Abstract :

The Rapid Expansion Of The Digital Gaming Industry And The Increasing Diversity Of Video Games Have Created A Strong Demand For Intelligent Systems Capable Of Accurately Classifying Games Across Multiple Genres And Domains. With The Continuous Growth Of Online Platforms And User-generated Content, Automated Analysis Has Become Essential For Efficient Organization, Recommendation, And Evaluation Of Game-related Data. However, Identifying Genres And Attributes From Textual Descriptions Remains Challenging Due To Domain Variability, Unstructured Data, And Semantic Ambiguity. Traditional Approaches, Such As Manual Tagging And Keyword-based Techniques, Along With Early Machine Learning (ML) Methods Like Bag-of-Words (BoW) And Term Frequency–Inverse Document Frequency (TF-IDF), Fail To Capture Contextual Meaning And Suffer From Limited Generalization. To Address These Limitations, This Study Proposes An Automated System Featuring A Tkinter-based Graphical User Interface (GUI) Integrated With A Machine Learning Framework For Multi-attribute Video Game Classification. The System Leverages Masked And Permuted Pre-training Network (MPNet) Transformer Embeddings To Extract Deep Semantic Features From Textual Data. Multiple Classifiers, Including Ridge Classifier (RC), Nearest Centroid (NC), Restricted Boltzmann Machine–Ridge (RBMR) Pipeline, And A Proposed Ensemble Of Oblique Trees (EOT) Model, Are Utilized For Improved Classification Performance. The Dataset Is Balanced Using Random Under Sampling (RUS) To Enhance Robustness. Additionally, The System Incorporates A Secure Authentication Mechanism Using Redis With SHA-256 Hashing For User Credential Protection And Session Management. Comprehensive Evaluation Metrics Demonstrate Improved Accuracy, Reliability, Scalability, And Reduced Manual Effort In Game Analytics.

Published:

09-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

2086-2095

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite