UP-TreeRec: Building Dynamic User Profiles Tree for News Recommendation

Online news recommendation systems aim to address the information explosion of news and make personalized recommendations for users. The key problem of personalized news recommendation is to model users' interests and track their changes. A common way to deal with the user modeling problem is to build user profiles from observed behavior. However, the majority of existing methods make static representations of user profiles and little research has focused on effective user modeling that could dynamically capture user interests in news topics. To address this problem, in this paper, we propose UP-TreeRec, a news recommendation framework based on a user profile tree(UP-Tree), which is a novel framework combining content-based and collaborative filtering techniques. First, by exploiting a novel topic model namely UILDA, we obtain the representation vectors for news content in a topic space as the fundamental bridge to associate user interests with news topics. Next, we design a decision tree with a dynamically changeable structure to construct a user interest profile from the user's feedback. Furthermore, we present a clustering-based multidimensional similarity computation method to select the nearest neighbor of the UP-Tree efficiently. We also provide a Map-Reduce framework-based implemen-tation that enables scaling our solution to real-world news recommendation problems. We conducted several experiments compared to the state-of-the-art approaches on real-world datasets and the experimental results demonstrate that our approach significantly improves accuracy and effectiveness in news recommendation.

Study on the Migration Mechanism of Typical Characteristic Pollutants in Coking Enterprises

Groundwater pollution in north China is serious, which is mostly caused by complex factors. Aiming at the problems such as the unknown reasons for the differences in the migration characteristics of typical characteristic pollutants in the same medium and the unknown migration rules of complex pollutants in soil and groundwater, this paper selected a single sample and a mixed sample of typical characteristic pollutants in coking enterprises to carry out the static adsorption test. The results showed that the distribution coefficients of benzene series and aromatic hydrocarbon pollutants in soil-water were K_(d)benzene >K_(d)toluene >K_(d)ethylbenzene >K_(d)pyrene >K_(d)anthracene >K_(d)naphthene, and the distribution coefficients of ammonia nitrogen, phenols and cyanogen were K_(d)ammonia nitrogen >K_(d)phenols >K_(d)cyanogen. The overall distribution coefficient of benzene series was higher than that of PAHs, and it was easier to be adsorbed by silty loam. Different carbon and hydrogen mass and even electron distribution of typical characteristic pollutants led to differences in the migration characteristics of benzene and aromatic pollutants. The more carbon and hydrogen there were, the more even the electron distribution was, and the more difficult it was to migrate in the soil. Among the same kind of pollutants, the migration of complex pollutants was weaker than that of single pollutants. The research could provide the parameter basis for establishing the solute transport model of groundwater and the design basis for developing the related risk control and pollution prevention strategies.