Beyond Star Ratings: Comparison of Sentiment‑Driven Deep Learning Models for Play-Store Game Recommendations

Babu Manuel, Alan (2025) Beyond Star Ratings: Comparison of Sentiment‑Driven Deep Learning Models for Play-Store Game Recommendations. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (5MB) | Preview

Abstract

User-generated reviews on app marketplace like google play store always presents a major challenge for assessing user sentiment and rating prediction. Game app recommendation systems provide substantial advantages to mobile users alongside developers. Mobile games form a substantial part of app stores yet users struggle to find suitable games because of the numerous available options. An efficient recommendation system solves this challenge through customized game recommendations that boost user engagement and satisfaction. The recommendation system generates longer playtime and increased game downloads that help developers reach their success goals. This study addresses the need for sentiment and rating prediction by evaluating four state‑of‑the‑art, sentiment‐enhanced deep‑learning architectures a GloVe‐embedded LSTM with attention, a DistilBERT‑based Transformer, a hybrid GRU–CNN model, and a DistilGPT2 Transformer on a large corpus of Play Store reviews. We trained and tested each model on 100K reviews using a consistent preprocessing pipeline (tokenization, padding, user–app embeddings) and optimized hyperparameters via randomized search. The hybrid GRU–CNN model delivers the lowest test MSE of 0.039 alongside MAE of 0.124 to outperform all other models including both LSTM‐ and Transformer‐only approaches while GloVe+LSTM+attention reaches the highest Recall@10 level of 0.8440.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Staikopoulos, Athanasios UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science G Geography. Anthropology. Recreation > GV Recreation Leisure > Games and Amusements > Computer Games. Video Games. Q Science > QA Mathematics > Computer software > Mobile Phone Applications T Technology > T Technology (General) > Information Technology > Computer software > Mobile Phone Applications
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	18 Nov 2025 13:44
Last Modified:	18 Nov 2025 13:44
URI:	https://norma.ncirl.ie/id/eprint/8938

Actions (login required)

View Item