A SURVEY ON BIG DATA ANALYTICS ON BIG DATA IN SOCIAL MEDIA

A SURVEY ON BIG DATA ANALYTICS ON BIG DATA IN SOCIAL MEDIA

Abstract

Big data is an essential factor that involves social media such as business, education, industries based information, healthcare department, etc. Social media-based big data gives a large amount of data to manipulate the efforts in social media. The function that manages big data analytics through an efficient way of approaches. An efficient manner of prominent social media data enhanced the performance, accuracy of results along with the style of massive data storage function. In this paper, the data of information enables the machine learning technique, natural language processing, and computational intelligence of big data analytics to manages the descriptive analysis of data analytics. The classification of big data in social media ensembles the uncertainty of big data to detriments the challenges of AI, which provides the sentiment analysis of data analytics, modeling of text mining, and computational evolution of big data analytics in social media. The qualitative analysis of big data in social media enumerates the functions of resources of authoritative analysis.

Key Words: Big data, Artificial Intelligence, Computational Intelligence, NLP

1. INTRODUCTION

Nowadays, big data provides an increased number of internet usages that enables through social media. Social media is an integral part of big data to access the bunch of data analytics of different kinds of information under one parameter. Social media is not only used to connect to others, but also used for business, online platforms, and other applications with an effective platform. The massive amount of significant data to be generated the social media platforms to produced the big data and compresses the quality attributes of big data. The implementation of big data analytics enables the internet and web 2.0 technologies (Ghani, Hamid, Hashem, & Ahmed, 2019). The web environment produces B2B organizations and the capability to analyze big data and social media analytics. In a marketing-based business environment, the profitable and remain sustainable operations. An intelligence and active based user engagement permits web participation. To improve business productivity and efficiency along with the shapes and sizes of the social media big data (Sivarajah, Irani, Gupta, & Mahroof, 2019). The significant data preparation enables the optimal machine learning approach for data analytics. Social media relies on the architecture of big data with the estimated layers. The big data analytics enables the text review on data subjectivity and additional features of social media (Jimenez-Marquez, Gonzalez-Carrasco, Lopez-Cuadrado, & Ruiz-Mezcua, 2019). The social media-based business and marketing provides the perception of customer engagement. The entertainment, interaction, and customization with social media activities of the proliferation of brands on user perception with brand-related social media messages and increases explicitly the user classification (Liu, Shin, & Burns, 2019).

The prediction and volatility of user-generated content (UGC) to enable the user-generation. The tweets, blog posts, and Google searches are provides by the uses of sources for the users. The multivariate user-generation provides the growth rate of stock events along with the stock returns, which is volatile and depends upon the marketing events drive. In sentiment analysis, the overall general and particular emotions manage the Supervised text classifiers (Geetha & Kumar, 2019). The crisis firms’ correspondence and public opinion reflects in online World-Of-Mouth (WOM). The search engine and social media establish the vast quantities of secondary data of social media in big data analytics. The strength of online WOMs, the particular increase in strategies of crisis firms. The social media are emerging the communication and essential business marketing with concept deposition structure. The massive user-generated content establishes the content analysis in big data and AI. The decomposition concept enables the extraction of temporal trends and detailed scale of individual insights strategies. The Big Data-oriented approach provides the millions of purchase of consumers and the user-generated products through this field of data analytics. Huawei over five months period, the proliferation of sentiment data analysis through the collection of data with the superior leaders of data analytics (Prabhu, Ashwini, Khan, & Das, 2019). Figure 1 shows the predictive data analytics in social media.

Figure 1 Predictive data analytics in social media

Information and Communication Technology (ICT) enables the process such as economic growth, social purposes of national security of computers, mobile devices, and other applications. The detrimental cyber activities enable the malicious attacks in the machine that confronting the highest priority to make the network intruder and also detects the intrusions (Gunavathi, Priya, & Aarthy, 2019).

The big data-based social media gives them enough information along with the usage of given parameters such as

• Personalization
• Decision making
• Effectiveness of campaign
• Product insight

  Don't use plagiarised sources.Get your custom essay just from $11/page

  GET CUSTOM PAPER

Big data analytics based on the toxic comment classification to ensembles the detection of unwanted messages. The social media-based significant data detriments in accuracy and classified the ANN. This classifier enables the toxicity changes to attains the trends of data analytics (Georgakopoulos, Tasoulis, Vrahatis, & Plagianakos, 2019). The processing of data streams provides a large amount of data with the sentiment mining technique to enriches social media analytics (Islam, Halder, Uddin, & Acharjee, 2019). Social media allows the real-time feedback to the users and gathers the data analytics for qualitative and quantitative analysis for the text mining and sentiment analysis with an effective way of visualization (Mini, Nair, & Jacob, 2019).

