Leveraging Sentiment Analysis of Consumer Feedback for Data-Driven CRM in Digital Game Ecosystems

Companies in the digital age rely on Customer Relationship Management (CRM) to build loyalty and keep users engaged. Traditionally built around structured inputs such as transactional logs or survey results, CRM systems are now challenged by the overwhelming influx of unstructured, experience-driven feedback from digital forums, review platforms, and social media. This sudden shift introduces feedback that is both high in emotional expressiveness and rich in feature-level granularity, posing significant interpretation challenges for legacy CRM workflows. This problem is obvious in the gaming industry, where users actively and continuously respond to game updates, service breakdowns, or balance issues through real-time public discourse. The domain-oriented tools are needed to manage this type of feedback to parse multi-dimensional opinion data. The proposed framework is specifically designed for gaming-related CRM applications. The current framework considers various online user reviews to process them through a dual pipeline architecture, considering the Removal of Personally Identifiable Information (PII), linguistic normalization, and ontology-driven tagging. The rule-based approach was used in the product pipeline using feature proximity. A hybrid NLP approach was employed for the service path. The sentiment tags were initialized by zero-shot RoBERTa, and a high-confidence-based fine-tuning was carried out using Sentiment140. Final predictions were reassigned and evaluated against pseudo-gold standards. Various interactive dashboards were designed to visualize the insights obtained from the framework, that asists CRM teams to act on player sentiment with feature-level and time-sensitive clarity.