From Raw Data to Consumer Insights: A Review of Descriptive Statistics in Social Media Consumption Analysis

The vast amounts of user behaviour data accumulated on social media platforms provide valuable material for understanding consumer preferences, however, the raw data itself cannot be directly converted into business insights. Descriptive statistics transform unstructured data into comprehensible information through metrics such as the mean, median, frequency and standard deviation. Although this method is widely used in empirical research, a systematic review of its application in the context of social media consumption data is still lacking.This paper adopts a literature review approach to systematically examine five key aspects: the interpretation of core indicators, the application of three types of behavioural scenarios, the identification of high-potential individuals, the inherent limitations of the method, and standardised implementation processes. The study found that descriptive statistics are a fundamental tool for data exploration, capable of rapidly revealing data characteristics and analytical directions, thereby providing guidance for subsequent in-depth analysis, however, they cannot infer causal relationships or predict trends, and their limitations must be clearly defined in practice. Focusing on social media consumption data, this review systematically clarifies the interpretation of indicators, application boundaries and implementation processes for descriptive statistics. It fills a research gap in this field regarding indicator systems and scenario-based applications, and provides a methodological reference for the preliminary analysis of social media consumption data.