article · Journal of Science Research and Reviews
Digital marketplaces produce immense volumes of user feedback daily, making automated sentiment classification essential for software developers, platform operators, and prospective consumers. A synthesis of empirical and methodological literature focuses on machine learning systems deployed on Google Play Store reviews. Common text preprocessing strategies include tokenisation, count vectorisation, term frequency-inverse document frequency, and transformer-based embeddings. Frequently implemented classification techniques span Support Vector Machines, Multinomial Naïve Bayes, AdaBoost, and diverse ensemble strategies, routinely evaluated by metrics such as accuracy, precision, recall, F1-score, and area under the ROC curve. The analysis highlights three critical technical hurdles: the systematic interpretation of emojis, principled handling of class imbalance, and rigorous statistical validation for reported performance gains. Overcoming these limitations calls for hybrid ensemble frameworks that pair classical algorithms with contextual embeddings suited to informal review language.
Manually sorting through massive streams of app store feedback is unfeasible. Automated sentiment analysis enables software creators and marketplace managers to track user satisfaction and detect product issues quickly. Clarifying persistent technical limitations ensures that future feedback analytics tools can reliably interpret informal writing, slang, and emojis without distorted results caused by imbalanced review data.
The primary beneficiaries are mobile application developers, customer support teams, and platform operators seeking automated user feedback analytics. Because this work represents an early-stage literature review and methodological synthesis rather than a packaged software solution, it remains distant from direct commercial deployment. Real-world adoption will depend on engineers implementing and validating proposed ensemble architectures within live data pipelines to handle informal text and emoji-heavy reviews reliably.
AI-generated from the published abstract. Always read the original work before citing.
Mobile application marketplaces generate huge volumes of user reviews daily. Automatically understanding if a review is positive or negative matters to developers, platform operators, and prospective users alike, since manually reading them one by one is not feasible. This paper reviews the empirical and methodological literature on machine-learning-based sentiment classification, with particular attention to studies using Google Play Store review data. It synthesises a substantial body of empirical work and examines the preprocessing techniques that recur across it, which includes tokenization, count vectorization, TF-IDF, and transformer-based embeddings. It also discusses, accuracy, precision, recall, F1-score, and AUC-ROC, and also reviews the core classifiers used. The Support Vector Machines, Multinomial Naïve Bayes, AdaBoost, and ensemble strategies where applied. Three major challenges with the classification of Google Play Store where also discussed. The challenges include the systematic handling of emojis, principled handling of class imbalance, and statistical validation of reported performance gains. Together, these gaps motivate further research into ensemble architectures that combine classical classifiers with modern contextual embeddings for domain-specific, imbalanced, and informally written review text.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.70882/josrar.2026.v3i5.292
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
