Browse Items (14421 total)
Sort by:
-
Twitter Sentiment Analysis and Emotion Detection Using NLTK and TextBlob
On an average, approximately 7000 tweets are communicated each second and in total it piles up to around 300 billion tweets every year. Society are free to contribute their opinions on public platform and hence it acts as a reliable interface to assess society ongoing viewpoint and attitude over any matter or event. Consumers very often make use of social media to exchange their views about anything. Business may get domain for enhancement and smooth interpretation of the behavior of people regarding various facts through opinion mining. Thus to carry out this mining of opinions on social media interface, textual categorization with language analysis is of great help. With the help of NLP token tool, phrases can be divided into various word series after dropping stop phrases. Larger tweets tokenizing and classifying into distinct labels is a concern. Thus, the main objective of this framework is to process the tweets based on specific keywords given by user, categorize these phrases into negative, positive and neutral ones. TextBlob module assists users and developers to interpret user sentiments about a news. This research tries to give suggestion a textual opinion assessment on social media samples utilizing the NLTK and TextBlob modules. 2023 IEEE. -
Twitter Sentiment Analysis Based on Neural Network Techniques
Our whole world is changing everyday due to the present pace of innovation. One such innovation was the Internet which has become a vital part of our lives and is being utilized everywhere. With the increasing demand to connected and relevant, we can see a rapid increase in the number of different social networking sites, where people shape and voice their opinions regarding daily issues. Aggregating and analysing these opinions regarding buying products and services, news, and so on are vital for todays businesses. Sentiment analysis otherwise called opinion mining is the task to detect the sentiment behind an opinion. Today, analysing the sentiment of different topics like products, services, movies, daily social issues has become very important for businesses as it helps them understand their users. Twitter is the most popular microblogging platform where users put voice to their opinions. Sentiment analysis of Twitter data is a field that has gained a lot of interest over the past decade. This requires breaking up tweets to detect the sentiment of the user. This paper delves into various classification techniques to analyse Twitter data and get their sentiments. Here, different features like unigrams and bigrams are also extracted to compare the accuracies of the techniques. Additionally, different features are represented in dense and sparse vector representation where sparse vector representation is divided into presence and frequency feature type which are also used to do the same. This paper compares the accuracies of Nae Bayes, decision tree, SVM, multilayer perceptron (MLP), recurrent neural network (RNN), convolutional neural network (CNN), and their validation accuracies ranging from 67.88 to 84.06 for different classification techniques and neural network techniques. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Twitter sentiment analysis on online food services based on elephant herd optimization with hybrid deep learning technique
Twitter is a social media stage, making it a valuable resource for learning about peoples opinions, feelings, and thoughts. For this reason, experts came up with methods to analyse the tone of tweets and determine whether they were favourable or negative. This article aims to assist businesses, and especially app-based meal delivery businesses, in conducting competitive research on social broadcasting and transforming social broadcasting data into data production for decision-makers. In this analysis, we compared Swiggy, Zomato, and UberEats. Customers tweets about all these brands are obtained using R-Studio, and a deep learning-based sentiment examination approach is functional on the retrieved tweets. The pseudo-inverse learning autoencoder is able to provide feature extraction in the form of an analytic solution after pre-processing, without resorting to many iterations. In this research, we suggest framework for combining the Convolutional Neural Network (CNN) and Bi-directional Long Short Term Memory (Bi-LSTM) models. ConvBiLSTM is used, which is a word embedding model that uses numerical values to represent tweets. The CNN layer takes the feature implanting as input and outputs lower features. In this instance, elephant herd optimization is used to fine-tune the Bi-LSTM weights. Among the three firms, the results indicate that Zomato got the most positive feedback (29%), followed by Swiggy (26%), and UberEats (25%). Zomato also had fewer bad reviews than Swiggy and UberEats, with only 11% of users having a poor experience. In addition, tweets were evaluated for unfavourable views against all three meal delivery services, and suggestions for improvement were offered. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023. -
