The advancement of social networks has facilitated the sharing and spread of news among people over the world. With the growth of these networks and growth of the volume of the news shared daily, the phenomena of fake news become more stronger and widely spread. In this paper, content-social based features for fake news detection model from Twitter data has been proposed. This work aims to analyze content-based features of news content including of linguistic features, writing style features, semantic features and sentiment features along with social-context based features of news diffusion over the social network including user-based features and network-based features to detect fake news from Twitter news posts. With using of unsupervised graph-based clustering approach, no labelled data is required and this make the proposed model more practical to detect online fake news.
The area of Event Detection (ED) has attracted researchers' attention over the last few years because of the wide use of social media. Many studies have examined the problem of ED in various social media platforms, like Twitter, Facebook, YouTube, etc. The ED task for social networks involves many issues, including the processing of huge volumes of data with a high level of noise, data collection and privacy issues, etc. Hence, this article discusses and presents the wide range of challenges encountered in the ED process from unstructured text data for the most popular Social Networks (SNs), such as Facebook and Twitter. The main goal is to aid the researchers to understand the main challenges and to discuss the future directions in the ED area.
O. Nasr Eldin, A. Hussein, S. Kumar, and A. Ashry, Suez Oil Company (SUCO) Abstract Recent advances in computer technology and the proliferation of computers in the workplace have had a big impact on technical decision making and on the day to day work of engineers. In petroleum engineering, we are faced with a variety of complex software, with different functionalities, prices and features. It is quite a challenge to review the options available and to select one which will be the optimum for a significant length of time and provide the company with best tools at the lowest price. This paper presents the philosophy and the methodology involved in the evaluation of software. The compulsions on the part of the suppliers as well as the demands of the customers are discussed. Practical criteria for evaluating software for petroleum engineering applications, evolved through the last decade of experience in several operating companies and with discussions with international suppliers and experts, are presented. The process of evaluation and the criteria and process of selection are described through two real examples, one for reservoir simulation software and the other for well test analysis software, undertaken recently at our company. Detailed tables and check-lists are presented for these two cases which enabled the engineers as well as the management to quickly review the available packages and to decide which one would best meet their needs. A desirable outcome of the process was the fact that we were able to provide the suppliers with a lot of sensible suggestions to improve their products for our benefit. This paper seeks to provide an understanding of the software process lifecycle, from design to sales to usage, in order to allow engineers the necessary insight for evaluating their own given software. The software industry is in such turmoil that these skills are now necessary on a frequent basis for continuous quality improvements which require that engineers find the best solutions to their problems at lowest cost. Introduction Computer software has proliferated because it fills a technical and business need - quick, precise computations, links to other technical processes, efficiency in repeated tasks, fast communication, etc. Computer software is behind all of these roles and is well on the way to acquire additional roles, such as training preservation of human expertise (expert system), intelligent search agents to scan information networks for user-specified information, etc. Form a user perspective, the key attributes of any software application are features and costs. Vendors have made tremendous progress on the former, but are only beginning to address the latter issue. Other issues from the user perspective include support, documentation, timely upgrades, etc. Management views software as a necessary tool for technical work and for designing presentations, but are often frustrated at the high costs, time-consuming computer, maintenance, incompatibility across platforms, rapid changes, intensive training requirements, etc. These problems are real and vendors looking for a competitive advantage must seek solutions as quickly as they can. Vendors seek new customers, increased market share and, above all, profitability. Once a sale is made, vendors rely on annual maintenance fees for expenditures on development and support. The incremental costs for a copy of the package are significant, therefore profitability is crucially dependent on finding new customers. The onus is on the vendors to meet the challenge and balance the customer's needs against their profitability. P. 337^
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.