Dataset and Code for User Acceptance of AR Beauty Technology: A Review Mining and TAM Analysis.

Dataset and Code Repository for the Study:"User Acceptance of AR Beauty Technology: A Review Mining and TAM Analysis" Description:This repository contains the raw datasets, preprocessed review data, mapping files, and Python scripts utilized for scraping, filtering, clustering, and evaluating user reviews from the Google Play Store regarding the AR virtual try-on features of Sephora and Ulta Beauty applications. Folder Contents:1. Sephora_Reviews.xlsx / Ulta_Reviews.xlsx: - Raw datasets containing user reviews extracted directly from the Google Play Store. 2. Sephora_Mapped_Framework_Final.xlsx / Ulta_Mapped_Framework_Final.xlsx: - Final processed and mapped datasets containing user reviews, cluster assignments, TF-IDF keyword extraction, and Extended TAM framework integration (Usefulness, Interactivity, Visual Realism, and Enjoyment). 3. Python Scripts (.ipynb notebooks): - Data collection and scraping scripts via google-play-scraper. - Text preprocessing, custom keyword filtering, and S-O-R rating mapping scripts. - TF-IDF keyword extraction and automated framework mapping scripts (e.g., Sephora_Framework_Final & Ulta cluster analysis notebooks). Methodology Summary:- Data Collection: Scraped from Google Play Store using Python.- Preprocessing & Filtering: Filtered using domain-specific keywords related to AR features (e.g., virtual, try-on, camera, shade match).- Analysis & Modeling: Text mining, TF-IDF keyword extraction, K-Means clustering, Davies-Bouldin Index (DBI) validation, and Extended TAM thematic mapping. Contact:For any inquiries regarding this dataset or code repository, please contact the corresponding author.