Twitter Sentiment Analysis using Machine Learning Techniques: A Case Study of ChatGPT
ChatGPT is a powerful AI bot developed by OpenAI. This technology has the potential to generate a humanlike response. ChatGPT is a pre-trained system capable of generating chat and understanding human speech. This paper identified the responses of ChatGPT users through related tweets with the help of natural language processing and machine learning techniques. This paper uses textBlob, VADER and human annotation to find the sentiment of each tweet; countvectorizer is used for feature extraction and different machine learning algorithms to classify them into different classes. LeXmo is used to identify the various sentiment analyses, and it is observed that positive and trust emotions are higher than other sentiments. SVM with 10-fold cross-validation shows better results than other techniques. 2023 IEEE. -
Twitter sentiment for analysing different types of crimes
Online social media like a twitter play a vital role as it helps to track the Spatialoral on social media data with respect crime rate. With the very fast evolving of users in social media, sentimental analysis has become an excellent source of information in decision making. Twitter is one of the most popular social networking site for communication and a primary source of information. More than 150 million users publish above 500 million 140 character TWEETS each day. Tweets have become a basis for product recommendation using sentimental analysis. This paper explains the approach for analyzing the sentiments of the users about a particular crime event tweets posted by the active users. The results so obtained will let you know about the change in the public opinion about the crime events whether it's positive or negative and to find out emotions on different types of crimes. 2018 IEEE. -
Two dimensional fuzzy context-free languages and tiling patterns
Fuzzy context-free languages are powerful compared to fuzzy regular languages as they are generated by fuzzy context-free grammars and fuzzy pushdown automata, which follow an enhanced computational mechanism. A two dimensional language (picture language) is a collection of two dimensional words, which are a rectangular array of symbols made up of finite alphabets. Two dimensional automata can recognize two dimensional languages that could not be recognized by one dimensional automata. In this paper, we introduce two dimensional fuzzy context-free languages generated by the two dimensional fuzzy context-free grammars and accepted by the two dimensional fuzzy pushdown automata in order to deal with the vagueness that arises in two dimensional context-free languages. We can construct a two dimensional fuzzy context free grammar from the given two dimensional fuzzy pushdown automata and vice versa. In addition, we prove that two dimensional fuzzy context-free languages are closed under union, column concatenation, column star, homomorphism, inverse homomorphism, reflection about right-most vertical, reflection about base, conjugation and half-turn and also show that two dimensional fuzzy context-free languages are not closed under matrix homomorphism, quarter-turn and transpose. Further, we have given the applications and the uses of closure properties in the formation of tiling patterns. 2024 Elsevier B.V. -
Two distance forcing number of a graph
Motivated from the graph parameters namely zero forcing number, k-forcing number and the connected k-forcing number, in this article, we introduce a new parameter known as the 2-distance forcing number. Assume that each vertex of a graph G = (V (G), E(G)) is colored as either white or black. Consider the set Z2d of black colored vertices of the graph G. The color change rule changes the color of a white vertex v to black if the white vertex v is the only 2-distance white neighbor of a black vertex u. The set Z2d is called a two distance forcing set of G if all vertices of the graph G will be turned black after limited applications of the color change rule. The 2-distance forcing number of G, denoted by Z2d (G), is the minimum of | Z2d | over all 2-distance forcing sets Z2d ? V (G). This manuscript is intended to study the 2-distance forcing number of some graphs. We find the exact value of the 2-distance forcing number of graphs such as the pineapple graph, gear graph, jelly fish graph, helm graph, sunflower graph, comet graph and the n-pan graph. 2020 the author(s). -
Two inventory models for growing items under different payment policies with deterioration
