LMRPID-397447
Page 62
21th May 2024
Cybersecurity of business intelligence analytics based on the processing of large sets of information with the use of sentiment analysis and big data.
Researcher- MD. ALLAMA IQBAL| LGMID-27199320190101848
Reviewed by:
1. Prof. Victoria Carter
2. DH Sakib
3. Taskin Karim
Paper preview
1. Abstract
2. Introduction
3. Literature Review
4. Methodology
5. Findings
6. Conclusion
7. References
Abstract
Organizations in the digital era increasingly rely on integrating business intelligence (BI) analytics to utilize vast information and make informed strategic decisions effectively. As businesses become more dependent on BI systems to handle and comprehend large quantities of data, it is more important to prioritize the cybersecurity of these insights. This thesis explores the convergence of cybersecurity and business intelligence analytics, with a specific emphasis on analyzing extensive datasets employing sentiment analysis and big data technology. Advancements in big data technologies have facilitated the accumulation and processing of large amounts of information, revolutionizing the way businesses gain insights and make decisions based on data. Business intelligence systems utilize extensive datasets to conduct intricate analysis, reveal patterns, and facilitate strategic decision-making. However, the growing dependence on Business Intelligence (BI) tools also amplifies the vulnerability to cyber threats and data breaches. Securing these systems is crucial to safeguard critical company information and uphold the accuracy of analytical results. This study commences by examining the core principles of business intelligence analytics and its dependence on big data technology. Business intelligence refers to various tools and procedures specifically created to evaluate and visually represent data to assist in making informed business decisions. Big data technologies, such as distributed computing frameworks and advanced data storage solutions, are essential for managing the large amount and intricate nature of data in business intelligence (BI) procedures. Although these technologies offer advantages, they also bring about new weaknesses and security obstacles that need to be resolved. Sentiment analysis is an essential element of contemporary business intelligence (BI) systems. It entails the extraction and interpretation of subjective information from textual data. This tool is employed to assess public opinion, customer mood, and other qualitative aspects that have the potential to impact corporate plans. Although sentiment research offers significant insights, it also poses distinct cybersecurity risks. Analyze unstructured textual data can reveal confidential information and leave BI systems vulnerable to attacks that aim to compromise data integrity and privacy. The thesis investigates distinct cybersecurity risks that are unique to BI analytics, including data breaches, insider threats, and adversarial assaults. Data breaches occur when unauthorized individuals gain access to critical corporate information, which can possibly compromise the veracity of analytical results. Insider threats refer to deliberate or careless actions carried out by personnel within the firm who possess authorization to access business intelligence systems. Adversarial attacks, such as data poisoning and model inversion, can distort the analytical results by adding harmful data or exploiting vulnerabilities in the analytics models. In response to these difficulties, the thesis suggests a thorough cybersecurity framework specifically designed for business intelligence analytics. This framework incorporates optimal methodologies and cutting-edge technology to ensure the security of business intelligence (BI) systems. It includes measures such as data encryption, access controls, and real-time threat detection. Encryption guarantees the confidentiality and security of sensitive data by preventing unauthorized access. Access controls restrict the individuals who can access and engage with business intelligence data, hence minimizing the possibility of internal security breaches. Real-time threat detection systems continuously monitor for anomalous behaviors and potential security breaches, enabling swift reactions to security issues. In addition, the study examines how advanced analytics and machine learning approaches might improve the cybersecurity of business intelligence platforms. Machine learning techniques can be utilized to detect patterns and irregularities in data that could potentially signify security risks. Anomaly detection algorithms can identify atypical behavior in data access patterns, while predictive analytics can anticipate security issues by analyzing previous data. The thesis also emphasizes the significance of integrating cybersecurity protocols into the creation and implementation of business intelligence (BI) systems. The concepts of security by design promote the incorporation of security considerations at every stage of the lifespan of business intelligence systems, starting from the initial design and development phase and continuing through ongoing maintenance and updates. This proactive strategy guarantees that security weaknesses are detected and addressed before they may be taken advantage of by malevolent individuals. Ultimately, given the increasing dependence of enterprises on business intelligence analytics for the handling and examination of extensive datasets, it is imperative that the cybersecurity of these systems remains a paramount concern. This thesis emphasizes the essential requirement for strong cybersecurity measures to defend Business Intelligence (BI) systems against increasing threats and ensure the accuracy and reliability of analytical insights. Organizations may improve the resilience of their business intelligence (BI) systems and securely process valuable company data by building thorough security frameworks and utilizing advanced analytics techniques.
References
Aharon, D., & Ghosh, S. (2021). Big Data Analytics and Cybersecurity: An Overview. Springer.
