TY - GEN
T1 - Investigating The Usability Issues In Mobile Applications Reviews Using A Deep Learning Model
AU - Alagmdi, Shabbab
AU - Albanyan, Abdullah
AU - Ludi, Stephanie
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Researchers and IT experts have long been in-terested in the usability of mobile apps, since well-designed mobile applications can improve user experiences and strengthen relationships between companies and customers. To better under-stand mobile app usability, this research employs machine and deep learning models to analyze usability issues in evaluations of mobile applications. An empirical study uses a unified hierar-chical approach to the usability of mobile applications. Usability qualities are taken into account at the detailed level, whereas usability principles examine usability attributes as shown later on. Usability features are used to evaluate the functionality of the most popular app stores across a variety of categories. Using a Kaggle dataset11https://www.kaggle.com/datasets/souravghoshOI/google-play-store-app-details?select=finalmetadatav3.csv, we found frequent usability issues based on user feedback. Despite the number of publicly available datasets (on sites like Kaggle and others) that provide information on the Apple App Store, there aren't many Google Play Store app-specific datasets elsewhere online. Further investigation revealed that the iTunes App Store website has an appendix-like, beau-tifully structured structure to make web scraping quick and straightforward. This dataset was examined, and we then linked it to usability characteristics, including assistance for users, interaction, information, and cognition. Each type of usability attribute has subcategories that are essential to the study. The study also identifies a set of essential and optional usability criterion elements for various categories of mobile apps. The study discovered that these principle attributes could be used to build mobile apps, but they are also beneficial for other purposes: substantial links between usability principles, qualities, and features.
AB - Researchers and IT experts have long been in-terested in the usability of mobile apps, since well-designed mobile applications can improve user experiences and strengthen relationships between companies and customers. To better under-stand mobile app usability, this research employs machine and deep learning models to analyze usability issues in evaluations of mobile applications. An empirical study uses a unified hierar-chical approach to the usability of mobile applications. Usability qualities are taken into account at the detailed level, whereas usability principles examine usability attributes as shown later on. Usability features are used to evaluate the functionality of the most popular app stores across a variety of categories. Using a Kaggle dataset11https://www.kaggle.com/datasets/souravghoshOI/google-play-store-app-details?select=finalmetadatav3.csv, we found frequent usability issues based on user feedback. Despite the number of publicly available datasets (on sites like Kaggle and others) that provide information on the Apple App Store, there aren't many Google Play Store app-specific datasets elsewhere online. Further investigation revealed that the iTunes App Store website has an appendix-like, beau-tifully structured structure to make web scraping quick and straightforward. This dataset was examined, and we then linked it to usability characteristics, including assistance for users, interaction, information, and cognition. Each type of usability attribute has subcategories that are essential to the study. The study also identifies a set of essential and optional usability criterion elements for various categories of mobile apps. The study discovered that these principle attributes could be used to build mobile apps, but they are also beneficial for other purposes: substantial links between usability principles, qualities, and features.
KW - Deep Learning
KW - Human Computer Interaction
KW - Usability
UR - http://www.scopus.com/inward/record.url?scp=85156221445&partnerID=8YFLogxK
U2 - 10.1109/CCWC57344.2023.10099350
DO - 10.1109/CCWC57344.2023.10099350
M3 - Conference contribution
AN - SCOPUS:85156221445
T3 - 2023 IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023
SP - 108
EP - 113
BT - 2023 IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023
A2 - Paul, Rajashree
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 13th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2023
Y2 - 8 March 2023 through 11 March 2023
ER -