Microblog User Recommendation Based on Particle Swarm Optimization

Considering that there exists a strong similarity between behaviors of users and intelligence of swarm of agents,in this paper we propose a novel user recommendation strategy based on particle swarm optimization(PSO)for Microblog network. Specifically,a PSO-based algorithm is developed to learn the user influence,where not only the number of followers is incorporated,but also the interactions among users(e.g.,forwarding and commenting on other users' tweets). Three social factors,the influence and the activity of the target user,together with the coherence between users,are fused to improve the performance of proposed recommendation strategy. Experimental results show that,compared to the well-known Page Rank-based algorithm,the proposed strategy performs much better in terms of precision and recall and it can effectively avoid a biased result caused by celebrity effect and zombie fans effect.

BPR-UserRec:a personalized user recommendation method in social tagging systems

Social tagging is one of the most important characteristics of Web 2.0 services, and social tagging systems （STS） are becoming more and more popular for users to annotate, organize and share items on the Web. Moreover, online social network has been incorporated into social tagging systems. As more and more users tend to interact with real friends on the Web, personalized user recommendation service provided in social tagging systems is very appealing. In this paper, we propose a personalized user recommendation method, and our method handles not only the users＇ interest networks, but also the social network information. We empirically show that our method outperforms a state-of-the-art method on real dataset from Last.fro dataset and Douban.

A User-Recommendation Method Based on Social Media

User-analysis techniques are mainly used to recommend friends and information. This paper discusses the data characteristics of microblog users and describes a multidimensional user rec- ommendation algorithm that takes into account microblog length, relativity between microblog and users, and familiarity between users. The experimental results show that this multidi- mensional algorithm is more accurate than a traditional recom- mendation algorithm.

Time-Ordered Collaborative Filtering for News Recommendation

Faced with hundreds of thousands of news articles in the news websites,it is difficult for users to find the news articles they are interested in.Therefore,various news recommender systems were built.In the news recommendation,these news articles read by a user is typically in the form of a time sequence.However,traditional news recommendation algorithms rarely consider the time sequence characteristic of user browsing behaviors.Therefore,the performance of traditional news recommendation algorithms is not good enough in predicting the next news article which a user will read.To solve this problem,this paper proposes a time-ordered collaborative filtering recommendation algorithm(TOCF),which takes the time sequence characteristic of user behaviors into account.Besides,a new method to compute the similarity among different users,named time-dependent similarity,is proposed.To demonstrate the efficiency of our solution,extensive experiments are conducted along with detailed performance analysis.

User Heterogeneity and Individualized Recommender

Previous works on personalized recommendation mostly emphasize modeling peoples＇ diversity in potential fa- vorites into a uniform recommender. However, these recommenders always ignore the heterogeneity of users at an individual level. In this study, we propose an individualized recommender that can satisfy every user with a customized parameter. Experimental results on four benchmark datasets demonstrate that the individualized recommender can significantly improve the accuracy of recommendation. The work highlights the importance of the user heterogeneity in recommender design.

Joint model of user check-in activities for point-of-interest recommendation

With the rapid development of location-based networks, point-of-interest（POI） recommendation has become an important means to help people discover interesting and attractive locations, especially when users travel out of town. However, because users only check-in interaction is highly sparse, which creates a big challenge for POI recommendation. To tackle this challenge, we propose a joint probabilistic generative model called geographical temporal social content popularity（GTSCP） to imitate user check-in activities in a process of decision making, which effectively integrates the geographical influence, temporal effect, social correlation, content information and popularity impact factors to overcome the data sparsity, especially for out-of-town users. Our proposed the GTSCP supports two recommendation scenarios in a joint model, i.e., home-town recommendation and out-of-town recommendation. Experimental results show that GTSCP achieves significantly superior recommendation quality compared to other state-of-the-art POI recommendation techniques.