As data grow rapidly on social media by users' contributions, specially with the recent coronavirus pandemic, the need to acquire knowledge of their behaviors is in high demand. The opinions behind posts on the pandemic are the scope of the tested dataset in this study. Finding the most suitable classification algorithms for this kind of data is challenging. Within this context, models of deep learning for sentiment analysis can introduce detailed representation capabilities and enhanced performance compared to existing feature-based techniques. In this paper, we focus on enhancing the performance of sentiment classification using a customized deep learning model with an advanced word embedding technique and create a long short-term memory (LSTM) network. Furthermore, we propose an ensemble model that combines our baseline classifier with other state-of-the-art classifiers used for sentiment analysis. The contributions of this paper are twofold. (1) We establish a robust framework based on word embedding and an LSTM network that learns the contextual relations among words and understands unseen or rare words in relatively emerging situations such as the coronavirus pandemic by recognizing suffixes and prefixes from training data. (2) We capture and utilize the significant differences in state-of-the-art methods by proposing a hybrid ensemble model for sentiment analysis. We conduct several experiments using our own Twitter coronavirus hashtag dataset as well as public review datasets from Amazon and Yelp. For concluding results, a statistical study is carried out indicating that the performance of these proposed models surpasses other models in terms of classification accuracy.

/pdf/improving-sentiment-analysis-for-social-media-applications-vgjvw90700.pdf

Improving Sentiment Analysis for Social Media Applications Using an Ensemble Deep Learning Language Model.

Maintaining software systems is getting more complex and difficult task. Code clone is one of the factors that make software maintenance more difficult. A code clone is a code portion in source files that is identical or similar to another. If some faults are found in a code clone, it is necessary to correct the faults in its all code clones. We have developed a maintenance support environment, Gemini, which provides the user with the useful functions to analyze the code clones and modify them. However, through case studies, several problems were reported. That is, the clones provided by Gemini were not appropriate to merge into one module. In this paper, we intend to extend the functionality of Gemini to cope with the problems. Finally, we apply the extended Gemini to several software and evaluate the applicability of the new functions.

On software maintenance process improvement based on code clone analysis

This paper explains the feasibility of blockchain technology in food organization. The technology of BCT helps the organizations to achieve integrity among peer-to-peer nodes, such as maintaining proof of work, reducing intermediaries, traceability, etc. It can be applied in the BCT at different levels of supply chain management processes. This empirical study was conducted with the help of the primary data. The data was collected from food industry managers who have knowledge about the BCT in the process of supply chain management. The questionnaire was prepared based on the different supply chain activities like procurement, pre-processing, logistics, warehousing, inventory management, distribution, retailing, processing, and marketing activities. Based on the literature and data analysis, the BCT had the greatest advantages including cost reduction, traceability, time-saving, immutability, authentication, and proof of work. The major weaknesses are associated with present employees having a lack of knowledge, limited scalability, complexity in usage, and high initial cost. KEywoRdS Blockchain Technology, Food Sector, Supply Chain Management

https://www.igi-global.com/ViewTitle.aspx?TitleId=290014&isxn=9781683180265

Blockchain Technology in the Food Supply Chain: Empirical Analysis

Enhanced Fuzzy Logic Zone Stable Election Protocol for Cluster Head Election (E-FLZSEPFCH) and Multipath Routing in wireless sensor networks

The purposes are to improve the accuracy of inventory demand forecast, balance the indexes of enterprises, and reduce the costs of human, material and financial resources of enterprises and suppliers, thus reducing the supply chain costs and meeting the actual needs of enterprises. In terms of training a large amount of data, deep learning is better than traditional machine learning. The sales demand time series data and the previous material demand time series data are input and trained by back propagation (BP) neural network, and then the material demand value is output. Therefore, the historical data of sales demand forecast and material information are input, and the model is established by BP neural network, which not only takes into account the decisive factor of sales demand forecast, but also considers the material consumption, achieving more accurate forecast. The material demand budget of enterprises is analyzed and a material forecast demand model based on deep learning algorithm is proposed. The model uses a neural network to input the sales demand forecast data, material inventory information and material attribute information into the model, and then the model is trained by the training set in accordance with the error back propagation algorithm. Finally, the training effect of the model is tested by the test set. The results show that when the independent variables include sales demand forecast, material consumption forecast and material attribute information, the forecast error of both models is lower and the effect is better, compared with the material consumption data only as an independent variable. The forecast method based on neural network proposed increases the lead time of the forecast, give the supplier a longer time to prepare goods, and reduce the shortage or surplus of supply caused by the short lead time. Therefore, the material demand forecast model based on convolution neural network (CNN) algorithm provides an important reference for the enterprises, helps them improve their work efficiency and promotes the development of enterprises. This model achieves a great improvement on the accuracy of material demand forecast, and has a certain guiding significance in relevant theory and practice.

