferences between the occurrences of words and an outcome variable. Accordingly, the method suggests direct implications for the social sciences: it serves as a statistical procedure for generating domain-specific dictionaries as opposed to frequently employed heuristics. In addition, researchers can now identify text segments and word choices that are statistically decisive to authors or readers and, based on this knowledge, test hypotheses from behavioral research.

Dissecting emotion and user influence in social media communities: An interaction modeling approach

Human emotion expressed in social media plays an increasingly important role in shaping policies and decisions. However, the process by which emotion produces influence in online social media networks is relatively unknown. Previous works focus largely on sentiment classification and polarity identification but do not adequately consider the way emotion affects user influence. This research developed a novel framework, a theory-based model, and a proof-of-concept system for dissecting emotion and user influence in social media networks. The system models emotion-triggered influence and facilitates analysis of emotion-influence causality in the context of U.S. border security (using 5,327,813 tweets posted by 1,303,477 users). Motivated by a theory of emotion spread, the model was integrated in an influence-computation method, called the interaction modeling (IM) approach, which was compared with a benchmark using a user centrality (UC) approach based on social positions. IM was found to have identified influential users who are more broadly related to U.S. cultural issues. Influential users tended to express intense emotions of fear, anger, disgust, and sadness. The emotion trust distinguishes influential users from others, whereas anger and fear contributed significantly to causing user influence. The research contributes to incorporating human emotion into the data-information-knowledge-wisdom model of knowledge management and to providing new information systems artifacts and new causality findings for emotion-influence analysis.

Performance evaluation of DNN with other machine learning techniques in a cluster using Apache Spark and MLlib

Sentiment analysis on large data has become challenging due to the diversity, and nature of data. Advancements in the internet, along with large data availability have obviated the traditional limitations to distributed computing. The objective of this work is to carry out sentiment analysis on Apache Spark distributed Framework to speed up computations and enhance machine performance in diverse environments. The analysis, such as polarity identification, subjective analysis and email spam etc., are carried on various text datasets. After pre-processing, Term Frequency-Inverse Document Frequency (TF-IDF) and unsupervised Spark-Latent Dirichlet Allocation (LDA) clustering algorithms are used for feature extraction and selection to improve the accuracy. Deep Neural Networks (DNN), Support Vector Machines (SVM), Tree ensemble classifiers are used to evaluate the performance of the framework on single node and cluster environments. Finally, the proposed work aims at building an approach for enhancing machine performance, more in terms of runtime over accuracy.

An Innovative Rotor Position Detection at Stand-Still and Low Speed with Carrier Phase-Shifted PWM Method

An innovative permanent magnet synchronous motor rotor position detection method using d-q reference-frames derived from PWM inverter switching is presented based on carrier phase-shift PWM method. It also gives the development the polarity identification at standstill for permanent magnet synchronies motor in the rotary frame with position detected of the neutral voltage. The new technique detects the motor position from simple measurements of the neutral point voltage of the motor influenced by the variation of inductances with respect to rotor position. The transfer is derived with constant element and 2nd harmonic element of selfinductance and mutual-inductance between three phase inductances and the inductance of d-axis and q-axis. Theoretical studies are carried out and verified using experiment results with variation rotor position over one electrical cycle at standstill. Rotor position estimation from stator inductance variation with rotor position is effective in zero speed and low speed.

AUXIN RESPONSE FACTOR3 plays distinct role during early flower development

ABSTRACTAUXIN RESPONSE FACTOR3 (ARF3), one of the auxin response factors family of transcription factors, is well characterized by its functions in polarity identification and organ patterning. We recently demonstrated that ARF3 plays important roles in floral meristem (FM) maintenance and termination by regulating cytokinin biosynthesis and signaling. However, the relationship of its multiple roles in differently developmental stage is still unclear. Here, we present data that ARF3 plays distinct roles during early flower development that are different from its roles in organ polarity determination and pattering. Thus, our findings shed light on the functional diversity of one specific transcription factor in plant development.

