Back close

Social media data analysis: rough set theory based innovative approach

Publication Type : Book Chapter

Publisher : Springer

Source : Intelligence of Things: AI-IoT Based Critical-Applications and Innovations

Url : https://link.springer.com/chapter/10.1007/978-3-030-82800-4_9

Campus : Chennai

School : School of Engineering

Year : 2021

Abstract : Social media data is the set of information collected from Social Network. Through these data statistician can track how individuals can manage with the content of Facebook, Twitter, LinkedIn and Research Gate, etc. Number of views, likes, comments, conversations and shares are some of the important metrics of this metadata. Social Media Data Analysis is the process of converting raw data into valuable or useful business outcome. Social media data for audience segmentation, personalized sales outreach, and experience with content engaging are some of the data collection techniques. Digital marketers are using the techniques and tools for understanding the behaviour of customers. AIIoT—Artificial Intelligence (AI) and the Internet of Things (IoT) provides massive approach to monitoring social media data. It offers the optimal method to aggregate social data with minimum time and effort. The device with chipset connected to social media network will collect large amount of information for every second. This chapter proposes innovative approach based on rough set in social media data analysis. Reduct generation process is discussed in this chapter. Reducts are most important subsets of given information system. For the construction of reduct, the relation between the objects is connected through rough graph. From this graph Rough discernibility matrix is being framed and then consistent network is verified

Cite this Research Publication : Anitha, K. (2021). Social Media Data Analysis: Rough Set Theory Based Innovative Approach. In: Al-Turjman, F., Nayyar, A., Devi, A., Shukla, P.K. (eds) Intelligence of Things: AI-IoT Based Critical-Applications and Innovations. Springer, Cham. https://doi.org/10.1007/978-3-030-82800-4_9.

Admissions Apply Now