Improving News Recommendations through Hybrid Sentiment Modelling and Reinforcement Learning

TL;DR

This paper presents a novel news recommendation system that combines hybrid sentiment analysis with reinforcement learning to improve personalization and adapt to users' emotional preferences.

Contribution

It introduces an integrated framework that uses hybrid sentiment scores within a reinforcement learning model to enhance news recommendation accuracy and user engagement.

Findings

The system effectively aligns article sentiment with user preferences.

Hybrid sentiment analysis improves robustness over single-method approaches.

Reinforcement learning enables continuous personalization adaptation.

Abstract

News recommendation systems rely on automated sentiment analysis to personalise content and enhance user engagement. Conventional approaches often struggle with ambiguity, lexicon inconsistencies, and limited contextual understanding, particularly in multi-source news environments. Existing models typically treat sentiment as a secondary feature, reducing their ability to adapt to users' affective preferences. To address these limitations, this study develops an adaptive, sentiment-aware news recommendation framework by integrating hybrid sentiment analysis with reinforcement learning. Using the BBC News dataset, a hybrid sentiment model combines VADER, AFINN, TextBlob, and SentiWordNet scores to generate robust article-level sentiment estimates. Articles are categorised as positive, negative, or neutral, and these sentiment states are embedded within a Q-learning architecture to guide the agent in learning optimal recommendation policies. The proposed system effectively identifies and recommends articles with aligned emotional profiles while continuously improving personalisation through iterative Q-learning updates. The results demonstrate that coupling hybrid sentiment modelling with reinforcement learning provides a feasible, interpretable, and adaptive approach for user-centred news recommendation.