Using long short-term memory deep neural networks for aspect-based sentiment analysis of Arabic reviews

This paper proposes a state-of-the-art research for aspect-based sentiment analysis of Arabic Hotels’ reviews using two implementations of long short-term memory (LSTM) neural networks. The first one is (a) a character-level bidirectional LSTM along with conditional random field classifier (Bi-LSTM-CRF) for aspect opinion target expressions (OTEs) extraction, and the second one is (b) an aspect-based LSTM for aspect sentiment polarity classification in which the aspect-OTEs are considered as attention expressions to support the sentiment polarity identification. Proposed approaches are evaluated using a reference dataset of Arabic Hotels’ reviews. Results show that our approaches outperform baseline research on both tasks with an enhancement of 39% for the task of aspect-OTEs extraction and 6% for the aspect sentiment polarity classification task.

Polarity identification of ZnO(0001) surface by reflection high-energy electron diffraction

We measured rocking curves of reflection high-energy electron diffraction (RHEED) from ZnO(0001) polar surfaces. It was found that the rocking curves for each Zn- and O-terminated surface differ considerably. The relaxed structure of each polar surface was obtained from first-principles calculations using density functional theory. The results reveal compression relaxation of the top bilayer. Experimental rocking curves of each polar surface have been successfully reproduced by dynamical calculation of RHEED based on their relaxed surface structures. It was demonstrated that the RHEED method can identify the polarity of ZnO(0001) surfaces.

Enhancing Aspect-Based Sentiment Analysis of Arabic Hotels’ reviews using morphological, syntactic and semantic features

This research presents an enhanced approach for Aspect-Based Sentiment Analysis (ABSA) of Hotels’ Arabic reviews using supervised machine learning. The proposed approach employs a state-of-the-art research of training a set of classifiers with morphological, syntactic, and semantic features to address the research tasks namely: (a) T1:Aspect Category Identification, (b) T2:Opinion Target Expression (OTE) Extraction, and (c) T3: Sentiment Polarity Identification. Employed classifiers include Naïve Bayes, Bayes Networks, Decision Tree, K-Nearest Neighbor (K-NN), and Support-Vector Machine (SVM).The approach was evaluated using a reference dataset based on Semantic Evaluation 2016 workshop (SemEval-2016: Task-5). Results show that the supervised learning approach outperforms related work evaluated using the same dataset. More precisely, evaluation results show that all classifiers in the proposed approach outperform the baseline approach, and the overall enhancement for the best performing classifier (SVM) is around 53% for T1, around 59% for T2, and around 19% in T3.

Rotor Position Sensorless Control of Wound-Field Flux-Switching Machine Based on High Frequency Square-Wave Voltage Injection

This paper compares three shaft-sensorless control schemes for wound-field flux-switching machines based on a high frequency (HF) square-wave voltage injection technique. An HF model for the machine, with inclusion of the field winding, is first presented. Because the machine had armature and field windings, HF voltage is injected into and processed in the armature winding as with conventional permanent magnet synchronous machines (PMSMs) or injected into one winding and processed in the induced current signal in the other winding. Both the analytical and experimental results reveal that the scheme with $d$ -axis voltage injection and a $q$ -axis induced current process is generally similar to that used for PMSMs. Polarity identification is required to prevent phase errors in the estimated position. The schemes with separate windings for voltage injection and current processing demonstrate superior performance compared with the scheme without, and both schemes do not require polarity identification. Moreover, voltage injection at the field winding has an additional advantage for high-speed operations.

Improving Root Cause Analysis Using Fuzzy Polarity Identification and Conflict Resolution Techniques

Identifying the root cause of feedbacks is one of the major functionalities in a marketing system. Increased use of online social networking media has automatically led to a raise in the users expressing their views in these platforms. Analyzing data from such media provides unbiased information regarding any product or service. This article presents a polarity-based root cause identification technique that identifies the root cause of a query presented by the user. The query is presented to all the available data sources, and the information returned is filtered using conflict resolution techniques. The data is then subjected to a fuzzy polarity analyzer that divides the data into groups based on their polarity levels. The data is then cross-referenced with the domain based ontology to identify the root cause.