CNN model optimization and intelligent balance model for material demand forecast

Stock Market Prediction system provides an overview for the business to gain high profit in the share market. The rise of a large volume of data related to the financial market makes it difficult to analyze and predict the stock market effectively. This research focuses on to improve the effectiveness of the stock market prediction based on the Kalman filter. The financial data from Yahoo and Twitter are used to forecast the stock market values. The technical indices are extracted from the data to investigate the stock values. Twitter data related to the company’s stock value are extracted and analyzed the sentiment. Next, the Kalman filter is applied to reduce the errors from data. Kalman filter is used here to smoothen the noise created by sudden peaks in the data or to filter out the abnormal incidents in the data for training. Hence, the classification algorithm is not trained with irrelevant features value. The Accelerated Gradient Long-Short Term Memory (AG-LSTM) is used for stock market prediction. The output of the method is analyzed with and without Kalman filter and this showed that the Kalman filter technique increased the performance of the stock market prediction. In Microsoft stock data, the accuracy of the proposed AG-LSTM with Kalman filter model has achieved accuracy of 90.42%, while existing AG-LSTM model has achieved 57.53%.

An Efficient Stock Market Prediction Method Based on Kalman Filter

\n Wireless Sensor Network (WSN) have transformed over recent years with incredible development in design of smart real time applications. In spite of countless potential, it poses numerous design issues like fault tolerant communication, low latency, scalability, transmission media and coverage problems. One of the foremost design issues of WSN is to detect the run time fault because it is unaware of internal operation of the sensor node. As a result, valuable sensed information is unable to reach its destination and performance start degrading throughout the routing period of the network. To address this issue, the proposed mechanism design a novel Pre-fault detection mechanism based on fuzzy rule based mechanism for multilevel transmission in distributed sensor networks. Many researchers have been focused on fault detection mechanisms without considering the dynamic behavior status of sensor node. In this proposed mechanism the Fuzzy decision rule set is identified to take routing decisions based on fuzzy fault count status. This mechanism helps to recognize the fault in advance and a routing decision has been taken in order to save energy as well as minimize delay. On the basis of node fault status data transmission rate is finalized in order to avoid more energy depletion. The experimented simulations results prove the accuracy of the proposed mechanism. The results demonstrate that the proposed mechanism performed well on judgment evaluation metrics such as energy dissipation ratio, packet drop rate and communication delay.

/pdf/energy-attentive-and-pre-fault-recognize-mechanism-for-jv7ichlfck.pdf

Energy Attentive and Pre-Fault Recognize Mechanism for Distributed Wireless Sensor Network Using Fuzzy Logic Approach

Task Pattern Identification and Scheduling Using Equal Opportunity Model for Minimization of Makespan and Task Diversity in Cloud Computing

Cloud computing has gained status of red carpet in recent years. The only rationale behind achieving this huge applause for cloud is its accessibility in requisite personalized form without harming its effectiveness. Efficiency of cloud computing has became the outcome of scheduling algorithms applied to maintained its potential, high end hardware involved and networks that support this huge infrastructure. This article is focusing on tasks scheduling in cloud computing particularly when tasks are of independent nature. Various techniques are available for minimizing scheduling time of tasks still optimization has scope in this regards. Task scheduling is usually considered as NP-hard problem and meta-heuristic algorithms are treated as one of the best solution in dealing with this kind of problem. There are plenty of meta-heuristic techniques presented as Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Language Championship Algorithm (LCA), Artificial Bee Colony (ABC) to mentioned a few. Comprehensive study and comparative analysis of these diverse types of algorithm in the region of user’s view and service provider’s view is articulated here. This article is focusing on tasks scheduling in cloud computing typically when tasks are of independent nature.

A Review on Meta-heuristic Independent Task Scheduling Algorithms in Cloud Computing

In digital era, the provision of streaming data and its storage has taken wider forms where data can be in structure, semi-structured and unstructured forms. As data is increasing the storage capacity also has to be increased, and the processing of data from such huge storage may be time consuming. And it is tricky to handle and process such data via conventional software and database procedures, which lead to the research toward big data analytics. It aims at handling of massive data storage with fast processing techniques and to help companies in optimizing business, advancement of operations, making more intelligent, and fast decisions. Hence Big data analytics is an important field that derives insights from the data and prediction system is one of the famous applications of it. It takes the historical data and analyses, and then it forecasts the past and future situations basing on identified hidden patterns of data considered. The analytics can be categorized into different forms namely Business Analytics (BA) and Predictive Analytics (PA). The inclusion of skills, technologies, applications, and processes with statistical techniques adopted by organizations for their data available to impel business planning is referred to as business analytics. The forecasting approach to foresee upcoming events and trends known as Predictive Analytics, which identifies the hidden patterns and determines what is likely to happen from the historical information available using statistical and mathematical models. To enhance the forecasting process, an opinion mining can also be included. Nowadays sentiment of the people also considered to improve the accuracy level of anticipation. Effecting factors should be considered and clearly analyzed to construct accurate model so as to supply most relevant suggestions. Several researchers proposed various prediction algorithms and methods in order to construct the accuracy improved model and user satisfaction. In this chapter, authors studied various anticipating models and discussed their preference criteria. As a part of that, we studied various important preference factors in stock trend prediction and categorized them based on effecting factors. This chapter reports prospect directions in prediction models and compiling an easy guide reference list to help out the researchers.

An Amalgamation of Big Data Analytics with Tweet Feeds for Stock Market Trend Anticipating Systems: A Review

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

M. Nirupama Bhat

Author Tools

Chat about Author