Recommendation In Social Networks Research Articles

Trust-based Service Recommendation in Social Network

With the number of Web services increasing constantly on the Internet, how to recommend personalized Web services for users has become more and more important. At present, there emerged some service recommendation systems utilizing influence ranking and collaborative filtering algorithms in service r ecommendation. However, they neither considered trust relationships among users, nor deal with the cold start problem very well. Fortunately, the popularity of social network in nowadays brings a good alternative for service recommendation to avoid those. In this study, we propose a social network-based service-recommendation method, which considers users' history service invocation behaviors, us ers preferences as well as trust relationships among users i mplied in social network and users comments/reviews on services. We have applied this method in a data set extracted from www.epinions.com. A series of experiments on 86,719 users, 604,190 user trust-relationships and 963,591 reviews on 292,713 services/produces show that this recommendation method get better recall rate, precision, f-measure and rank score.

Incorporating Memory-Based Preferences and Point-of-Interest Stickiness into Recommendations in Location-Based Social Networks

In location-based social networks (LBSNs), point-of-interest (POI) recommendations facilitate access to information for people by recommending attractive locations they have not previously visited. Check-in data and various contextual factors are widely taken into consideration to obtain people’s preferences regarding POIs in existing POI recommendation methods. In psychological effect-based POI recommendations, the memory-based attenuation of people’s preferences with respect to POIs, e.g., the fact that more attention is paid to POIs that were checked in to recently than those visited earlier, is emphasized. However, the memory effect only reflects the changes in an individual’s check-in trajectory and cannot discover the important POIs that dominate their mobility patterns, which are related to the repeat-visit frequency of an individual at a POI. To solve this problem, in this paper, we developed a novel POI recommendation framework using people’s memory-based preferences and POI stickiness, named U-CF-Memory-Stickiness. First, we used the memory-based preference-attenuation mechanism to emphasize personal psychological effects and memory-based preference evolution in human mobility patterns. Second, we took the visiting frequency of POIs into consideration and introduced the concept of POI stickiness to identify the important POIs that reflect the stable interests of an individual with respect to their mobility behavior decisions. Lastly, we incorporated the influence of both memory-based preferences and POI stickiness into a user-based collaborative filtering framework to improve the performance of POI recommendations. The results of the experiments we conducted on a real LBSN dataset demonstrated that our method outperformed other methods.

Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey

Dynamic networks are used in a wide range of fields, including social network analysis, recommender systems, and epidemiology. Representing complex networks as structures changing over time allow network models to leverage not only structural but also temporal patterns. However, as dynamic network literature stems from diverse fields and makes use of inconsistent terminology, it is challenging to navigate. Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification. Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks. To address the challenges resulting from the fact that this research crosses diverse fields as well as to survey dynamic graph neural networks, this work is split into two main parts. First, to address the ambiguity of the dynamic network terminology we establish a foundation of dynamic networks with consistent, detailed terminology and notation. Second, we present a comprehensive survey of dynamic graph neural network models using the proposed terminology

Study on social network recommendation service method based on mobile cloud computing

In order to improve the recommendation ability of social network, the design method of social network recommendation service system based on mobile cloud computing is proposed. Design the topology ...

Location‐based social network recommendations with computational intelligence‐based similarity computation and user check‐in behavior

AbstractLocation recommending frameworks plays a very significant role in suggesting the users with new places to visit especially when users are visiting unfamiliar areas. Most of the existing recommender systems do not consider the fact that different users have different behavior while checking in. Some approaches do not consider the essential factors while providing recommendations. These systems lack adaptability and hence they provide poor recommendations. An adaptive approach to provide users with a personalized recommendation has been proposed in this paper. We have considered three features namely, user activeness feature, user similarity feature, and the spatial feature. In addition to this, we have also considered the location popularity for a given timeslot. We have divided the users into inactive and active based on the degree of activeness on social networks using fuzzy c‐means clustering. We have provided two strategies based on the activeness of the user. A two‐dimensional Gaussian kernel density estimation strategy is used for the active user. A one‐dimensional power‐law function strategy is used for inactive users. Moreover, we have integrated the time‐based popularity of the location and probability estimation based on the similarity between the users. To evaluate the proposed model, we have used a large‐scale Foursquare dataset.

Circle-based Group Recommendation in Social Networks

A large amount of data available on Web has proven to be an immense resource for innovative recommender system (RS) techniques and concepts. The traditional recommender system intended to provide recommendations for a single user. However, in certain domains the recommendation is required for a group of users. As to provide better recommendations for a group of users, we leverage the concept of circles in a network. In this work, we use the genetic algorithm (GA) K_Means clustering algorithm to generate social circles in a network. Then, we compute the status of each user in these overlapping circles. Finally, a circle-based group recommendation approach is used to generate the final group recommendation. The results obtained on the Epinions dataset validate the eminence of the proposed model over traditional approaches of group recommendation.

