Browse Items (11809 total)
Sort by:
-
Sentiment Analysis of Online Hotel Reviews Employing Bidirectional GRU with Attention Mechanism
Online hotel reviews are a more reliable resource for potential hotel guests. Sentiment analysis is a branch of text mining, Natural Processing Language that seeks to identify personality traits, emotions, and other factors. Deep Learning algorithms such as LSTM and GRU have successfully generated context information in sequence learning. However, deep learning cannot focus on the words that contribute the most and cannot capture important content information. This research aims to overcome the inability of LSTM and GRU to capture information. The results are satisfactory, with 93.12% accuracy, 95% ROCAUC, and 95.28% precision recall. This research paper helps managers identify areas to improve their products and services, target marketing campaigns, and identify customer churn. 2024 IEEE. -
Sentiment Analysis of Lenders Motivation to Use a Peer-To-Peer (P2P) Lending Platform: LenDenClub.Com
Peer-To-Peer lending platforms are becoming a good investment avenue for lenders to invest their money in borrowers, who need money for a different purpose. As lending and borrowing of money is facilitated by the P2P lending platform, it becomes necessary for the platform to understand the users and accordingly fine tune the 'User Interface' (UI) and 'User Experience' (UX) of the platform. For lending and borrowing to take place through a platform it is necessary to have an 'n' number of lenders who are ready to lend money to an 'x' number of borrowers. This study is specifically done to understand lenders' motivation to use P2P lending platforms. This is a unique research work as sentiment analysis of lenders' motivation to use these platforms has not been explored earlier. The sentiment analysis technique was used to examine lenders' sentiments towards the use of P2P lending platforms. The research results show that, ~ 70 percent of lenders showed motivation to use P2P lending platforms as an investment avenue in the future. As the P2P lending platforms are relatively new more research can be carried out in future. 2024 IEEE. -
Sentiment analysis of impact of social platforms on the market share of a company
Sentimental analysis is also known as opinion mining or emotion AI. It refers to the use of natural language processing, text analysis, computational linguistics and biometrics to systematically identify, extract, and study affective states and subjective information. In this paper, Amazon reviews and blogs are analyzed to detect the sentiment using linguistic feature utility. Evaluation of the usefulness of existing lexical resources as well as capturing information about the informal and creative language used in online service platform is done. The goal of this research is to show the impact on the market-share of Vivo in comparison with that of Oppo and highlight the reason for the impact. BEIESP. -
Sentiment Analysis of COVID-19 tweets by Deep Learning ClassifiersA study to show how popularity is affecting accuracy in social media
COVID-19 originally known as Corona VIrus Disease of 2019, has been declared as a pandemic by World Health Organization (WHO) on 11th March 2020. Unprecedented pressures have mounted on each country to make compelling requisites for controlling the population by assessing the cases and properly utilizing available resources. The rapid number of exponential cases globally has become the apprehension of panic, fear and anxiety among people. The mental and physical health of the global population is found to be directly proportional to this pandemic disease. The current situation has reported more than twenty four million people being tested positive worldwide as of 27th August, 2020. Therefore, it is the need of the hour to implement different measures to safeguard the countries by demystifying the pertinent facts and information. This paper aims to bring out the fact that tweets containing all handles related to COVID-19 and WHO have been unsuccessful in guiding people around this pandemic outbreak appositely. This study analyzes two types of tweets gathered during the pandemic times. In one case, around twenty three thousand most re-tweeted tweets within the time span from 1st Jan 2019 to 23rd March 2020 have been analyzed and observation says that the maximum number of the tweets portrays neutral or negative sentiments. On the other hand, a dataset containing 226,668 tweets collected within the time span between December 2019 and May 2020 have been analyzed which contrastingly show that there were a maximum number of positive and neutral tweets tweeted by netizens. The research demonstrates that though people have tweeted mostly positive regarding COVID-19, yet netizens were busy engrossed in re-tweeting the negative tweets and that no useful words could be found in WordCloud or computations using word frequency in tweets. The claims have been validated through a proposed model using deep learning classifiers with admissible accuracy up to 81%. Apart from these the authors have proposed the implementation of a Gaussian membership function based fuzzy rule base to correctly identify sentiments from tweets. The accuracy for the said model yields up to a permissible rate of 79%. 2020 Elsevier B.V. -
Sentiment Analysis for Online Shopping Reviews Using Machine Learning
