Semantic Network Analysis For Operating System Privacy And Security Using Twitter Data
Download Semantic Network Analysis For Operating System Privacy And Security Using Twitter Data PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Semantic Network Analysis For Operating System Privacy And Security Using Twitter Data book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Semantic Network Analysis for Operating System Privacy and Security Using Twitter Data
As today's technologies are rapidly advancing, privacy and security issues have become one of the most significant concerns in digital communication. Thus, it is important to understand and draw a conceptual view that relies on how people perceive privacy and security in this current era of dynamic digital proliferation. This research aims to analyze and observe what people perceive about the privacy and security of online merchants, online social media, and other digital media. This research analyzes user interactions on one of the most widely used social media websites, Twitter. Primary data, including over 6 million tweets over twenty-five months was collected and analyzed to draw a conclusion. The study extracts meaningful data to aid in determining users' perception of privacy and security in the digital world based on personal experiences and encounters with privacy and security issues. This research focused on privacy and security issues posed by Twitter as a popular social media platform. In the initial analysis, we recorded the frequency of use of keywords in tweets. As a second step, we performed cleaning the tweets (data), all numbers, symbols, and other non-word text are filtered and removed. The research conducted further discourse analysis to determine how these words were emerging and correlating using TextRank, clustering and topic modeling algorithms. Furthermore, we classified sentiment of Twitter data by exhibiting results of machine learning using different algorithms. We tested three models to understand performance against the Naïve Bayes model. AdaBoost, Decision Tree, and Random Forest all underperformed in accuracy. Consequently, we developed a multilayer perceptron (MLP) model that would use one hidden layer. MLP was trained on 10 epochs and returned an accuracy of 83% on test data. This surpassed the Naïve Bayes model and results in high precision for neutral and positive tweets. MLP was one of the best algorithms, due to its feedforward artificial neural network that produced a series of outputs from a set of inputs. Although this algorithm is time consuming compared to the listing method, it can lead to relatively effective estimation. The tweets we examined are extracted and pre-processed and then categorized in neutral, negative, and positive sentiments. By applying the chosen methodology, the study was able to identify the most effective operating systems under study (i.e. Mac, iOS, Windows, and Android) in terms of privacy and security according to the sentiments of social media users. The approach will help us in simultaneously assessing the competitive intelligence of the Twitter data and the challenges in the form of privacy and security of the user content and their contextual information. The findings of the empirical research of the sentiment analysis shows that users are more concerned about the privacy of the iOS and Android compared to Mac and Windows. With a fully trained model, we made predictions on tweets including operating systems and the keywords "security" and "privacy". The selected operating systems were Mac, iOS, Windows, and Android. The results show that most tweets on these topics are positive except for iOS's privacy and Android's privacy, which both indicate a higher percentage of neutral and negative tweets. Mac's security showed the highest rate of postivie sentiment at 81.8% of tweets being categorized as positive.
Analyzing and Securing Social Networks
Analyzing and Securing Social Networks focuses on the two major technologies that have been developed for online social networks (OSNs): (i) data mining technologies for analyzing these networks and extracting useful information such as location, demographics, and sentiments of the participants of the network, and (ii) security and privacy technolo
Cloud Security
This comprehensive work surveys the challenges, the best practices in the industry, and the latest developments and technologies. It covers the fundamentals of cloud computing, including deployment models, service models, and the benefits of cloud computing, followed by critical aspects of cloud security, including risk management, threat analysis, data protection, identity and access management, and compliance. Cloud Security explores the latest security technologies, such as encryption, multi‐factor authentication, and intrusion detection and prevention systems, and their roles in securing the cloud environment. Features: Introduces a user-centric measure of cyber security and provides a comparative study on different methodologies used for cyber security Offers real-world case studies and hands-on exercises to give a practical understanding of cloud security Includes the legal and ethical issues, including the impact of international regulations on cloud security Covers fully automated run-time security and vulnerability management Discusses related concepts to provide context, such as Cyber Crime, Password Authentication, Smart Phone Security with examples This book is aimed at postgraduate students, professionals, and academic researchers working in the fields of computer science and cloud computing.