The Influence of Network Structural Preference on Link Prediction

Link prediction in complex networks predicts the possibility of link generation between two nodes that have not been linked yet in the network, based on known network structure and attributes. It can be applied in various fields, such as friend recommendation in social networks and prediction of protein-protein interaction in biology. However, in the social network, link prediction may raise concerns about privacy and security, because, through link prediction algorithms, criminals can predict the friends of an account user and may even further discover private information such as the address and bank accounts. Therefore, it is urgent to develop a strategy to prevent being identified by link prediction algorithms and protect privacy, utilizing perturbation on network structure at a low cost, including changing and adding edges. This article mainly focuses on the influence of network structural preference perturbation through deletion on link prediction. According to a large number of experiments on the various real networks, edges between large-small degree nodes and medium-medium degree nodes have the most significant impact on the quality of link prediction.

Vulnerabilities to Online Social Network Identity Deception Detection Research and Recommendations for Mitigation

Identity deception in online social networks is a pervasive problem. Ongoing research is developing methods for identity deception detection. However, the real-world efficacy of these methods is currently unknown because they have been evaluated largely through laboratory experiments. We present a review of representative state-of-the-art results on identity deception detection. Based on this analysis, we identify common methodological weaknesses for these approaches, and we propose recommendations that can increase their effectiveness for when they are applied in real-world environments.

Content-Based Bipartite User-Image Correlation for Image Recommendation

The popularity of online social curation networks takes benefits from its convenience to retrieve, collect, sort and share multimedia contents among users. With increasing content and user intent gap, effective recommendation becomes highly desirable for its further development. In this paper, we propose a content-based bipartite graph for image recommendation in social curation networks. Bipartite graph employs given sparse user-image interactions to infer user-image correlation for recommendation. Beside given user-image interactions, the user interacted visual content also reveals valuable user preferences. Visual content is embedded into the bipartite graph to extend the correlation density and the recommendation scope simultaneously. Furthermore, the content similarity is employed for recommendation reranking to improve the visual quality of recommended images. Experimental results demonstrate that the proposed method enhances the recommendation ability of the bipartite graph effectively.

Social Group Recommendation With TrAdaBoost

In recent years, group recommendation has become a research hotspot and focus in online social network community. Currently, several deep-learning-based approaches are leveraged to learn preferences of groups for items and predict the next items in which groups may be interested. Yet, their recommendation performance is still unsatisfactory due to the sparse group-item interactions. In order to address this problem, in this article, we introduce an effective model, namely Social Group Recommendation model with TrAdaBoost (SGRTAB), to raise the performance of group recommendation in online social networks. The SGRTAB model includes two stages: data preprocessing (DP) and model optimization (MO). In DP, SGRTAB produces inputs for MO and implements three related tasks: extracting individual features, handling group data via GloVe, and utilizing user contribute ratings to their own groups, whereas in MO, SGRTAB implements group preference learning with the assistance of user preference learning based on the TrAdaBoost algorithm. Specifically, SGRTAB can effectively absorb the knowledge of user preferences into the process of group preference learning through the idea of transferring-ensemble learning. Moreover, extensive experiments on four real-world data sets indicate that the proposed SGRTAB model significantly outperforms the state-of-the-art baselines for social group recommendation.

Boosting node activity by recommendations in social networks

In a social network, the propagation of information has sparked intense research. Influence Maximization (IM) is a well-studied problem that asks for k nodes to influence the largest users in the social network. However IM is submodular at the most time. In recent years, many non-submodular problems have been proposed and researchers give a lot of algorithms to solve them. In this paper, we propose Activity Probability Maximization Problem without submodular property. For a given social network G, a candidate edge set $${\overline{E}}$$ and a constant k, the Activity Probability Maximization Problem asks for k edges in the candidate edge set that make the all nodes of G with highest probability of being activated under a pre-determined seed set S. Using the marginal increment, we give a general way to construct submodular lower bound and submodular upper bound functions of the non-submodular objective function at the same time. Interestingly, the optimal solution of upper bound is the same as that of lower bound. Therefore, we develop the Sandwich framework called Semi-Sandwich framework. Based on the same optimal solution of lower and upper bounds, we propose a Difference Minimizing Greedy (DMG) algorithm to get an approximation solution of the original problem. Through massive experiments, we show that the method and algorithm are effective.

Link prediction using node information on local paths

Link prediction is one of the most important and challenging tasks in complex network analysis, which aims to predict missing link based on existing ones in a network. This problem is of both theoretical interest and has applications in diverse scientific disciplines, including social network analysis, recommendation systems, and biological networks. In this paper we propose a novel link prediction method that aims at improving the accuracy of existing path-based methods by incorporating information about the nodes along local paths. We investigate the proposed framework empirically and conduct extensive experiments on real-world datasets obtained from diverse domains. Results show that the proposed method has achieved increased prediction accuracy when compared to existing state-of-the-art link prediction methods.