Everyday shoppers need reliable and insightful reviews of e-commerce websites to enhance their shopping experience. This research study explores sentiment analysis on Amazon reviews. It utilizes them as a diverse repository of customer opinions by unlocking their embedded sentiments, thereby recognizing their pivotal role in guiding potential buyers. Sentiment misinterpretations may result from many machine learning models that have trouble comprehending the context of Amazon reviews, particularly regarding subtle wordings, sarcasm, or irony. Additionally, these models can have biases that skew sentiment analysis results, mainly when working with a diverse set of Amazon review datasets. To overcome these, three machine learning models, namely, Bidirectional Encoder Representations from Transformers (BERT), Bidirectional and Auto-Regressive Transformers (BART), and Generative Pre-trained Transformers (GPT) are used in this study. During the experimental research, it was observed that BERT gave the highest accuracy of 90% when compared with BART (70%) and GPT (84%) models. BERTs bidirectional contextual comprehension at identifying subtleties in language provides a thorough and realistic representation of the sentiments of Amazon users, which is why the model gave the highest accuracy. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
-
Sentencing Framework in the Administration of Criminal Justice in India :
This Thesis aims at having uniformity while sentencing the accused in respect of similar newlineoffences by various criminal courts. It is submitted that, in India, there is no separate sentencing Act which provides for the sentencing of the accused. It is submitted that the present thesis also recommends for the post sentencing/research process and administration of Criminal Justice through courts and supervisory power of the court over the executive after newlinethe conviction of the accused and during the pre-trial detention. Emphasis is also laid on newlineBails Act which is required to be legislated in the administration of Criminal Justice in India. The said Bails Act and Sentencing Act are very much in force in different common law countries such as New Zealand, UK, and USA. Similar legislations are the need of hour in the present day for administration of Criminal justice in India. The thesis also aims at highlighting the disparity of Sentencing by the different Criminal Courts in India. There are instances where length of detention itself is held to be sufficient, mitigating grounds are taken into consideration, and the accused is being given set-off for the period that he has already newlineundergone. The administration of post-sentencing process, more particularly probation is also being highlighted. The need for probation is also being highlighted, so also the requirement of plea bargaining being more popularised. The grant of parole by the executive in ignorance of conviction order is also critically analysed. Reforms are suggested for the better administration of criminal justice with special reference to sentencing. -
Sentence Classification Using Attention Model for E-Commerce Product Review
The importance of aspect extraction in text classification, particularly in the e-commerce sector. E-commerce platforms generate vast amounts of textual data, such as comments, product descriptions, and customer reviews, which contain valuable information about various aspects of products or services. Aspect extraction involves identifying and classifying individual traits or aspects mentioned in textual reviews to understand customer opinions, improve products, and enhance the customer experience. The role of product reviews in e-commerce is discussed, emphasizing their value in aiding customers' purchase decisions and guiding businesses in product stocking and marketing strategies. Reviews are essential for boosting sales potential, maintaining a good reputation, and promoting brand recognition. Customers extensively research product reviews from different sources before purchasing, making them vital user-generated content for e-commerce businesses. The current work provided an efficient and novel classification model for sentence classification using the ABNAM model. The automated text classification models available cannot categorize the data into sixteen distinct classes. The technologies applied for the mentioned work contain TF-IDF, N-gram, CNN, linear SVM, random forest, Nae bays, and ABNAM with significant results. The best-performing ML method for the successful classification of a given sentence into one of the sixteen categories is achieved with the proposed model named the based Neural Attention Model (ABNAM), which has the highest accuracy at 97%. The research acclaimed ABNAM as a novel classification model with the highest-class categorizations. 2024 Nagendra N and Chandra J. This open-access article is distributed under a Creative Commons Attribution (CC-BY) 4.0 license. -
Sensory processing sensitivity in relation to coping strategies: exploring the mediating role of depression, anxiety and stress
Existing research on sensory processing sensitivity (SPS) focuses majorly on populations involving children, those with Autism Spectrum Disorder, and those belonging to the Western countries. This study aims to contribute in bridging this gap by exploring the mediating role of Depression, Anxiety, Stress on the relationship between SPS and coping strategies in the general population, while also assessing the prevalence of these variables. Data was collected from a convenience sample of 107 participants (mean age = 20.6years, 57.9% females). Participants responses were recorded for the Highly Sensitive Person Scale (HSPS), the Depression, Anxiety, Stress Scale (DASS-21), and the Coping Strategies Inventory-Short Form (CSI-SF). Correlational and mediation analyses of SPS, coping strategies and Depression, Anxiety and Stress were done. In the sample, 31.78% of individuals were found to be Highly Sensitive Persons (HSPs). The findings revealed significant relationships between SPS, Depression, Anxiety, Stress and coping strategies. Depression and Anxiety were observed to be significant mediators. While SPS as a trait may not be inherently modifiable, our results on its association with emotion-focused disengagement coping provide insight into target dysfunctional patterns for effective management of depression, stress, and anxiety. Further research is warranted to enhance the applicability of this study. The Author(s) 2024. -
Sensor based intelligent wearable helmet for early detection of stroke in patients /
Patent Number: 202141044803, Applicant: Dr.S.Balamurugan.
