Machine-learning-based Classification of Customers’ Behavioural Model in Instagram

This study investigates the factors influencing consumer behaviour on Instagram, a social media platform under the Meta platform. Due to the complex and often unclear nature of social media user behaviour, we leverage supervised machine-learning algorithms to gain insights. We conducted a survey amo...

Full description

Saved in:
Bibliographic Details
Published in:Paradigm (Ghāziabād, India) India), 2024-12, Vol.28 (2), p.223-240
Main Authors: Bigdeli, Mostafa, Akbari, Mahsa
Format: Article
Language:English
Subjects:
Algorithms
Consumer behavior
Decision trees
Digital media
Machine learning
Polls & surveys
Social networks
User behavior
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study investigates the factors influencing consumer behaviour on Instagram, a social media platform under the Meta platform. Due to the complex and often unclear nature of social media user behaviour, we leverage supervised machine-learning algorithms to gain insights. We conducted a survey among 390 Meta Platform users (Instagram and Facebook) who have recently made social media purchases (past 6 months). In the machine-learning phase, the collected data were submitted to analyse the dataset using Scikit Learn along with Decision Tree Classifier. The survey is conducted in a semi-structured manner, allowing respondents to contribute to this process. The findings of the study reveal a total of 54 distinct customer behaviour patterns. The study demonstrates that product-related factors, content characteristics, technology usage, social influences, and situational context are the primary drivers of consumer behaviour on the Meta platform. It is noteworthy that the research findings indicate the considerable impact of product attributes, including pricing, quality, and product category, on consumer behaviour on Meta platform. The present study offers a novel contribution by identifying meta-specific attributes that can be used to classify and predict customer behaviour patterns on Facebook and Instagram. The findings provide a valuable guide for understanding the complexities of consumer behaviour on social media.
ISSN:0971-8907
2394-6083
DOI:10.1177/09718907241286336