Predictive Modeling of User Engagement Patterns on Social Media using Data Mining Approaches

VIKRANT VITTHALRAO MADNURE; Dr. Purushottam Anandrao Kada

Predictive Modeling of User Engagement Patterns on Social Media using Data Mining Approaches

Author(s)	Mr. VIKRANT VITTHALRAO MADNURE, Dr. Purushottam Anandrao Kada
Country	India
Abstract	The current study propose a framework of data mining and machine learning to predict user engagements on social media platforms. The data will combine multi-dimensional features such as that of the content attributes (type of post, category of topics, media format), time (time of day, seasonality), user history of interaction (likes, comments, shares, click-through rates) and context (location, type of device, connectivity state). Data would be taken or rather sampled on various platforms such as Facebook, Instagram, Twitter, and YouTube settings all capturing active user behaviors and passive user behavior, in addition to cultural events and regular times. With feature engineering, some important predictors of engagement were determined, such as media type, posting time, topical timeliness, and past engagement patterns. LSTM neural networks, K-Nearest Neighbor, Decision Tree, Random Forest, Gradient Boosting, Support Vector Machines, and Logistic Regression were the seven prediction models that were trained and evaluated. The comparative tests showed that the Gradient Boosting model presented the most accuracy in the case of tabular features based prediction, whereas the LSTM networks showed superior results in sequential, time-series prediction engagement. The procedure involved pre-processing raw data, conducting exploratory data analysis, feature engineering, model tuning, and validation which was implemented through machine toolkit written in Python. The study provides practical conclusions concerning content optimization techniques, with the marketers, platform administrators, and content producers potentially using the data to increase engagement rates by making well-informed decisions.
Keywords	predictive modelling; user engagement; social media analytics; data mining; machine learning; Gradient Boosting; LSTM; feature engineering; context-aware prediction; classification; time-series; content optimisation
Field	Computer
Published In	Volume 16, Issue 4, October-December 2025
Published On	2025-10-18

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 16 Isu 3 Cover Page Vol 16 Isu 2 Cover Page Vol 16 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Predictive Modeling of User Engagement Patterns on Social Media using Data Mining Approaches

Share this