Sentiment Analysis of Mobile Legends App Reviews Using Machine Learning and LSTM-Based Deep Learning Models

arXiv cs.CL / 5/5/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The study evaluates sentiment analysis for Mobile Legends app reviews by comparing traditional machine learning approaches with an LSTM-based deep learning model.
Using 10,000 labeled reviews (positive, negative, neutral), the researchers test TF-IDF features with PyCaret AutoML baselines.
The LSTM model is reported to outperform the classical ML baselines, reaching 92% accuracy and a weighted F1-score of 91%.
The results suggest deep learning is better suited to informal, context-dependent review language because it can model sequential dependencies in text.
The paper contributes an applied comparison framework for choosing between classical ML and LSTM architectures in app-review sentiment tasks.

Abstract

This paper compares Machine Learning and LSTM-based Deep Learning methods for sentiment analysis of Mobile Legends app reviews. Using a dataset of 10,000 reviews labeled as positive, negative, and neutral, the study evaluates traditional models with TF-IDF and PyCaret AutoML and compares them against an LSTM model designed to capture sequential text dependencies. The results show that the LSTM model outperforms the classical Machine Learning baselines, achieving 92% accuracy and a weighted F1-score of 91%. The findings indicate that deep learning is more effective for handling informal and context-dependent user review text.