LAUSR

Cellular networks are constantly evolving to support the new context and demands of users with increasing internet traffic. The key to a service provider’s success is a direct response to endpoints to retain existing users and attract new users. For this reason, Mobile Network Operators (MNOs) must reach user satisfaction under a user-centered perspective with Quality of Experience (QoE) to achieve a Return on Investment (RoI). In the latest QoE modelling, our previous method performed QoE estimation and synthesis using an Artificial Neural Network (ANN). Nevertheless, such work did not prove the characteristics of the QoE model built on different working situations. The essential features of the area and user diversities need to be considered in detail to summarize the proper model. In this paper, the proposed framework focuses on analyzing QoE model characteristics under different operating situations for comprehensive implementation. The experimental results reveal that the created QoE models from areas of different densities affect the different predictive variables. Inter-Rater Reliability (IRR) analysis exposes the reliability of datasets gathered from users of different groups to distinguish the effects on the response of significant parameters. Additionally, the summary specifies the characteristics of the appropriate model by area and user group as a guideline for improving the multimedia services.