Unveiling User Perceptions in the Generative AI Era: A Sentiment-Driven Evaluation of AI Educational Apps' Role in Digital Transformation of e-Teaching
Adeleh Mazaherian, Erfan Nourbakhsh
2025-12-17
Summary
This research investigates how people feel about using AI-powered apps for learning, looking specifically at reviews from apps available on the Google Play Store.
What's the problem?
While AI is quickly becoming a part of education, there hasn't been much research into what students and teachers actually *think* about these AI learning tools. Are they helpful? What problems do people run into when using them? Understanding these perceptions is crucial for making AI in education effective and fair.
What's the solution?
The researchers collected a lot of user reviews from popular AI education apps. They then used several AI tools themselves – RoBERTa to figure out if a review was positive or negative, GPT-4o to pull out the main points from each review, and GPT-5 to group similar positive and negative comments together. They also categorized the apps into types like 'homework helper' or 'language learning' to see if certain kinds of apps were rated better than others.
Why it matters?
The study found that most reviews were positive, especially for apps that help with homework. However, apps designed for specific subjects or language learning often had more complaints. This research highlights the potential of AI to make learning more accessible and efficient, but also points out risks like relying too much on AI, unfair access due to costs, and the need for better, more reliable apps. It suggests future improvements like combining AI with human teachers and creating more immersive learning experiences, and also calls for rules about how these apps charge money to ensure everyone can benefit.
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).