Text Mining Applications for Mobile Banking User Satisfaction

As mobile banking gains popularity for financial transactions, research aimed at enhancing user satisfaction has become increasingly important. This paper examines the literature on the application of text-mining methods to extract insights from user-generated content in the context of mobile banking. The objective is to identify the text-mining methods commonly employed and the key factors influencing user satisfaction in mobile banking. A systematic literature review was conducted to identify relevant articles from Google Scholar, Scopus, IEEE Xplore, and ScienceDirect. The results show that sentiment analysis, topic modelling and word cloud are the most widely used methods in the mobile banking context. Furthermore, the findings highlight that the most cited drivers of user satisfaction in mobile banking based on text mining approaches are security, ease of use and software updates. Additionally, the review uncovers gaps in previous research, particularly the underutilization of advanced text mining methods. To address these gaps, this paper establishes a comprehensive framework that consolidates previous findings and provides actionable recommendations for future research. This framework serves as a guide to better understand user satisfaction and to leverage text mining for more effective insights in the evolving landscape of mobile banking.

Implementing a Process Mining Framework to Improve Customer Experience

Improving Customer Experience (CX) is a strategic priority for organisations. This study develops and evaluates a Process Mining framework that extracts operational performance metrics and interpretable insights from event logs to support evidence-based decisions for optimizing CX. The framework encompasses the discovery of visual process models, cycle time measurement, analysis of operational flows and frequencies, identification of recurring bottlenecks, and evaluation of model accuracy. Applied to three datasets (Sepsis Events, BPI Challenge, and Hospital Billing), the results showed strong model accuracy, ranging from 88% for BPI Challenge to 100% for Hospital Billing. Additionally, the analysis uncovered efficiency variations, with cycle times spanning 19.4 hours to 149.2 days, and flagged notable delays, such as over 700 hours in administrative duties. These findings affirm the framework’s ability to offer in-depth insights, helping organisations identify key obstacles and take purposeful steps to elevate service quality and customer contentment.

Australia’s Broadband Evolution to 2007

The Journal revisits an historic paper, written by Peter Darling in 2007, which details Australia’s evolving broadband policy as background to the decisions likely to be made by the incoming new Australian Government in that year. Broadband policy was a critical differentiator between the outgoing Coalition government and the incoming Labor government in the 2007 federal election. The paper is written for a broad readership within the Australian telecommunications industry.

Hybrid Deep Learning Ensemble with Dynamic Fusion for Reliable Anomaly Detection in Operational LTE RANs

Monitoring long-term evolution (LTE) network performance is increasingly complex due to rapidly growing data volumes and the diversity of quality-of-service indicators. Traditional monitoring approaches relying on static thresholds and manual key performance indicator (KPI) analysis often fail to detect multidimensional, evolving anomalies. We propose instead a hybrid deep ensemble learning framework for anomaly detection and diagnosis in Radio Access Networks (RANs). This framework integrates four complementary architectures: (i) a convolutional autoencoder (CAE); (ii) a Bidirectional Long Short-Term Memory AutoEncoder (BLSTM-AE); (iii) a transformer autoencoder (transformer AE); and (iv) a bidirectional LSTM forecaster, generating various anomaly scores. These scores are dynamically fused across frequency bands and processed with an Isolation Forest (IF) to produce the final anomaly judgment. An evaluation on real LTE data from Algerian mobile networks (three months, 1650 base stations, hourly KPIs) demonstrates the effectiveness of the proposed approach, achieving a maximum F1 score of 93.89%, an improvement of up to 9.5% over the best individual model. SHapley Additive exPlanations (SHAP)-based explainability analysis reveals that key operational indicators related to mobility and resource use drive the model’s decisions. This work provides a practical, interpretable hybrid framework validated on confidential operational data from a national operator under region-specific conditions.

Modelling and Analysis of Regulatory Interventions for Sustainable Public Wi-Fi Programs

Public Wi-Fi is a suitable technology alternative to mobile broadband for affordable Internet access. With a 2.6 billion population yet to be connected globally, many countries are formulating policies around Public Wi-Fi to bridge the digital divide. India lags considerably in broadband connectivity, with only 44% rural Internet/broadband density. Public Wi-Fi penetration in India is meagre compared to global deployments. The Indian government launched the Wi-Fi Access Network Interface (WANI) as an approved Public Wi-Fi infrastructure in December 2020 with the dual objectives of encouraging local entrepreneurs to become Public Data Offices (PDOs) and offering citizens affordable high-speed Wi-Fi Internet service. However, the scheme has so far met with limited success. The sustainability of these PDOs is critical for the success of the program. We develop an Agent-Based Model of the WANI ecosystem by incorporating the Bass diffusion model for users’ adoption of Internet data service offered by PDOs. Our simulations indicate that offering a one-time subsidy, capping the market share of PDOs, and fixing a lower Internet backhaul tariff will lead to more sustainable and competitive Wi-Fi markets.

Analysing the Effects of Paid Subscriptions on User Engagement in Social Media Platforms

This study investigates the effects of paid subscriptions on revenue and user engagement on social media platforms, focusing on Instagram. By leveraging Network Externality Theory, Customer Engagement Theory, and Uses and Gratifications Theory, the research explores how paid subscriptions impact network effects, user base growth, and emotional and behavioural engagement. A longitudinal analysis of 146,942 Instagram comments reveals a predominantly positive sentiment towards paid subscriptions, with users expressing high levels of appreciation and satisfaction. The study identifies key themes such as positive engagement, content quality and constructive feedback. Findings suggest that paid subscriptions enhance platform attractiveness and user interaction, driving increased engagement and revenue growth. This research provides valuable insights for platform developers and content creators, highlighting the importance of continuous monitoring and responsiveness to user feedback.