Wyniki wyszukiwania - BazTech

Ograniczanie wyników

1 Computer Assisted Methods in Engineering and Science

1 2024

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: sentiment transfer network

Sortuj według:

Ogranicz wyniki do:

STN-CDRS: Sentiment Transfer Network for Cross-Domain Recommendation Systems

Taneja Nikita, Thakur Hardeo Kumar

Computer Assisted Methods in Engineering and Science

2024

Vol. 31, no. 3

389--415

In enterprise environments, the products may come from a variety of categories or do-mains. Users may engage with entities in one domain, but not in the others when theyare presented with multiple domains. Such users are referred to as “cold-starters” in otherdomains. The primary difficulty in cross-domain recommendation systems is to efficientlytransfer user’s latent information based on their engagements in one domain into theother domains. The advancements in recommendation systems have inspired us to de-velop review-driven recommendation models that utilize cross-domain knowledge transferand deep learning models. This work proposes a sentiment transfer network specificallydesigned for providing recommendation in cross-domain (STN-CDRS). The novelty of thework lies in the user rating enrichment mechanism, which is done by extracting latentinformation from user review data to fill sparse rating matrix. This enrichment uses pre-viously developed RNN-Core method for efficiently learning user reviews. The reviewsprovided by the users are used to enrich sparse data across domains. This enrichmentallows two things: alleviates the cold start problem and allows more intersecting usersacross domains to bridge the gap while learning. This work empirically demonstrates itsefficiency by iteratively updating over the baseline recommendation models in terms ofMAE (mean absolute error), RMSD (root mean squared deviation), precision and recallmeasures with other state-of-the-art-review-aided cross-domain recommendation systems.