This paper presents Deep Cooperative Neural Networks (DeepCoNN), a deep learning model designed to jointly learn item properties and user behaviors from review text for recommendation systems. DeepCoNN consists of two parallel neural networks, each focusing on learning user behaviors and item properties, respectively. These networks are coupled through a shared layer that enables latent factors learned for users and items to interact with each other, similar to factorization machine techniques. The model leverages pre-trained word embeddings to capture the semantic meaning of review text, enhancing the accuracy of rating predictions. Experimental results on various datasets, including Yelp, Amazon, and Beer, demonstrate that DeepCoNN significantly outperforms baseline recommender systems, particularly in scenarios with few ratings, thus effectively alleviating the sparsity problem. The proposed model is scalable and suitable for online learning, making it a valuable contribution to the field of recommender systems.This paper presents Deep Cooperative Neural Networks (DeepCoNN), a deep learning model designed to jointly learn item properties and user behaviors from review text for recommendation systems. DeepCoNN consists of two parallel neural networks, each focusing on learning user behaviors and item properties, respectively. These networks are coupled through a shared layer that enables latent factors learned for users and items to interact with each other, similar to factorization machine techniques. The model leverages pre-trained word embeddings to capture the semantic meaning of review text, enhancing the accuracy of rating predictions. Experimental results on various datasets, including Yelp, Amazon, and Beer, demonstrate that DeepCoNN significantly outperforms baseline recommender systems, particularly in scenarios with few ratings, thus effectively alleviating the sparsity problem. The proposed model is scalable and suitable for online learning, making it a valuable contribution to the field of recommender systems.