ZS-CEBE: leveraging zero-shot cross and bi-encoder architecture for cold-start news recommendation

News recommendation systems heavily rely on the information exchange between news articles and users to personalize the recommendation. Consequently, one of the significant challenges is the cold-start problem in news recommendation models, referring to the low accuracy of recommendations for new users due to a lack of interaction data. This study addresses the cold-start challenge in news recommendation systems by introducing a novel zero-shot-based approach. The ZS-CEBE approach presented in this paper utilizes a rarely explored zero-shot paradigm to effectively tackle the cold-start problem in news recommendations. The methodology incorporates two crucial models: the fine-tuned Cross-Encoder and a Bi-Encoder model. The cross-encoder captures user-news interactions, predicting the likelihood of user engagement with a news article. Subsequently, the bi-encoder, designed for swift inference, precomputes embeddings for users and articles and calculates their relevance during predictions. The proposed technique is applicable to various neural news recommendation systems and is empirically evaluated using real-world benchmark datasets MIND and Adressa. The experimental results demonstrate that ZS-CEBE outperforms baseline methods in terms of nDCG@k, AUC, and MRR, both in cold-start scenarios and regular user-news interaction situations. This underscores the efficacy of the zero-shot approach in mitigating the cold-start dilemma and improving overall recommendation system performance