User Content Information Research Articles

Network embedding enhanced intelligent recommendation for online social networks

With the fast development of Internet technology, more and more online social networks are changing our daily life. Whether or not an accurate recommendation can be provided for each user in the massive amount of information directly affects the user’s enthusiasm for receiving network services and the user experience effect, which in turn determines the user’s participation and loyalty to network applications. However, most previous methods only use a single network topology information and ignore other auxiliary information (such as user content information). Moreover, how to deal with large scale network is a challenging task. To tackle these challenges, we propose a topic-aware network embedding approach for providing intelligent recommendation services. Specifically, we first extract the network topology based on the constructed social network. Then, we extract the topic information based on the context released by the users with the help of topic model. Finally, a topic-aware network embedding framework is utilized for recommendation. Experimental results on two-widely used dataset demonstrate that our method can achieve the best performance.

Making recommendations using transfer learning

Deep learning-based recommender systems have gained much attention due to the advantage of encoding content-based information, such as user textual reviews and item descriptions, images, or videos, without the trouble of manually crafting feature vectors. However, those systems are trained from scratch with randomly initialized parameters, where the training process can take a long time to converge. With the most recent breakthroughs in Natural Language Processing using transfer learning, pre-trained transformer-based models now provide a better foundation for textual information encoding. This inspires us to propose a transformer-based recommender system using transfer learning. As the first core contribution in this work, we apply transfer learning to the system, by fine-tuning the pre-trained transformer models for information encoding. The experiment result shows that the proposed system outperforms several other deep learning-based recommender systems on multiple datasets. As the second core contribution, we propose a novel user vector encoding algorithm that assists all the models to achieve a better performance, when the user content information is not available.

AIRC: Attentive Implicit Relation Recommendation Incorporating Content Information for Bipartite Graphs

With users being exposed to the growing volume of online information, the recommendation system aiming at mining the important or interesting information is becoming a modern research topic. One approach of recommendation is to integrate the graph neural network with deep learning algorithms. However, some of them are not tailored for bipartite graphs, which is a unique type of heterogeneous graph having two entity types. Others, though customized, neglect the importance of implicit relation and content information. In this paper, we propose the attentive implicit relation recommendation incorporating content information (AIRC) framework that is designed for bipartite graphs based on the GC–MC algorithm. First, through reconstructing the bipartite graphs, we obtain the implicit relation graphs. Then we analyze the content information of users and items with a CNN process, so that each user and item has its feature-tailored embeddings. Besides, we expand the GC–MC algorithms by adding a graph attention mechanism layer, which handles the implicit relation graph by highlighting important features and neighbors. Therefore, our framework takes into consideration both the implicit relation and content information. Finally, we test our framework on Movielens dataset and the results show that our framework performs better than other state-of-art recommendation algorithms.

A Distributed Hybrid Community Detection Methodology for Social Networks

Nowadays, the amount of digitally available information has tremendously grown, with real-world data graphs outreaching the millions or even billions of vertices. Hence, community detection, where groups of vertices are formed according to a well-defined similarity measure, has never been more essential affecting a vast range of scientific fields such as bio-informatics, sociology, discrete mathematics, nonlinear dynamics, digital marketing, and computer science. Even if an impressive amount of research has yet been published to tackle this NP-hard class problem, the existing methods and algorithms have virtually been proven inefficient and severely unscalable. In this regard, the purpose of this manuscript is to combine the network topology properties expressed by the loose similarity and the local edge betweenness, which is a currently proposed Girvan–Newman’s edge betweenness measure alternative, along with the intrinsic user content information, in order to introduce a novel and highly distributed hybrid community detection methodology. The proposed approach has been thoroughly tested on various real social graphs, roundly compared to other classic divisive community detection algorithms that serve as baselines and practically proven exceptionally scalable, highly efficient, and adequately accurate in terms of revealing the subjacent network hierarchy.

Personalized ranking with pairwise Factorization Machines

Pairwise learning is a vital technique for personalized ranking with implicit feedback. Given the assumption that each user is more interested in items which have been previously selected by the user than the remaining ones, pairwise learning algorithms can well learn users’ preference, from not only the observed user feedbacks but also the underlying interactions between users and items. However, a mass of training instances are randomly derived according to such assumption, which makes the learning procedure often converge slowly and even result in poor predictive models. In addition, the cold start problem often perplexes pairwise learning methods, since most of traditional methods in personalized ranking only take explicit ratings or implicit feedbacks into consideration. For dealing with the above issues, this work proposes a novel personalized ranking model which incorporates implicit feedback with content information by making use of Factorization Machines. For efficiently estimating the parameters of the proposed model, we develop an adaptive sampler to draw informative training instances based on content information of users and items. The experimental results show that our adaptive item sampler indeed can speed up our model, and our model outperforms advanced methods in personalized ranking.

A web recommendation system considering sequential information

With the rapid growth of information technology, the current era is witnessing an exponential increase in the generation and collection of web data. Projecting the right information to the right person is becoming more difficult day by day, which in turn adds complexity to the decision making process. Recommendation systems are intelligent systems that address this issue. They are widely used in e-commerce websites to recommend products to users. Most of the popular recommendation systems consider only the content information of users and ignore sequential information. Sequential information also provides useful insights about the behavior of users. We have developed a novel system that considers sequential information present in web navigation patterns, along with content information. We also consider soft clusters during clustering, which helps in capturing the multiple interests of users. The proposed system has utilized similarity upper approximation and singular value decomposition (SVD) for the generation of recommendations for users. We tested our approach on three datasets, the MSNBC benchmark dataset, simulated dataset and CTI dataset. We compared our approach with the first order Markov model as well as random prediction model. The results validate the viability of our approach.