{"ID":2831867,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.02372","arxiv_id":"2601.02372","title":"Improving News Recommendations through Hybrid Sentiment Modelling and Reinforcement Learning","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.","short_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 senti...","url_abs":"https://arxiv.org/abs/2601.02372","url_pdf":"https://arxiv.org/pdf/2601.02372v1","authors":"[\"Eunice Kingenga\",\"Mike Wa Nkongolo\"]","published":"2025-12-08T21:39:11Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}