Arxiv 2512.11934

Abstract— The rapid integration of generative artificial intelligence into education has driven digital transformation in e-teaching, yet user perceptions of AI educational apps remain underexplored. This study performs a sentiment-driven evaluation of user reviews from top AI ed-apps on the Google Play Store to assess efficacy, challenges, and pedagogical implications. Our pipeline involved scraping app data and reviews, RoBERTa for binary sentiment classification, GPT-4o for key point extraction, and GPT-5 for synthesizing top positive/negative themes. Apps were categorized into seven types (e.g., homework helpers, math solvers, language tools), with overlaps reflecting multifunctional designs. Results indicate predominantly positive sentiments, with homework apps like Edu AI (95.9% positive) and Answer.AI (92.7%) leading in accuracy, speed, and personalization, while language/LMS apps (e.g., Teacher AI at 21.8% positive) lag due to instability and limited features. Positives emphasize efficiency in brainstorming, problem-solving, and engagement; negatives center on paywalls, inaccuracies, ads, and glitches. Trends show that homework helpers outperform specialized tools, highlighting AI’s democratizing potential amid risks of dependency and inequity. The discussion proposes future ecosystems with hybrid AI-human models, VR/AR for immersive learning, and a roadmap for developers (adaptive personalization) and policymakers (monetization regulation for inclusivity). This underscores generative AI’s role in advancing e-teaching by enabling ethical refinements that foster equitable, innovative environments. The full dataset is available here(https://github.com/erfan-nourbakhsh/GenAI-EdSent) . Index Terms– Generative AI, e-Teaching, sentiment analysis, educational apps, digital transformation I. INTRODUCTION
The Generative artificial intelligence (GenAI) has reshaped education, advancing digital transformation in e- teaching through enhanced personalization, accessibility, and efficiency [1]. GenAI supports dynamic features such as automated tutoring and adaptive assessments, as seen in the rise of AI-integrated educational apps (ed-apps) on platforms such as the Google Play Store1, addressing needs ranging from homework assistance to language learning [4]. Yet, a key gap remains in grasping user perceptions in real-world use. This study fills this gap through sentiment analysis of user reviews, uncovering strengths, challenges, and implications for equitable e-teaching. Recent surveys reveal varying AI adoption in education, highlighting opportunities and barriers. Students prioritize efficiencies like brainstorming, summarizing, and feedback [2]. Educators focus on strategic uses such as lesson ideas, plans, and simplifying topics [2]. This divergence reflects students’ productivity needs versus teachers’ pedagogical emphasis. However, most K-12 teachers remain non-users due to concerns like integrity, training, and hurdles [3], [5], [6]. Despite challenges, a dedicated minority drives momentum for personalized learning, underscoring the need for empirical insights to bridge gaps [7], [8]. User perceptions are crucial, revealing satisfaction, ethical, usability, and inclusivity issues in AI’s digital transformation role [9], [10]. Traditional evaluations via surveys or interviews are limited by sample size and subjectivity [11]. Instead, app store reviews provide scalable, real-time insights into authentic experiences, including sentiments on accuracy, monetization, and integration [12]. This study uses NLP techniques—RoBERTa for sentiment classification and GPT- 4o/GPT-5 for theme extraction—to analyze reviews from 21 top AI ed-apps [13]. Apps are categorized into seven types: AI Quiz & Question Generators, All-in-One Study Companions, Homework Helpers, Math-Focused Solvers, Document/Content Tools, Learning Management Systems (LMS), and Language Learning Apps, highlighting multifunctional overlaps and feedback trends. The primary objectives are threefold: (1) quantify sentiment distributions and distill key positive/negative themes across app categories; (2) compare performance trends, showing why homework helpers receive high praise while LMS and language apps face criticism; and (3) discuss implications for future AI educational ecosystems, proposing hybrid models integrating AI strengths with human oversight.

1. https://play.google.com/

This analysis contributes data-driven recommendations for

…(Full text truncated)…