1. MACHINE LEARNING AND BIG DATA

Social media becomes the most important platform to access data information through this platform. The machine learning approach enhanced the user experience and promoting their data analytics along with the use of a machine learning approach. The social media platform experienced handling and increased the data analytics content. Machine learning provides an individual subject from the group level statistics of data with the specifications of accuracy, sensitivity, specificity, and area of receives the data. This may lead to the characteristics of enhanced outcomes, diagnosis, and prevention of individual quality of data analytics (Passos et al., 2019). The machine learning approach enables social media with the accessing of big data and its methods. This technique leads the following characteristics such as

• Improved media quality
• Brand enhancement to achieve the target
• Maintaining the security of data analytics
• Handling and automating of data

The big data based on data collection. The integration of data collection effectively has done the process of the machine learning approach. Due to the data collection processing, the challenges to affect the gathering of data, and the quality control process used to enumerates the shortage of data collection (Roh, Heo, & Whang, 2019). Machine learning concerns the service based big data with the sizeable competitive service, which used to predicts the highly efficient situation of systems. The machine learning approach provides high accuracy by decreases the errors, data balance with the trained data information of the lifecycle (Ahmad, Jafar, & Aljoumaa, 2019). The content of modern computing technologies and the machine learning approach used for different societal applications. The improvement of overtime learns with enough data with the highly automated and self-modified data with the minimum intervention of data analytics. The correlation of enumerates the effect of human capability and accurate prediction (Tripathy, Acharya, Kumar, & Chatterjee, 2019).

The contributing factors that make the highly productive with the efforts of collaborative and prominent outlets of substantial quality, and emerging the scenarios with intelligent transportation. The industrial and chemical systems established the one-to-two way of healthcare department (El-Alfy & Mohammed, 2020). The various industries gather the data of consumers; co-workers are used to enables the different pace, format, and volume matters to be detriments the significant factor. This leads to an active organization in the business with the long-time process of data through data mining, statistical approaches of supervised machine learning approaches (Talha, Ali, Shah, Khan, & Iqbal, 2019). The improved machine learning provides large applications such as vast array of high execution performance along with the enhanced response time. From this array concept, the data analytics produced single-cell data and the coherent way of encapsulating capabilities (Yau & Campbell, 2019).

The machine learning technique provides the bulk of nontraditional data with an advanced approach. This gave the input data presentation and generalized the data analytics for future consideration. The high performance of data provides the prediction, feature extraction, and of raw input data. If any complications, the input data to reduced (Jan et al., 2019). In health care systems, social media-based big data provides the flexibility and scalability, privacy, and security along with the prediction of disease and its risks. This machine learning concept allows a considerable large amount of complex health-care data and its offering of risks (Ngiam & Khor, 2019).

III. NATURAL LANGUAGE PROCESSING AND BIG SOCIAL MEDIA DATA

Natural language processing is the process of understanding textual format for human life. The natural language processing enables social media processing and controls the operation of multiple sources and its various forms of languages. The large volume of data to monitored and also provides social media marketing. This method regulates the textual data mining and its corresponding large amount of data sets. This can be integrated with big data and fixed effects. The process of inconsistency due to the conceptualization and realization of a large amount of data (Liu et al., 2019). The natural language processing enables the spatial modeling and temporal dynamic capability of proper planning. The local management system enables local stakeholders and provides the management decisions consequences with the biodiversity of services. This system establishes the sensitive ecosystems (Gosal, Geijzendorffer, Václavík, Poulin, & Ziv, 2019). Advanced analytical techniques establish a huge amount of data requirements. The high precision gives better decision-making techniques. The significant data increases due to the amount, variety, and speed parameters with the inherent lack of confidence. The critical parameters are enhanced, such as the uncertain condition of noise, incomplete data analytics, and inconsistency of big data (Hariri, Fredericks, & Bowers, 2019).

The natural language processing based sentimental analysis, which needs the opinion mining and factorized the positive, negative, and neutral parameters of specific data products. The detailed explanation of strategic data provides the content in social media-based big data (Manasa & Padma, 2019).  This is a creative process of analysis and gathers the data through multi-task performance. The relation between structure knowledge and recognition of speech with the automatic summary of sentiment analysis through the identification of significant data development (Ghani et al., 2019). This method analyzed the decision-making approach and provided the semantic analysis. The text of semantic analysis used to make valuable data extraction from the concern of social media, which offers the best quality of information through policymakers in the government. The extracted value of data to performed by policy makers (Driss, Mellouli, & Trabelsi, 2019). The hate speech of social media websites predicts the natural language processing of big data. The collection of data concerns under the services like streaming, token splitting, removal of inconsistent characters, and elimination of infection along with the consideration of natural hate speech processing, which classifies the textual data to neutral data mining (Al-Makhadmeh & Tolba, 2019). Natural language processing enables the in-depth domain data knowledge to regulate the decision-making process. The decision making provides the contextual interpretation of big data and personalized health information management. The volume, velocity, value, and variety of big data to be investigated through data mining (Kho, Padhee, Bajaj, Thirunarayan, & Sheth, 2019).