Industries of growing items show an upward trend in the production as well as in consumption. Poultry and livestock are good examples of growing items which are both deteriorating and ameliorating in nature. In this study apart from these specific features of growing items, one of the real-world business policies, permission of delay in payment is also considered. Present paper proposed two inventory models, one with the permission of delay in payment and another without it. Concavity of the profit functions with respect to decision variables are discussed analytically for both the models. Solution procedure and numerical examples are provided in order to get the managerial insights. The numerical analysis growth in weight is approximated by Richard's growth function. The numerical analysis predicts that net profit and the initial purchase quantity both increases under the permissible delay payment policy compared to without it. Sensitivity analysis provides important managerial insights. Copyright 2022 Inderscience Enterprises Ltd. -
Two-dimensional chromium telluride-coated 3D-printed architectures for energy harvesting
Rapid development of industries, urbanization, and technological advancements have increased demand for sustainable and cost-effective alternative energy sources. In this work, a self-powered flexible 3D-printed triboelectric nanogenerator coated with 2D chromium telluride (Cr2Te3) (3D-TENG) is presented as an innovative energy harvesting approach from pressure and temperature. The optimized flexible 3D-printed hexagonal structures with coatings show varying specific yield strength and porosity. The 3D-TENGs achieved a maximum output voltage of ?39 V under periodic impacts of ~0.8 kPa and their performance further increased (?45 V) in the presence of varied temperatures. The outstanding results and flexibility of the 3D-TENG devices highlight their potential in self-powered energy harvesting from external heat, magnetic fields, and body weight. Density functional theory (DFT) calculations further explained the interaction between 2D Cr2Te3 and the polymer surface under external impact. Therefore, we believe that our findings illustrate the potential of integrating 2D materials with 3D-printed architectures to enhance the efficiency and adaptability of flexible, lightweight, low-cost, and eco-friendly TENG devices for industrial applications. 2025 The Royal Society of Chemistry. -
Two-dimensional Ti3C2 MXene for photocatalytic hydrogen production: A review
This study focuses on the utilization of two-dimensional Ti3C2 MXene as a catalyst for photocatalytic hydrogen production. MXenes, a class of transition metal carbides/nitrides, exhibit exceptional properties conducive to enhancing photocatalytic reactions. This research explores the performance of Ti3C2 MXene as a cocatalyst in photocatalytic systems, aiming to improve charge separation, inhibit recombination, and facilitate efficient hydrogen evolution from water under light irradiation. The synthesis methods, catalyst-loading strategies, and overall photocatalytic mechanisms are investigated, shedding light on the potential of Ti3C2 MXene as a promising material for advancing hydrogen production through sustainable means. 2023 Korean Chemical Society, Seoul & Wiley-VCH GmbH. -
Two-dimensional Ti3C2Tx MXenes as a catalyst support for the synthesis of 1,4-disubstituted-1,2,3-triazoles via azide-nitroalkene oxidative cycloaddition
Two-dimensional transition metal carbides/nitrides: MXenes have become a prime choice for researchers to exploit their outstanding properties for various applications in different fields majorly including energy, health and environment. Interestingly, there are no reports of utilizing 2D materials especially MXenes as a catalyst support for organic transformations. In the present study, we have utilized 2D Ti3C2Tx MXenes as a catalyst support for the synthesis of 1,4-disubstituted-1,2,3-triazoles via azide-nitroalkene cycloaddition for the first time. Reusability of Ti3C2Tx MXene catalyst up to five cycles without the loss of catalytic activity with appreciable yields of the product is the noteworthy feature of the present protocol. The synthesized 1,2,3-triazole derivatives possessing long alkyl chain upto fourteen carbon atoms on terminal nitrogen in triazole ring could become a good precursors to give a liquid crystalline properties beyond its biological properties. Nontoxic catalyst, catalyst reusability, broad substrate scope, and good yield are some of the salient features of the present protocol. 2023 Elsevier B.V. -
Two-phase flow of dusty Casson fluid with Cattaneo-Christov heat flux and heat source past a cone, wedge and plate
