We propose an indirect-link-weakened mass diffusion method（IMD）, by considering the indirect linkage and the source object heterogeneity effect in the mass diffusion（MD） recommendation method. Experimental results...We propose an indirect-link-weakened mass diffusion method（IMD）, by considering the indirect linkage and the source object heterogeneity effect in the mass diffusion（MD） recommendation method. Experimental results on the MovieLens, Netflix, and RYM datasets show that, the IMD method greatly improves both the recommendation accuracy and diversity, compared with a heterogeneity-weakened MD method（HMD）, which only considers the source object heterogeneity. Moreover, the recommendation accuracy of the cold objects is also better elevated in the IMD than the HMD method. It suggests that eliminating the redundancy induced by the indirect linkages could have a prominent effect on the recommendation efficiency in the MD method.展开更多
Reviewing the existing environmental policies in Western China,we find that:in time sequence,the characteristics of China's western environmental policies shift from"development drive governance"to the f...Reviewing the existing environmental policies in Western China,we find that:in time sequence,the characteristics of China's western environmental policies shift from"development drive governance"to the full implementation of environmental protection and construction;and in spatial sequence,the ecological,social,and economic development of Western China reach to coordination through the nature reserve setting,ecological migrants,fiscal transfer payment and differentiated ecological environmental policies.Due to the implementation of the policies and projects,environmental degradation trends in the western ecological environment were alleviated significantly,the living conditions of farmers and herdsmen were improved,and many successful experiences were explored.However,future ecological environmental construction in Western China requires further improvement in integrated planning,eco-compensation mechanism,and policy assessment.This paper concludes with specific recommendations such as drawing up ecological environment construction planning,strengthening environmental law enforcement and incentive mechanisms,improving policy assessment and scientific support,enhancing environmental protection capacity,improving eco-compensation mechanism,and refining the environmental policies for key areas.展开更多
The anchoring effect is a powerful and widespread cognitive phenomenon in the decision-making field.Our quantitative analysis of a sample of 520 sentences indicates that the sentencing recommendation of the public pro...The anchoring effect is a powerful and widespread cognitive phenomenon in the decision-making field.Our quantitative analysis of a sample of 520 sentences indicates that the sentencing recommendation of the public procuratorate has a marked influence upon the court＇s sentencing judgment.That is,whether we are investigating the freedom penalty,the fine penalty or the term of probation imposed by the judge,we find that the anchoring effect does exist.In addition,a change in the court conviction or in the trial sentencing circumstances and the availability of a defense lawyer may weaken the anchoring effect of the procuratorate＇s sentencing recommendations.As a form of cognitive bias,the presence of the anchoring effect in the area of sentencing further highlights the necessity of applying analyses based on legal realism to the field of criminal justice in China;and at the institutional level,it demands that judges adopt corresponding arrangements to ensure the impartial exercise of discretion.展开更多
A travel recommendation system based on social media activity provides a customized place of interest to accommodate user-specific needs and preferences. In general, the user’s inclination towards travel destinations...A travel recommendation system based on social media activity provides a customized place of interest to accommodate user-specific needs and preferences. In general, the user’s inclination towards travel destinations is subject to change over time. In this project, we have analyzed users’ twitter data, as well as their friends and followers in a timely fashion to understand recent travel interest. A machine learning classifier identifies tweets relevant to travel. The travel tweets are then used to obtain personalized travel recommendations. Unlike most of the personalized recommendation systems, our proposed model takes into account a user’s most recent interest by incorporating time-sensitive recency weight into the model. Our proposed model has outperformed the existing personalized place of interest recommendation model, and the overall accuracy is 75.23%.展开更多
Next point-of-interest(POI)recommendation is an important personalized task in location-based social networks(LBSNs)and aims to recommend the next POI for users in a specific situation with historical check-in data.St...Next point-of-interest(POI)recommendation is an important personalized task in location-based social networks(LBSNs)and aims to recommend the next POI for users in a specific situation with historical check-in data.State-of-the-art studies linearly discretize the user’s spatiotemporal information and then use recurrent neural network(RNN)based models for modeling.However,these studies ignore the nonlinear effects of spatiotemporal information on user preferences and spatiotemporal correlations between user trajectories and candidate POIs.To address these limitations,a spatiotemporal trajectory(STT)model is proposed in this paper.We use the long short-term memory(LSTM)model with an attention mechanism as the basic framework and introduce the user’s spatiotemporal information into the model in encoding.In the process of encoding information,an exponential decay factor is applied to reflect the nonlinear drift of user interest over time and distance.In addition,we design a spatiotemporal matching module in the process of recalling the target to select the most relevant POI by measuring the relevance between the user’s current trajectory and the candidate set.We evaluate the performance of our STT model with four real-world datasets.Experimental results show that our model outperforms existing state-of-the-art methods.展开更多
基金Project supported by the National Natural Science Foundation of China(Grant No.11175079)the Young Scientist Training Project of Jiangxi Province,China(Grant No.20133BCB23017)
文摘We propose an indirect-link-weakened mass diffusion method（IMD）, by considering the indirect linkage and the source object heterogeneity effect in the mass diffusion（MD） recommendation method. Experimental results on the MovieLens, Netflix, and RYM datasets show that, the IMD method greatly improves both the recommendation accuracy and diversity, compared with a heterogeneity-weakened MD method（HMD）, which only considers the source object heterogeneity. Moreover, the recommendation accuracy of the cold objects is also better elevated in the IMD than the HMD method. It suggests that eliminating the redundancy induced by the indirect linkages could have a prominent effect on the recommendation efficiency in the MD method.