1. COMPUTATIONAL INTELLIGENCE AND BIG DATA

Computational Intelligence is the subsystem in Machine Learning process. This concept provides the processing of personal information and provides the processing of reasoning mechanisms for complex and uncertainty of data sources, which is involved in nature. CI is the bunch of nature-inspired data sources, which provides the challenges in social mining, permits the algorithmic design strategies. The computational intelligence gives the different formats and contents of large size of files (Camacho & Bello-Orgaz, 2019). This method approaches the computer affected, sentiment analysis, and overcome the human process and its textual computations. Computational intelligence establishes the highly attains the benefits of data through the remarkable prediction of marketing. It performs the consumption of human, big tasks, and unstructured information along with product preferences (Cambria, Poria, Hussain, & Liu, 2019). CI provided timely effective management and relied on the usage of data information. Computational information enables the context of emergency management. The lifecycle management emerges the quality of industries in biodiversity condition with the stabilization of utilized data (Chen, Liu, Bai, & Chen, 2019).

Computational Intelligence provides the supervised learning concept along with the function of labels and its related input datasets. The detection of data and its extensive modes gives more attention, which detects the information of the system (Balas, Solanki, Kumar, & Khari, 2019). This method provides big data analytics of versatile digital information. This system provides the real-time physical environment and allows the potential knowledge of AI. This leads to enumerates the high ability to manages the data and an effective manner of relying on the overlying of images. The automated collaborators provides better information about big data analytics in AI (Uma, 2019). For bio-inspired big data analysis, the prediction of the minimum number of computational resources along with the usage of memory and execution of response time. This approach provides the optimization in-vehicle sensors to enables the modeling platforms of data analytics. This system offers the following features such as

• Self-learning and Adaptation
• Effective computational efficiency
• Robustness and Resilience
• Algorithmic Hybridization

The practical approaches of textual information provide the data analytics for a human to enables the common mechanism and self-organization (Del Ser, Osaba, Sanchez-Medina, & Fister, 2019).

CONCLUSION

The rapid technological evolution to gathered by using the big data-based social media. The approaches provide the effective addressing of problem in social media around the world. The complexity in data analytics manages the quality of data and computation complexity. The social media established the structured learning approach, self-organization of augmented data analytics. The capability of data analytics emerges the Machine Learning, Artificial Intelligence, Computational Intelligence, and Natural Language Processing along with the practical adaptation of big data analytics. The social media-based big data provides the remarkable objectives in the perception of quality of data. This survey leads to discusses the inefficient factors in big data, the inconsistency of flow, and replication of data analytics through the incorporation of social media integration. The performance of big data effectively provides the accuracy, scalability, and reliable data storage among the given mediated social media.

References:

1. Ahmad, A. K., Jafar, A., & Aljoumaa, K. (2019). Customer churn prediction in telecom using machine learning in the big data platform. Journal of Big Data, 6(1), 28.
2. Al-Makhadmeh, Z., & Tolba, A. (2019). Automatic hate speech detection using killer natural language processing optimizing ensemble deep learning approach. Computing, 1-22.
3. Balas, V. E., Solanki, V. K., Kumar, R., & Khari, M. (2019). Internet of Things and Big Data Analytics for Smart Generation: Springer.
4. Camacho, D., & Bello-Orgaz, G. (2019). Special issue on computational intelligence for social mining: Springer.
5. Cambria, E., Poria, S., Hussain, A., & Liu, B. (2019). Computational Intelligence for Affective Computing and Sentiment Analysis [Guest Editorial]. IEEE Computational Intelligence Magazine, 14(2), 16-17.
6. Chen, N., Liu, W., Bai, R., & Chen, A. (2019). Application of computational intelligence technologies in emergency management: a literature review. Artificial Intelligence Review, 52(3), 2131-2168.
7. Del Ser, J., Osaba, E., Sanchez-Medina, J. J., & Fister, I. (2019). Bioinspired computational intelligence and transportation systems: A long road ahead. IEEE Transactions on Intelligent Transportation Systems.
8. Driss, O. B., Mellouli, S., & Trabelsi, Z. (2019). From citizens to government policy-makers: Social media data analysis. Government Information Quarterly, 36(3), 560-570.
9. El-Alfy, E.-S. M., & Mohammed, S. A. (2020). A review of machine learning for big data analytics: bibliometric approach. Technology Analysis & Strategic Management, 1-22.
10. Geetha, S., & Kumar, K. V. (2019). Tweet Analysis Based on Distinct Opinion of Social Media Users’ Advances in Big Data and Cloud Computing (pp. 251-261): Springer.
11. Georgakopoulos, S. V., Tasoulis, S. K., Vrahatis, A. G., & Plagianakos, V. P. (2019). Convolutional Neural Networks for Twitter Text Toxicity Analysis. Paper presented at the INNS Big Data and Deep Learning conference.
12. Ghani, N. A., Hamid, S., Hashem, I. A. T., & Ahmed, E. (2019). Social media big data analytics: A survey. Computers in Human Behavior, 101, 417-428.
13. Gosal, A. S., Geijzendorffer, I. R., Václavík, T., Poulin, B., & Ziv, G. (2019). Using social media, machine learning and natural language processing to map multiple recreational beneficiaries. Ecosystem Services, 38, 100958.
14. Gunavathi, C., Priya, R. S., & Aarthy, S. (2019). Big data analysis for anomaly detection in telecommunication using clustering techniques Information Systems Design and Intelligent Applications (pp. 111-121): Springer.
15. Hariri, R. H., Fredericks, E. M., & Bowers, K. M. (2019). Uncertainty in big data analytics: survey, opportunities, and challenges. Journal of Big Data, 6(1), 44.
16. Islam, M. A., Halder, S., Uddin, M. A., & Acharjee, U. K. (2019). An Efficient Sentiment Mining Approach on Social Media Networks Emerging Technologies in Data Mining and Information Security (pp. 451-461): Springer.
17. Jan, B., Farman, H., Khan, M., Imran, M., Islam, I. U., Ahmad, A., . . . Jeon, G. (2019). Deep learning in big data analytics: a comparative study. Computers & Electrical Engineering, 75, 275-287.
18. Jimenez-Marquez, J. L., Gonzalez-Carrasco, I., Lopez-Cuadrado, J. L., & Ruiz-Mezcua, B. (2019). Towards a big data framework for analyzing social media content. International Journal of Information Management, 44, 1-12.
19. Kho, S. J., Padhee, S., Bajaj, G., Thirunarayan, K., & Sheth, A. (2019). Domain-specific Use Cases for Knowledge-enabled Social Media Analysis Emerging Research Challenges and Opportunities in Computational Social Network Analysis and Mining (pp. 233-246): Springer.
20. Liu, X., Shin, H., & Burns, A. C. (2019). Examining the impact of luxury brand’s social media marketing on customer engagement: Using big data analytics and natural language processing. Journal of Business Research.
21. Manasa, K., & Padma, M. (2019). A Study on Sentiment Analysis on Social Media Data Emerging Research in Electronics, Computer Science and Technology (pp. 661-667): Springer.
22. Mini, U., Nair, V., & Jacob, K. P. (2019). Monitoring Public Participation in Multilateral Initiatives Using Social Media Intelligence Data Science and Big Data Analytics (pp. 201-214): Springer.
23. Ngiam, K. Y., & Khor, W. (2019). Big data and machine learning algorithms for health-care delivery. The Lancet Oncology, 20(5), e262-e273.
24. Passos, I. C., Ballester, P. L., Barros, R. C., Librenza‐Garcia, D., Mwangi, B., Birmaher, B., . . . Mansur, R. B. (2019). Machine learning and big data analytics in bipolar disorder: A position paper from the International Society for Bipolar Disorders Big Data Task Force. Bipolar disorders, 21(7), 582-594.
25. Prabhu, B. A., Ashwini, B., Khan, T. A., & Das, A. (2019). Predicting Election Result with Sentimental Analysis Using Twitter Data for Candidate Selection Innovations in Computer Science and Engineering (pp. 49-55): Springer.
26. Roh, Y., Heo, G., & Whang, S. E. (2019). A survey on data collection for machine learning: a big data-ai integration perspective. IEEE Transactions on Knowledge and Data Engineering.
27. Sivarajah, U., Irani, Z., Gupta, S., & Mahroof, K. (2019). Role of big data and social media analytics for business to business sustainability: A participatory web context. Industrial Marketing Management.
28. Talha, M., Ali, S., Shah, S., Khan, F. G., & Iqbal, J. (2019). Integration of Big Data and Deep Learning Deep Learning: Convergence to Big Data Analytics (pp. 43-52): Springer.
29. Tripathy, H. K., Acharya, B. R., Kumar, R., & Chatterjee, J. M. (2019). Machine learning on big data: A developmental approach on societal applications Big Data Processing Using Spark in Cloud (pp. 143-165): Springer.
30. Uma, S. (2019). Latest Research Trends and Challenges of Computational Intelligence Using Artificial Intelligence and Augmented Reality Computational Intelligence and Sustainable Systems (pp. 43-59): Springer.
31. Yau, C., & Campbell, K. (2019). Bayesian statistical learning for big data biology. Biophysical reviews, 11(1), 95-102.