Every year nearly 50 million people suffer from stroke, within which 5 million people become permanently disabled. Early detection of stroke and right time of hospitalization of patients increases the chances of complete recovery. Proposed is a sensor based intelligent wearable helmet for early detection of stroke in patients. The proposed helmet allows real-time monitoring and simultaneous analysis of health parameter of patients, the affected parts of brain and cardio vascular system. -
Sensor based intelligent smart watch for early detection of heart attacks in patients suffering from cardiovascular diseases /
Patent Number: 202141045592, Applicant: Dr.S.Balamurugan.
Heart attack is one of the leading reasons for human deaths worldwide. When the blood supply to heart is suddenly blocked by a clot in coronary artery, heart attack occurs. This shortage of blood supply to the heart can cause serious damage to heart muscles and may sometime lead to death of the individual. However, early detection of symptoms of heart attack and providing necessary first aid could drastically reduce the mortality rate. Fatal heart attacks are quite common in people who are already suffering from cardiovascular diseases. This invention discloses a smart watch with multiple sensors that are capable to detect the possibility of cardiac arrest and inform the same to caretakers, doctors and ambulance vehicles in the nearby geographical location. -
Sensor based intelligent digital nose to detect spoilage of food using machine learning /
Patent Number: 202141042368, Applicant:Dr.S.Balamurugan.
Detecting the spoilage of food is a challenging ang important task to be carried out in food processing industry. The food contamination may cause variety of diseases to human mankind including- diarrhoea, dysentery, and sometime may even to death of the individual. Proposed is an intelligent electronic nose, which is capable of diagnosing the food decay based on the foul smell evolved from the food material. The digital nose is composed of an array of metallic-oxide sensors which are capable of detecting the odours from the foods stored roughly more than a week. The sensor arrays are capable of detecting the odours and classifying the same into categories- pungent, alcoholic, fishy, cheesy, fermented, musty and bitter. -
Sensitization of university students in supporting underprivileged children
Education is the fundamental right of every child and an essential element of human growth. Indian education is divided into two parts: private and government education. Underprivileged children, affected by socio-economic factors, predominantly choose government education. Government primary educational institutions have failed to cope with the requirements of the corporate world. On the other hand, the students studying in private higher educational institutions seldom think of the challenges that socio-economically underprivileged children face. Genesys is the forum that unites these socio-economically underprivileged children with students at Christ University. Teaching and training disadvantaged children are the social responsibilities of young people, especially those in higher education. Each student should teach at least one person to make it a win-win situation for both learner and trainer. It helps University students build social skills and provides them with the opportunity to become part of the nation-building process. The chapter employed the quantitative study method to analyze the students' perception of teaching underprivileged children and how demographic variables impact it. It also identified the factors influencing the student's academic performance and psychological well-being. The study found that the students gained different skills like interpersonal skills, adaptability, teaching skills, and happiness, and these skills positively impacted their academic performance and psychological wellbeing. The expected outcome of the program supported by the university is to develop a win-win model for both University students and schoolchildren from low-income groups in society 2024 Nova Science Publishers, Inc. -
Sensitivity computation of nonlinear convective heat transfer in hybrid nanomaterial between two concentric cylinders with irregular heat sources
