This paper examines how Consumer Electronics (CE)–enabled touchpoints influence airline passenger experience by analyzing a decade of British Airways customer reviews collected from the Skytrax platform. Unlike prior work that focuses on short-term reviews or sentiment classification, this study provides a long-term CE-centric analysis by combining descriptive analytics, clustering, and predictive modeling on a decade of British Airways consumer feedback. Using social network data, descriptive analytics, and machine learning models, the study identifies the digital service attributes most strongly associated with consumer satisfaction, including value for money, cabin staff interactions, seat comfort, and inflight digital services such as Wi-Fi and entertainment systems. Results reveal a long-term decline in recommendation rates and highlight persistent weaknesses in connectivity and media services, both of which form critical CE components in modern travel. Predictive modeling using logistic regression achieves 95% accuracy in forecasting customer recommendation behavior, demonstrating the potential of data-driven approaches for enhancing consumer experience. The study concludes with strategic recommendations on how airlines can leverage social networks and CE-based service platforms to improve engagement, operational responsiveness, and brand loyalty.
Paper
Full text
Machine Learning Analysis of Consumer Electronics-Enabled Passenger Experience
OpenAlex · AI in Service Interactions · 2026
Abstract
This paper examines how Consumer Electronics (CE)–enabled touchpoints influence airline passenger experience by analyzing a decade of British Airways customer reviews collected from the Skytrax platform. Unlike prior work that focuses on short-term reviews or sentiment classification, this study provides a long-term CE-centric analysis by combining descriptive analytics, clustering, and predictive modeling on a decade of British Airways consumer feedback. Using social network data, descriptive analytics, and machine learning models, the study identifies the digital service attributes most strongly associated with consumer satisfaction, including value for money, cabin staff interactions, seat comfort, and inflight digital services such as Wi-Fi and entertainment systems. Results reveal a long-term decline in recommendation rates and highlight persistent weaknesses in connectivity and media services, both of which form critical CE components in modern travel. Predictive modeling using logistic regression achieves 95% accuracy in forecasting customer recommendation behavior, demonstrating the potential of data-driven approaches for enhancing consumer experience. The study concludes with strategic recommendations on how airlines can leverage social networks and CE-based service platforms to improve engagement, operational responsiveness, and brand loyalty.