Evolving Hierarchical and Tag Information via the Deeply Enhanced Weighted Non-Negative Matrix Factorization of Rating Predictions

Abstract

Identifying the hidden features of items and users of a modern recommendation system, wherein features are represented as hierarchical structures, allows us to understand the association between the two entities. Moreover, when tag information that is added to items by users themselves is coupled with hierarchically structured features, the rating prediction efficiency and system personalization are improved. To this effect, we developed a novel model that acquires hidden-level hierarchical features of users and items and combines them with the tag information of items that regularizes the matrix factorization process of a basic weighted non-negative matrix factorization (WNMF) model to complete our prediction model. The idea behind the proposed approach was to deeply factorize a basic WNMF model to obtain hidden hierarchical features of user’s preferences and item characteristics that reveal a deep relationship between them by regularizing the process with tag information as an auxiliary parameter. Experiments were conducted on the MovieLens 100K dataset, and the empirical results confirmed the potential of the proposed approach and its superiority over models that use the primary features of users and items or tag information separately in the prediction process.

Improved Real-Time Fire Warning System Based on Advanced Technologies for Visually Impaired People

“…Because the source codes and datasets for these approaches are not publicly available, we used the results in their publications for comparison; however, we are unsure of their veracity. As in our previous studies [ 31 , 32 , 33 , 34 , 35 ], we calculated the F-measure (FM), precision, and recall. The FM score is a weighted average that equalizes the measurements of the recall rates and precision.…”

Assessing Methods for Evaluating the Number of Components in Non-Negative Matrix Factorization

“…Indeed, these developments include extensions of NMF that include sparseness constraints so that over-complete data can be modeled [51], new divergence measures [52][53][54], and multiple algorithms to address signal-dependent noise [55]. Others have examined NMF extensions on the basis of sparseness and other constraints for graphical analysis [56] and deeply enhanced weighted NMF [57]. Even more recent work has leveraged NMF in the context of deep learning [58][59][60].…”

Deep-Sequence–Aware Candidate Generation for e-Learning System

“…Regarding user history, Zhao et al [17] developed a product recommender system that considers the time interval between purchased products. Moreover, several studies have integrated different sources of information simultaneously into the prediction process [1,18,19].…”

“…Therefore, web service providers have been utilizing recommendation systems that analyze and harness user-item interactions to improve customer satisfaction and personalized recommendations and increase the income interests of their services. Moreover, with the development of deep-learning and machine-learning technologies, recommendation systems have become an integral part of multi-billion business organizations such as Amazon and Alibaba [1]. During the early development stages of recommendation systems, most recommendation models were based on the similarity concept.…”

“…During the early development stages of recommendation systems, most recommendation models were based on the similarity concept. For example, the correlation (cosine similarity (1) or Pearson correlation (2)) of each item or user was calculated using historical data or content information, and items with higher correlations shared the same history that was not observed in the other item.…”