This article addresses the boundary layer flow and heat transfer in Casson fluid submerged with dust particles over three different geometries (vertical cone, wedge and plate). The aspects of Cattaneo-Christov heat flux and exponential space-based heat source (ESHS) are also accounted. At first, the partial differential equations are transformed into a set of ordinary differential equations via appropriate similarity transformations. Resulting equations are solved via shooting method coupled with the Runge-Kutta-Fehlberg-45 integration scheme. The consequences of dimensionless parameters on velocity and temperature fields of both fluid and dust particles phase are analyzed. The rate of increment/decrement in the skin friction as well as the Nusselt number for various values of physical parameters are also estimated via slope of linear regression line using data points. 2018 Trans Tech Publications, Switzerland. -
Two-phase Sakiadis flow of a nanoliquid with nonlinear Boussinesq approximation and Brownian motion past a vertical plate: Koo-Kleinstreuer-Li model
This paper investigates the Sakiadis flow of a Al2O3-H2O nanoliquid with consistently scattered dust particles over a vertical plate. To account for the effect of the Brownian movement, the Koo-Kleinstreuer-Li model is considered. In some thermal systems such as reactor safety areas, and solar collectors, combustion works from moderate to high temperature, making the relationship between the temperature and density nonlinear. To consider this temperature-dependent density, the nonlinear Boussinesq estimation is utilized. The present physical structure, which includes energy and momentum equations, is converted into a system of ordinary, coupled, and nonlinear differential conditions through the help of similarity transformations. By using the finite difference code, the subsequent equations have been numerically solved. The impact on the velocity and the thermal profiles of the nondimensional parameters is visualized through graphs. Both the Nusselt number and friction factor strengthen with ahigher nonlinear thermal parameter in the case of nonlinear Boussinesq approximation compared to the linear Boussinesq case. Growing estimations of nonlinear thermal parameter deteriorate the thermal profile but it boosts the velocity profile of both liquid and dust phases. 2020 Wiley Periodicals LLC -
U.R Ananthamurthy - A man more sinned against than sinning? /
Indian Literature, Vol.59, Issue 6, pp.138-147, ISSN No: 0019-5804. -
UAV Security Analysis Framework
This study presents a framework that allows for various types of checks to detect weaknesses in UAV subsystems. The UAV testing process is automated and allows the operator only to select the types of checks or types of structural and functional characteristics that the operator wants to test. To ensure the possibility of automated verification, implemented databases are used, which include a catalog of structural characteristics, threats, vulnerabilities, and attacks. These catalogs are many-to-many related, and thanks to these links, it is possible to identify threats or vulnerabilities specific to a particular structural characteristic. In essence, such an architecture is a knowledge base based on an ontological model. Thanks to this architecture of the system, it is enough for the operator to determine what types of structural characteristics need to be checked and the system will give him information about the vulnerabilities of the UAV. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
UK-IDS-Machine Learning Based Intrusion Detection System for Unknown Attack Detection
Computer networks have become the major focus for attackers. Hence intrusion detection system plays a significant role in detecting attacks. Many researchers have already focused on the domain of cyber security by developing an efficient framework. However, developing an efficient IDS is still a challenging task because of its effectiveness in determining novel attacks. Hence in the current study, a machine learning based IDS called UK-IDS is proposed by incorporating OC-SVM and a basic SVM model. The aim of the proposed system is to achieve high accuracy and F1 score by detecting novel attacks. The OC-SVM approach identifies the novel attacks by collaborating the clustering and thresholding mechanism. The basic SVM model is to distinguish the type of attack. The experimental study reveals that UK-IDS framework shows good performance in terms of accuracy and F1 score. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Ultra-low loss compact active TM mode pass polarizer using phase change material in silicon waveguide
An active low-loss transverse magnetic (TM) pass polarizer, based on the phase change material (Ge2Sb2Te5), is proposed. The proposed polarizer is based on silicon-on-insulator technology that consists of a silicon waveguide that incorporates a thin layer of Si3N4 placed in-between GST. Enhancing the interaction between light and GST is achieved by strategically placing a double-layer GST adjacent to the slot waveguide. The polarizers tunability, on the other hand, depends on the shift in the refractive index (RI) of GST as it transitions between its crystalline and amorphous phases. By optimizing the structure, the polarizer exhibits negligible loss for both modes in the amorphous phase, and with the change of phase to crystalline, the loss of TE mode is more than 8 dB. In contrast, the loss of TM is less than 0.05 dB with a high ER of 21.82 dB, propagation length of 79.89 m and Figure of merit reaches up to 108 at 1550 nm. Due to the combination of these performance parameters, the suggested active TM pass polarizer is an appealing and effective device for various photonic applications. In addition, the fabrication technique of the proposed active TM pass polarizer is explained. 2024 IOP Publishing Ltd. -