ABSA Toolkit: An Open Source Tool for Aspect Based Sentiment Analysis

With a rapid increase in e-commerce websites, people are often interested in analyzing customer reviews expressing customer sentiments on different features of a product before making purchase decisions. In this paper, we present ABSA (Aspect-Based Sentiment Analysis) Toolkit developed for performing aspect-level sentiment analysis on customer reviews. The system has two main phases: (a) development phase and (b) production phase. The development phase allows a user to train models for performing aspect level sentiment analysis tasks on the target domain. In the production phase, a web application is provided through which an end user can submit reviews to analyze aspect level sentiments. The system is built using state-of-the-art approaches of aspect term extraction, aspect category detection, and aspect polarity identification. To the best of our knowledge, there is no framework publicly available to build aspect-level sentiment analysis application. All the source code of the ABSA toolkit is available on GitHub.

Deep Recurrent neural network vs. support vector machine for aspect-based sentiment analysis of Arabic hotels’ reviews

In this research, state-of-the-art approaches based on supervised machine learning are presented to address the challenges of aspect-based sentiment analysis (ABSA) of Arabic Hotels’ reviews. Two approaches of deep recurrent neural network (RNN) and support vector machine (SVM) are implemented and trained along with lexical, word, syntactic, morphological, and semantic features. The proposed approaches are evaluated using a reference dataset of Arabic Hotels’ reviews. Evaluation results show that the SVM approach outperforms the other deep RNN approach in the research investigated tasks (T1: aspect category identification, T2: aspect opinion target expression (OTE) extraction, and T3: aspect sentiment polarity identification). Whereas, when focusing on the execution time required for training and testing the models, the deep RNN execution time was faster, especially for the second task.

Initial Rotor Position Estimation Using Zero-Sequence Carrier Voltage for Permanent-Magnet Synchronous Machines

Both rotating and anticlockwise pulsating signal injection methods based on zero-sequence voltage sensing have been reported to have large signal-to-noise ratio and bandwidths, and great stability for the sensorless control of permanent-magnet synchronous machines. However, the initial rotor position estimation and magnetic polarity identification using zero-sequence voltage have not been investigated. Therefore, this paper presents two types of magnetic polarity identification methods, based on the amplitude variation of zero-sequence voltage due to saturation changing, and based on the secondary harmonics of zero-sequence voltage, for the two carrier injection methods, respectively. It is found that the amplitude variation based method using zero-sequence voltage has higher detection sensitivity for the real magnetic polarity compared to the conventional method using the carrier current. In contrast, the secondary harmonic based identification method using zero-sequence voltage for rotating signal injection has the advantage of fast response, and moreover has large signal amplitude and less distortion compared to the conventional secondary carrier current harmonics. However, the secondary harmonic method loses the capability for polarity detection for the anticlockwise pulsating injection method. Experiments are carried out on a laboratory permanent-magnet machine to verify the theoretical analyses.

Polarity Identification of Aspect based Sentiment Reviews

Objectives: To show the effectiveness of using random Fourier features in detecting sentiment polarities. Methods/ Statistical Analysis: The paper proposes on identifying the sentiment polarity of laptop and restaurant dataset towards three different polarity categories- positive, negative, and neutral. It provides experimental comparisons on conventional machine learning methods for detecting review polarities. Several articles have shown the effectiveness of random Fourier features are used in classification problems. The present paper prepares random Fourier features corresponding to the polarity data. A regularized least square strategy is adopted to fit a model and to perform the polarity detection task. Findings: Experiments were performed with 10 cross-validations. The proposed method with random Fourier features gives 80% accuracy over conventional classifiers. Initially the features are mapped to a lower dimension (chosen manually) and corresponding random Fourier features are obtained. The experiments are evaluated using Precision, recall, and F-measure. Application/Improvements: The method presented in this paper shows that aspect based polarity detection can be improved by choosing suitable features and mapping to lower dimension.

Polarity Identification of Aspect based Sentiment Reviews

Polarity Identification of Aspect based Sentiment Reviews