A Personalized Collaborative Filtering Recommendation System Based on Bi-Graph Embedding and Causal Reasoning.

The integration of graph embedding technology and collaborative filtering algorithms has shown promise in enhancing the performance of recommendation systems. However, existing integrated recommendation algorithms often suffer from feature bias and lack effectiveness in personalized user recommendation. For instance, users' historical interactions with a certain class of items may inaccurately lead to recommendations of all items within that class, resulting in feature bias. Moreover, accommodating changes in user interests over time poses a significant challenge. This study introduces a novel recommendation model, RCKFM, which addresses these shortcomings by leveraging the CoFM model, TransR graph embedding model, backdoor tuning of causal inference, KL divergence, and the factorization machine model. RCKFM focuses on improving graph embedding technology, adjusting feature bias in embedding models, and achieving personalized recommendations. Specifically, it employs the TransR graph embedding model to handle various relationship types effectively, mitigates feature bias using causal inference techniques, and predicts changes in user interests through KL divergence, thereby enhancing the accuracy of personalized recommendations. Experimental evaluations conducted on publicly available datasets, including "MovieLens-1M" and "Douban dataset" from Kaggle, demonstrate the superior performance of the RCKFM model. The results indicate a significant improvement of between 3.17% and 6.81% in key indicators such as precision, recall, normalized discount cumulative gain, and hit rate in the top-10 recommendation tasks. These findings underscore the efficacy and potential impact of the proposed RCKFM model in advancing recommendation systems.

Associations of dietary habits, physical activity and cognitive views with gestational diabetes mellitus among Chinese women.

OBJECTIVE: To evaluate the relationship between dietary habits, physical activity and cognitive views and the risk of gestational diabetes mellitus (GDM) in Chinese women. DESIGN: A cross-sectional study to explore the potential risk factors of GMD through the International Physical Activity Questionnaire, an FFQ and a self-designed structured questionnaire, respectively. SETTING: Guangzhou, Guangdong Province, China. SUBJECTS: Chinese pregnant women (n 571) who underwent a 75-g oral glucose tolerance test at their 24th to 28th gestational week. RESULTS: Thirteen per cent of the investigated women were identified as having GDM, and an increased intake of local featured foods and lower physical activity were observed in the GDM-positive group v. the GDM-negative group. Women who regarded early-pregnancy morning sickness as relevant to fetal abnormalities and those with unlimited dietary intake after the ending of morning sickness both had an increased risk for GDM (P = 0·018 and P = 0·038, respectively). After multiple logistic regression analysis, cognitive views for unlimited food intake subsequent to morning sickness, increased consumption of energy-dense snack foods and high-glycaemic-index fruits were strongly associated with the risk of GDM (OR = 1·911, P = 0·032; OR = 1·050, P = 0·001; and OR = 1·002, P = 0·017, respectively). CONCLUSIONS: Local featured foods and incorrect cognitive views on pregnancy-related health were closely related to the risk of GDM in Chinese women. Intensive health education about pregnancy physiology and reasonable dietary and physical exercise behaviours should be strengthened for the control of GDM.