Enhancing Business Value Creation Via Social Media Metrics Evaluation: A Machine Learning and Data Analytics Approach
No Thumbnail Available
Authors
Adebayo, Olumide
Issue Date
2020-12-11
Type
Thesis
Language
en_US
Keywords
Big data , Data envelopment analysis , Sentiment analysis , Social media marketing , Technology management
Alternative Title
Abstract
Social Media Marketing (SMM) plays an important role in business growth and expansion. With its growing capability and impact, SMM offers a major challenge for decision makers seeking to quantify the value of emergent SMM channels in their marketing mix. The inherent risks and challenges of big data makes the return valuation more pertinent in SMM. Conventional methods used for measuring return on investment (ROI) of marketing activities do not seamlessly translate to SMM operations due to the active involvement of external participants and significant differences in the cost structure. There is no well-established approach to systematically relate organizational social media activities to various revenue streams hindering efforts to justify these investments. This study analyzes social network characteristics and typology to evaluate business performance. Social network typology is a relatively new and important research topic for business performance quantification and evaluation. Historically, performance measurements in SMM research have always been viewed in terms of numbers of followers, comments, likes, retweets and such. No organization is formed with the end goal of increasing its likes or followers. The main goal of every organization is to increase shareholder value. The contribution of this paper is multi-fold. It aims to start drawing research from these vanity and/or actionable metrics towards organizational performance metrics measurement. The research also introduces a multi-dimensional model that can be instrumental in evaluating the added value of SMM expenditures at the corporate level.
Description
Citation
O. Adebayo, "Enhancing Business Value Creation Via Social Media Metrics Evaluation: A Machine Learning and Data Analytics Approach", Ph.D. dissertation, Dept. of Engineering, Univ. of Bridgeport, Bridgeport, CT, 2020.