Cloud Service Recommendation with Bi-LSTM and GLDA Based Approach

With the rapid growth of cloud computing and the increasing number of cloud services available, the accurately selecting and recommending cloud service has become a challenging task for users. Traditional methods based on text classification and topic modeling have limitations in handling the diverse range of cloud services. To overcome these challenges, this paper proposes a novel approach that combines Gaussian Latent Dirichlet Allocation (GLDA) and attention mechanisms to enhance the accuracy and effectiveness of cloud service's selection and recommendation. GLDA captures the continuity and relevance between words, improving topic modeling. The attention mechanisms focus on relevant tag fragments to guide attention toward content related to cloud services. By combining GLDA and attention mechanisms, our method offers advantages in semantic information and precise recommendations. This paper provides a promising solution to improve the selection and recommendation of cloud services, offering users a better experience.