Enhancing Topic Extraction in Recommender Systems with Entropy Regularization

Linking latent features with their semantic meanings can improve the interpretability of recommender systems [16]. In recent years, many recommender systems have Typically, topic modeling techniques are utilized to extract utilized textual data for topic extraction to enhance topics from textual data and align extracted topics to latent interpretability. However, our findings reveal a noticeable features. For example, [13] introduces an approach that combines deficiency in the coherence of keywords the traditional latent factor model with Latent Dirichlet within topics, resulting in low explainability of the Allocation (LDA) [3] to uncover topics correlated with the model. This paper introduces a novel approach latent factors of both products and users. On the other hand, called entropy regularization to address the issue, [12] adopts a convolutional neural network (CNN) to encode leading to more interpretable topics extracted from textual reviews into item embeddings. The convolutional kernels recommender systems, while ensuring that the performance are then utilized to extract topics that correspond to the of the primary task stays competitively latent factors of items.