Ultrafast nonreciprocal transmission modulation in metasurfaces with epsilon-near-zero materials
Nonreciprocity refers to the difference in received to transmitted ratio when the source and detector are interchanged [1]. Optical isolator - component which allows transmission in one direction - is a canonical example of a nonreciprocal device. Nonreciprocity can be achieved through three known pathways; (i) materials with asymmetric permittivity or permeability tensors, such as ferrites; (ii) nonlinear light-matter interactions[2-4]; and (iii) time-varying systems[5]. While traditionally nonreciprocal components are quite large in size, nanofabrication of metasurfaces has enabled their miniaturisation to the nanoscale. However, ultrafast nonreciprocal responses at the nanoscale remain still a challenge. Here we design and study metasurface with an epsilon near zero material indium tin oxide (ITO) that enables ultrafast switching of refractive index via Kerr nonlinearity, in order to achieve optical isolation. 2025 IEEE. -
Ultrahigh Power Factors in Ultrawide-Band-Gap GaB3N4and AlB3N4for High-Temperature Thermoelectric Applications
With recent thermoelectric studies concentrating too much on low- and mid-temperature applications, an interesting question is, "are there any materials suitable for high-temperature thermoelectric operations?"To answer this, we have demonstrated in this work the viability of the ternary ultrawide-band-gap materials GaB3N4 and AlB3N4 for high-temperature thermoelectric applications using the first-principles calculation method. Our accurate transport calculations, considering both elastic and inelastic scattering mechanisms, reveal the ultrahigh power factors as high as 1821 ?W m-1 K-2 in GaB3N4 and 1876 ?W m-1 K-2 in AlB3N4 at 2000 K. The power factors are calculated from the Seebeck coefficients and electrical conductivities for both electron and hole carrier concentrations between 1018 and 1021 cm-3. For the figure-of-merit (ZT) calculation, the obtained power factors along with the electronic thermal conductivities determined from the definite Lorenz numbers and the lattice thermal conductivities from the phonon vibrations were used. The calculated ZT values seem to be appreciable for high-temperature applications considering the materials' stability factor and the temperature range within the optimum electron carrier concentration of 1021 cm-3. Although the lattice thermal conductivities are higher, which decrease the values of ZT, considering the ultrahigh power factors instead of the ZT factor could be the right choice for high-temperature thermoelectric applications. -
Ultrasmall cobalt boride-decorated P, K-doped gC3N4 for plasmon-driven degradation of high concentration tetracycline
The widespread contamination of aquatic ecosystems by pharmaceutical pollutants, particularly tetracycline (TC) antibiotics, poses significant environmental risks. gC3N4 is widely studied as a photocatalyst for environmental remediation, yet its practical use remains limited. To overcome these limitations, we developed gC3N4 by co-doping phosphorus (P) and potassium (K), and further decorating with ultrasmall cobalt boride (CoB) nanoparticles. Elemental co-doping with P and K modulates the electronic structure of gC3N4 by narrowing the bandgap, introducing shallow impurity bands, and enhancing charge separation through directional charge redistribution, supported by spectroscopic analysis and DFT simulations. The introduction of plasmonic CoB nanoparticles leads to the formation of Schottky junctions, while also inducing localized surface plasmon resonance (LSPR) that significantly amplifies the photocatalytic activity. CoB/P-K-gC3N4 exhibited a 21-fold increase in TC degradation rate compared to pristine gC3N4, where 84.8 % of 100 ppm TC was degraded using 10 mg of photocatalyst in one hour, achieving high removal activity of 7.1 mgpollutant/gcatalyst/min. The catalyst also demonstrated excellent structural stability and sustained photocatalytic efficiency over multiple reuse cycles. Electrochemical studies showed a higher charge carrier density along with a noticeable decline in charge transfer resistance, while photoluminescence and time-resolved fluorescence analysis confirmed a suppressed electron-hole recombination rate. This study demonstrates the synergistic interplay of co-doping and plasmonic enhancement in advancing next-generation photocatalysts for sustainable water purification. 2025 Elsevier B.V.