Heat exchangers, hot rolling, heat storage systems, and nuclear power plants utilize hybrid nanoliquid flow through an annulus for heat transport. The linear Boussinesq approximation is no longer suitable as these devices work at both moderate and extremely high temperatures. Hence, the salient features of quadratic convection on the hybrid nanoliquid flow in an inclined porous annulus are analyzed. The heat transport phenomenon is examined with an exponential space-related heat source (ESHS), the convective boundary conditions, and temperature-related heat source (THS). The significance of various shapes of nanoparticles (blades, spherical, platelets, bricks, and cylinders) on the heat and fluid flow characteristics has been explored. The complicated governing equations are solved numerically. Additionally, a statistical study (response surface methodology (RSM) and sensitivity analysis) is performed. The consequence of key parameters on the non-dimensional velocity, skin friction coefficient, temperature, and Nusselt number fields are presented through two-dimensional and surface plots. The irregular heat sources increase the magnitude of velocity and temperature fields. The quadratic and mixed convection mechanism favors the flow structure. The temperature and velocity fields are greater for platelet-shaped nanoparticles followed by cylinder, brick, and spherical-shaped nanoparticles. Further, the Nusselt number is more influenced by THS and less by the total nanoparticle volume fraction 2021 Elsevier Ltd -
Sensitivity and tolerance analysis of 2D Profilometer for TMT primary mirror segments
The primary mirror (M1) of Thirty Meter Telescope (TMT) consists of 492 segments of which, 86 are ground and polished by India-TMT. These segments are off-Axis and aspheric in nature and one of the effective methods to polish such segments is through Stressed Mirror Polishing (SMP). During SMP, consistent in-situ metrology of the surface is needed to achieve the required profile. A 2D Profilometer (2DP) will be used by India-TMT for the low frequency profile metrology. The 2DP is a contact-Approach metrology, consisting of probes positioned in a spiral pattern, measuring the sag of segment surface. Initial section of this paper deals with the sensitivity and tolerance analysis of the 2DP. This is followed by the study on position and rotational errors of the 2DP as a whole. Simulation of these analysis is carried out initially on a sphere and then on different segments of the TMT, in order to study the induced measurement errors. COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. -
Sensitivity analysis of thermal optimisation within conical gap between the cone and the surface of disk with particle deposition
This work examines the thermal and flow characteristics of TiO2+AgBr+GO/EG trihybrid nanofluid in the conical gap that exists between a disc and a cone. Effect of thermophoresis and particle deposition are examined to perceive the mass dissipation change on the surface. The governing equations of the problem are in the form of partial differential equations which are converted to nonlinear ordinary differential equations by applying proper scaling similarity transformations, and then the resultant equations are approximated numerically by using RKF45 technique. The interesting part of this research is to discuss the impact of various pertinent parameters on three cases namely: (1) rotating cone/disk (2) rotating cone/stationary disk and (3) stationary cone/rotating disk. The flow field, heat and mass transfer rates were analysed using graphical representations. Additionally, sensitivity analysis is performed on derived rate of heat transfer as a response function for input factors for different parameters. From the graph, it is perceived that flow field increases significantly with increase in the values of Reynolds numbers for both cone and disk rotations. Also, it is seen that temperature upsurges significantly for ascendent values of solid volume fraction of nanoparticles. It is also noticed that the sensitivity of the Nusselt number towards n is more for all the values of source/sink and for middle level values of n. Akadiai KiadZrt 2024. -
Sensitivity analysis of radiative heat transfer in Casson and nano fluids under diffusion-thermo and heat absorption effects
The exact analysis of the magnetohydrodynamic flow of a Newtonian nanofluid past an inclined plate through a porous medium is carried out. The flows of a Newtonian nanofluid and a non-Newtonian Casson fluid are juxtaposed. The heat transport phenomenon is analyzed in the presence of Dufour and heat absorption effects. The Darcy model and Rosseland approximation are employed to simulate the effects of porous media and radiative heat. The exact solutions are obtained by using the Laplace transform method. The effects of different physical parameters on the velocity, temperature and concentration profiles are scrutinized using graphs. Statistical techniques, like the slope of data points, coefficient of correlation, probable error, and multiple linear regression, are employed to analyze the rate of heat transfer and skin friction coefficient. Further, the sensitivity of the skin friction coefficient and Nusselt number are analyzed using the Response Surface Methodology (RSM). The Nusselt number has a positive sensitivity towards thermal radiation, and it is negatively sensitive towards nanoparticle volume fraction and Dufour number. 2019, SocietItaliana di Fisica / Springer-Verlag GmbH Germany, part of Springer Nature. -
