User representation learning is crucial for capturing different user preferences,but it is also critical challenging because user intentions are latent and dispersed in complex and different patterns of user-generated...User representation learning is crucial for capturing different user preferences,but it is also critical challenging because user intentions are latent and dispersed in complex and different patterns of user-generated data,and thus cannot be measured directly.Text-based data models can learn user representations by mining latent semantics,which is beneficial to enhancing the semantic function of user representations.However,these technologies only extract common features in historical records and cannot represent changes in user intentions.However,sequential feature can express the user’s interests and intentions that change time by time.But the sequential recommendation results based on the user representation of the item lack the interpretability of preference factors.To address these issues,we propose in this paper a novel model with Dual-Layer User Representation,named DLUR,where the user’s intention is learned based on two different layer representations.Specifically,the latent semantic layer adds an interactive layer based on Transformer to extract keywords and key sentences in the text and serve as a basis for interpretation.The sequence layer uses the Transformer model to encode the user’s preference intention to clarify changes in the user’s intention.Therefore,this dual-layer user mode is more comprehensive than a single text mode or sequence mode and can effectually improve the performance of recommendations.Our extensive experiments on five benchmark datasets demonstrate DLUR’s performance over state-of-the-art recommendation models.In addition,DLUR’s ability to explain recommendation results is also demonstrated through some specific cases.展开更多
BACKGROUND: We compare educational environments(i.e. physical, emotional and intellectual experiences) of emergency medicine(EM) residents training in the United States of America(USA) and Saudi Arabia(SA).METHODS: A ...BACKGROUND: We compare educational environments(i.e. physical, emotional and intellectual experiences) of emergency medicine(EM) residents training in the United States of America(USA) and Saudi Arabia(SA).METHODS: A cross-sectional survey study was conducted using an adapted version of the validated Postgraduate Hospital Educational Environment Measure(PHEEM) survey instrument from April 2015 through June 2016 to compare educational environments in all emergency medicine residency programs in SA and three selected programs in the USA with a history of training Saudi physicians. Overall scores were compared across programs, and for subscales(autonomy, teaching, and social Support), using chi-squared, t-tests, and analysis of variance.RESULTS: A total of 219 surveys were returned for 260 residents across six programs(3 SA, 3 USA), with a response rate of 84%. Program-specific response rates varied from 79%–100%. All six residencies were qualitatively rated as "more positive than negative but room for improvement". Quantitative PHEEM scores for the USA programs were significantly higher: 118.7 compared to 109.9 for SA, P=0.001. In subscales, perceptions of social support were not different between the two countries(P=0.243); however, role autonomy(P<0.001) and teaching(P=0.005) were better in USA programs. There were no significant differences by post-graduate training year.CONCLUSION: EM residents in all three emergency medicine residency programs in SA and the three USA programs studied perceive their training as high quality in general, but with room for improvements. USA residency programs scored higher in overall quality. This was driven by more favorable perceptions of role autonomy and teaching. Understanding how residents perceive their programs may help drive targeted quality improvement efforts.展开更多
基金supported by the Applied Research Center of Artificial Intelligence,Wuhan College(Grant Number X2020113)the Wuhan College Research Project(Grant Number KYZ202009).
文摘User representation learning is crucial for capturing different user preferences,but it is also critical challenging because user intentions are latent and dispersed in complex and different patterns of user-generated data,and thus cannot be measured directly.Text-based data models can learn user representations by mining latent semantics,which is beneficial to enhancing the semantic function of user representations.However,these technologies only extract common features in historical records and cannot represent changes in user intentions.However,sequential feature can express the user’s interests and intentions that change time by time.But the sequential recommendation results based on the user representation of the item lack the interpretability of preference factors.To address these issues,we propose in this paper a novel model with Dual-Layer User Representation,named DLUR,where the user’s intention is learned based on two different layer representations.Specifically,the latent semantic layer adds an interactive layer based on Transformer to extract keywords and key sentences in the text and serve as a basis for interpretation.The sequence layer uses the Transformer model to encode the user’s preference intention to clarify changes in the user’s intention.Therefore,this dual-layer user mode is more comprehensive than a single text mode or sequence mode and can effectually improve the performance of recommendations.Our extensive experiments on five benchmark datasets demonstrate DLUR’s performance over state-of-the-art recommendation models.In addition,DLUR’s ability to explain recommendation results is also demonstrated through some specific cases.
文摘BACKGROUND: We compare educational environments(i.e. physical, emotional and intellectual experiences) of emergency medicine(EM) residents training in the United States of America(USA) and Saudi Arabia(SA).METHODS: A cross-sectional survey study was conducted using an adapted version of the validated Postgraduate Hospital Educational Environment Measure(PHEEM) survey instrument from April 2015 through June 2016 to compare educational environments in all emergency medicine residency programs in SA and three selected programs in the USA with a history of training Saudi physicians. Overall scores were compared across programs, and for subscales(autonomy, teaching, and social Support), using chi-squared, t-tests, and analysis of variance.RESULTS: A total of 219 surveys were returned for 260 residents across six programs(3 SA, 3 USA), with a response rate of 84%. Program-specific response rates varied from 79%–100%. All six residencies were qualitatively rated as "more positive than negative but room for improvement". Quantitative PHEEM scores for the USA programs were significantly higher: 118.7 compared to 109.9 for SA, P=0.001. In subscales, perceptions of social support were not different between the two countries(P=0.243); however, role autonomy(P<0.001) and teaching(P=0.005) were better in USA programs. There were no significant differences by post-graduate training year.CONCLUSION: EM residents in all three emergency medicine residency programs in SA and the three USA programs studied perceive their training as high quality in general, but with room for improvements. USA residency programs scored higher in overall quality. This was driven by more favorable perceptions of role autonomy and teaching. Understanding how residents perceive their programs may help drive targeted quality improvement efforts.