基金financially supported by the"Strategy and Policies on Environment and Development in Western China"project
文摘Reviewing the existing environmental policies in Western China,we find that:in time sequence,the characteristics of China's western environmental policies shift from"development drive governance"to the full implementation of environmental protection and construction;and in spatial sequence,the ecological,social,and economic development of Western China reach to coordination through the nature reserve setting,ecological migrants,fiscal transfer payment and differentiated ecological environmental policies.Due to the implementation of the policies and projects,environmental degradation trends in the western ecological environment were alleviated significantly,the living conditions of farmers and herdsmen were improved,and many successful experiences were explored.However,future ecological environmental construction in Western China requires further improvement in integrated planning,eco-compensation mechanism,and policy assessment.This paper concludes with specific recommendations such as drawing up ecological environment construction planning,strengthening environmental law enforcement and incentive mechanisms,improving policy assessment and scientific support,enhancing environmental protection capacity,improving eco-compensation mechanism,and refining the environmental policies for key areas.
基金Supported by the Philosophy and Social Sciences Foundation of Shanghai(No.:2017BFX001)Shanghai’s Outstanding Young Talents Projects
文摘The anchoring effect is a powerful and widespread cognitive phenomenon in the decision-making field.Our quantitative analysis of a sample of 520 sentences indicates that the sentencing recommendation of the public procuratorate has a marked influence upon the court＇s sentencing judgment.That is,whether we are investigating the freedom penalty,the fine penalty or the term of probation imposed by the judge,we find that the anchoring effect does exist.In addition,a change in the court conviction or in the trial sentencing circumstances and the availability of a defense lawyer may weaken the anchoring effect of the procuratorate＇s sentencing recommendations.As a form of cognitive bias,the presence of the anchoring effect in the area of sentencing further highlights the necessity of applying analyses based on legal realism to the field of criminal justice in China;and at the institutional level,it demands that judges adopt corresponding arrangements to ensure the impartial exercise of discretion.
文摘A travel recommendation system based on social media activity provides a customized place of interest to accommodate user-specific needs and preferences. In general, the user’s inclination towards travel destinations is subject to change over time. In this project, we have analyzed users’ twitter data, as well as their friends and followers in a timely fashion to understand recent travel interest. A machine learning classifier identifies tweets relevant to travel. The travel tweets are then used to obtain personalized travel recommendations. Unlike most of the personalized recommendation systems, our proposed model takes into account a user’s most recent interest by incorporating time-sensitive recency weight into the model. Our proposed model has outperformed the existing personalized place of interest recommendation model, and the overall accuracy is 75.23%.
文摘Next point-of-interest(POI)recommendation is an important personalized task in location-based social networks(LBSNs)and aims to recommend the next POI for users in a specific situation with historical check-in data.State-of-the-art studies linearly discretize the user’s spatiotemporal information and then use recurrent neural network(RNN)based models for modeling.However,these studies ignore the nonlinear effects of spatiotemporal information on user preferences and spatiotemporal correlations between user trajectories and candidate POIs.To address these limitations,a spatiotemporal trajectory(STT)model is proposed in this paper.We use the long short-term memory(LSTM)model with an attention mechanism as the basic framework and introduce the user’s spatiotemporal information into the model in encoding.In the process of encoding information,an exponential decay factor is applied to reflect the nonlinear drift of user interest over time and distance.In addition,we design a spatiotemporal matching module in the process of recalling the target to select the most relevant POI by measuring the relevance between the user’s current trajectory and the candidate set.We evaluate the performance of our STT model with four real-world datasets.Experimental results show that our model outperforms existing state-of-the-art methods.