Sensitivity Analysis of Operational Parameters of a High Temperature-Proton Exchange Membrane Fuel Cell
The lack of widespread commercialization of High-Temperature Proton Exchange Membrane Fuel Cells (HT-PEMFC) is primarily due to their poor performance and durability. Various factors impact the performance of fuel cells, one such crucial factor being the operational parameters. Suitable operating conditions not only enhance the output cell performance but also extend a fuel cell's life. Current research on the impact of operational factors on HT-PEMFC performance is largely qualitative in nature, with no quantitative indication of affecting the sensitivity of these parameters. In the present work, a three-dimensional, non-isothermal HT-PEMFC model developed earlier is used to investigate the influential sensitivities of five crucial operating parameters, each with four different levels, and is analyzed quantitatively using six evaluation indexes. The orthogonal/Taguchi method L16(45) is implemented to investigate the impact of operating parameters quantitatively. Further, the effect of each operating parameter on evaluation indexes under different operational current density regimes is investigated. The findings show that, of the parameters chosen, the working temperature and cathode pressure are the most sensitive to cell voltage and cathode overpotential distribution under all operating current density regimes. The findings would provide more precise recommendations for experimental research targeted at improving cell performance by optimizing operational parameters. 2023 The Electrochemical Society ("ECS"). Published on behalf of ECS by IOP Publishing Limited.; Highlights Influential sensitivities of crucial operating parameters are investigated. The orthogonal method is employed to investigate the impact of operating parameters. Impact of operational parameters on uniformity of species distribution is examined. The sensitivity of each operating parameter on evaluation indexes is investigated. The varying trends of operating parameters under different current density regimes is studied. 2023 The Electrochemical Society ("ECS"). Published on behalf of ECS by IOP Publishing Limited. -
Sensitivity analysis of nonlinear radiated heat transport of hybrid nanoliquid in an annulus subjected to the nonlinear Boussinesq approximation
The main emphasis of the current study is to analyze the novel feature of the quadratic convective and nonlinear radiative flow of MHD hybrid nanoliquid (CuAl2O3H2O) in an annulus with sensitivity analysis. The significance of exponential space-related heat source, movement of annuli and a new radiation parameter corresponding to an asymptotic nature are also comprehended in the existing study. The dimensionless governing nonlinear equations are treated numerically by employing shooting technique. Impact of effective parameters on the flow and heat transport features has been scrutinized. The optimization procedure is implemented to analyze the influence of three effective parameters (1.5?Rf?5.5,1?QE?3and1%??Cu?3%) on skin friction and Nusselt number by utilizing response surface methodology and sensitivity analysis. The obtained results portray that the nonlinear convection parameter is more favorable for the skin friction coefficient. Further, a comparison of sensitivity depicts that the skin friction coefficient is more sensitive to Rf and QE, whereas Nusselt number is more sensitive to ?Cu. 2020, Akadiai Kiad Budapest, Hungary. -
Sensitivity analysis of Marangoni convection in TiO2EG nanoliquid with nanoparticle aggregation and temperature-dependent surface tension
The sensitivity analysis of the magnetohydrodynamic thermal Marangoni convection of ethylene glycol (EG)-based titania (TiO2) nanoliquid is carried out by considering the effect of nanoparticle aggregation. The rate of heat transfer is explored by utilizing response surface methodology and estimating the sensitivity of the heat transfer rate toward the effective parameters: radiation parameter (1 ? R ? 3), magnetic parameter (1 ? M ? 3) and nanoparticle volume fraction (1 % ? ?? 5 %). The heat transfer phenomenon is scrutinized with thermal radiation and variable temperature at the surface. The effective thermal conductivity and viscosity with aggregation are modeled by using the MaxwellBruggeman and KriegerDougherty models. The governing equations are solved by using the apposite similarity transformations. It is found that when the effect of aggregation is considered, the velocity profile is lower. A positive sensitivity of the Nusselt number toward thermal radiation is observed. Further, a negative sensitivity of the heat transfer rate is observed toward the magnetic field and nanoparticle volume fraction. 2020, Akadiai Kiad Budapest, Hungary.