• This email address is being protected from spambots. You need JavaScript enabled to view it.

"Research is what I'm doing when I don't know what I'm doing." ~ Wernher von Braun

Exploring Customer Behavior with Social Media Analytics

Abstract

Social media is a phenomenon which has transformed the communication of people around the globe. Social media have also affected brands, by improving their interaction with consumers. Among other industries, fashion industry seems to be benefited, taking advantage of social media global and direct communication reach capability, to track users’ intention to spend a quite big amount of money for fashion products and services by configurating the factors which impact users’ engagement. This study examines how users engage with image posts, providing an analytical report of the factors. Those factors refer to the performance of the description text in a image post and include post text readability and education level required to read it, and numbers of post’s text hashtags, words, and characters which are the independent variables. Datasets were exported from a women fashion retail Facebook business page. Performance metrics were preprocessed, computed, labeled, processed, and mined. Text readability ease and the level of education required, were measured by an online tool. Posts’ performances were measured by eight Facebook performance metrics including Post Shares, Post Likes, Lifetime Post Total Reach, Lifetime Post Total Impressions, Lifetime Engaged Users, Lifetime Post Impressions by People Who Have Liked the Page, Lifetime Post Reach by People Who Like the Page, Lifetime People Who Have Liked the Page and Engaged with the Post, considered as depended variables. The independent and depended performance metrics refer to 135 image posts with description tests. The data are analytically processed through a series of statistical tests including normality distribution tests, descriptive statistics per category, correlation tests, significant differences tests and data mining technique where post performance represented by a decision tree graph. This research contributes to prior literature by providing more specific set of guidelines to marketers and decision makers on how to increase users’ engagement through organic posts social media activity..

Keywords: User behavior, Digital marketing, Social media marketing, Social media insights, Machine learning, Decision making.

Gkikas D. C. (2021). Exploring Customer Behavior with Social Media Analytics. [Master's Dissertation, International Hellenic University] URI https://repository.ihu.edu.gr//xmlui/handle/11544/2990, Download

© 2024 Dimitris C. Gkikas. All Rights Reserved.