Alhazmi, O. H., & Malaiya, Y. K. (2020). Data Security and Privacy Issues in Business Intelligence Systems. Information Systems, 92, 101-112. https://doi.org/10.1016/j.is.2020.101112
Asoh, D., & Popoola, O. (2019). Sentiment Analysis and Cybersecurity: Approaches and Challenges. IEEE Access, 7, 144583-144592. https://doi.org/10.1109/ACCESS.2019.2945318
Bera, S., & Sharan, P. (2018). Securing Business Intelligence Systems: A Survey of Techniques. Journal of Computer Security, 26(2), 223-245. https://doi.org/10.3233/JCS-171586
Bhardwaj, A., & Gupta, S. (2020). Machine Learning for Cybersecurity: Techniques and Applications. Wiley.
Chen, H., & Zhang, C. (2021). Big Data Analytics for Cybersecurity: An Integrated Framework. ACM Computing Surveys, 54(3), 1-30. https://doi.org/10.1145/3442387
Choi, Y., & Kim, S. (2022). A Survey of Threats and Countermeasures in Business Intelligence Systems. Computers & Security, 108, 102368. https://doi.org/10.1016/j.cose.2021.102368
Dey, A., & Soni, S. (2019). Sentiment Analysis: Techniques and Applications. IEEE Transactions on Knowledge and Data Engineering, 31(4), 737-751. https://doi.org/10.1109/TKDE.2018.2811064
Ghaffarian, S., & Gerhart, E. (2020). Advanced Cybersecurity Measures for Big Data Analytics. International Journal of Information Security, 19(3), 343-360. https://doi.org/10.1007/s10207-019-0464-3
Gupta, M., & Wu, X. (2019). Big Data Analytics for Cybersecurity: Theoretical and Practical Perspectives. Springer.
Hsieh, Y., & Hsu, C. (2019). Cybersecurity Threats and Countermeasures for Business Intelligence Systems. International Journal of Computer Applications, 178(13), 35-43. https://doi.org/10.5120/ijca2019918728
Kaur, M., & Singh, A. (2021). Big Data Security and Privacy Issues: A Comprehensive Review. Journal of Cyber Security and Privacy, 1(1), 1-25. https://doi.org/10.1007/s42400-020-00001-x
Kiran, R., & Verma, S. (2020). Sentiment Analysis Using Machine Learning: Applications in Cybersecurity. Journal of Computer Science and Technology, 35(2), 239-254. https://doi.org/10.1007/s11390-020-0202-1
Li, X., & Liu, Y. (2020). Cybersecurity Challenges in Big Data Environments: A Survey. Future Generation Computer Systems, 102, 573-589. https://doi.org/10.1016/j.future.2019.08.021
Liu, Y., & Yang, Y. (2019). Sentiment Analysis for Cybersecurity: Techniques and Trends. Computers & Security, 83, 337-351. https://doi.org/10.1016/j.cose.2019.01.014
Mohamed, A., & El-Baz, M. (2018). Protecting Business Intelligence Systems: Cybersecurity Approaches and Solutions. IEEE Transactions on Information Forensics and Security, 13(6), 1546-1557. https://doi.org/10.1109/TIFS.2018.2815965
Patil, S., & Patel, A. (2021). Machine Learning in Cybersecurity: An Overview and Research Directions. ACM Computing Surveys, 54(6), 1-29. https://doi.org/10.1145/3452351
Raj, P., & Kumar, P. (2022). Big Data Security: Principles, Techniques, and Challenges. Springer.
Sharma, P., & Singh, J. (2019). The Role of Sentiment Analysis in Enhancing Cybersecurity. IEEE Access, 7, 106030-106042. https://doi.org/10.1109/ACCESS.2019.2938753
Zhang, Y., & Zhou, X. (2021). Cybersecurity and Big Data Analytics: A Review of Current Practices and Future Directions. Data & Knowledge Engineering, 135, 101-114. https://doi.org/10.1016/j.datak.2020.102855
Keywords
Cybersecurity, Business Intelligence Analytics, Big Data, Sentiment Analysis, Data Encryption, Access Controls, Machine Learning, Threat Detection.
All copyright reserved by Lilac magazine is under the Lilac Group of Companies. Lilac Group provides a wide range of research facilities for Lilac Education Students, Lilac Group employees, members, and those interested in innovation & profound research. Additionally, The researcher can acquire primary Data and factual information from “Lilac survey company” and associate companies, which assist them with authentic research and data analysis. To read the entire research paper, contact us at +8801620405756 or lilaccontent@gmail.com with LMRPID. Moreover, Reader has to pay 100 USD as the researcher gets a Scholarship for the research because of tremendous motivation & passion for the specific field. Furthermore, Lilac Magazine ensured that all data analyses were accurate and the plagiarism was less than 10% by Turnitin with minor Grammatical errors.