Sequential dynamic event recommendation in event-based social networks: An upper confidence bound approach

In recent years, there have been some platforms that have focused on recommending commodities or events to users using event-based social networks (EBSNs). Some studies have attempted to find the optimal recommendation sequence of these items, assuming that the sequence stops once the user accepts one recommendation or the item list runs out. However, in reality, social media platforms will not stop recommending different commodities or social events to users until the user becomes bored and abandons the platform. Since it is 5 to 25 times more difficult to attract a new user than to retain an old one,11https://hbr.org/2014/10/the-value-of-keeping-the right-customers. it would be helpful if the platform could determine when to stop making recommendations. In this work, we investigate the problem of sequential dynamic event recommendation with feedback (SDERF), where the platform continues recommending events even when the user has accepted one that is satisfactory. We first model the SDERF problem and provide two variants, namely, an online learning model with/without contextual information. Then, we apply an upper confidence bound (UCB) approach with an expected regret polynomial in the number of events and rounds. Finally, we evaluate the performance of our proposed algorithms using both real and synthetic datasets.

Dynamic discovery of favorite locations in spatio-temporal social networks

A large volume of data flowing throughout location-based social networks (LBSN) gives support to the recommendation of points-of-interest (POI). One of the major challenges that significantly affects the precision of recommendation is to find dynamic spatio-temporal patterns of visiting behaviors, which can hardly be figured out because of the multiple side factors. To confront this difficulty, we jointly study the effects of users’ social relationships, textual reviews, and POIs’ geographical proximity in order to excavate complex spatio-temporal patterns of visiting behaviors when the data quality is unreliable for location recommendation in spatio-temporal social networks. We craft a novel framework that recommends any user the POIs with effectiveness. The framework contains two significant techniques: (i) a network embedding method is adopted to learn the vectors of users and POIs in an embedding space of low dimension; (ii) a dynamic factor graph model is proposed to model various factors such as the correlation of vectors in the previous phase. A collection of experiments was carried out on two real large-scale datasets, and the experimental outcomes demonstrate the supremacy of the proposed method over the most advanced baseline algorithms owing to its highly effective and efficient performance of POI recommendation.

Three-tier IoT-edge-cloud (3T-IEC) architectural paradigm for real-time event recommendation in event-based social networks

With the popularization of internet, event-based social networks (EBSNs) have experienced recognition among people for planning and communicating social events. Due to plethora of events occurring over EBSNs and time varying user interests, different recommendation techniques have been employed to make suitable events suggestions to participants. The state of the art event recommendation methods have not explored the importance of real-time data while generating event recommendations. However, we strongly believe that performance of event recommendation in EBSN can significantly be improved if multiple parameters captured through IoT devices may be considered. In this work, a real-time event recommendation problem which involves monitoring user’s current location, present road traffic, and weather conditions is addressed that adopts instant event recommendation. To address this problem, a novel three-tier IoT-edge-cloud based solution for real-time context-aware event recommendation problem named as 3T-IEC has been proposed. The 3T-IEC introduces edge computing layer where IoT data is processed for deriving contextual IoT-based location information along with event recommendation generator in the cloud layer. Further, contextual information such as user’s current location, weather and temporal feasibility has been applied to filter the events. Furthermore, group, category, and economic influences are modeled on filtered events to rank them with help of multiple criteria decision making method. Moreover, personalized weights on influential factors are also learned by using distance method. For practical realization, an android based mobile application-SpotEvent has been developed. Furthermore, the qualitative and quantitative analysis of the 3T-IEC is performed on two real-world datasets acquired from Meetup. The results clearly indicate that recommendation quality of proposed system is better, when compared to its variants and other baseline methods such as VSM (260%), SVD (144%), CAER (335%), Skyline (100%) and SoCast* (16%).

Effective contact recommendation in social networks by adaptation of information retrieval models

We investigate a novel perspective to the development of effective algorithms for contact recommendation in social networks, where the problem consists of automatically predicting people that a given user may wish or benefit from connecting to in the network. Specifically, we explore the connection between contact recommendation and the text information retrieval (IR) task, by investigating the adaptation of IR models (classical and supervised) for recommending people in social networks, using only the structure of these networks.We first explore the use of adapted unsupervised IR models as direct standalone recommender systems. Seeking additional effectiveness enhancements, we further explore the use of IR models as neighbor selection methods, in place of common similarity measures, in user-based and item-based nearest-neighbors (kNN) collaborative filtering approaches. On top of this, we investigate the application of learning to rank approaches borrowed from text IR to achieve additional improvements.We report thorough experiments over data obtained from Twitter and Facebook where we observe that IR models, particularly BM25, are competitive compared to state-of-the art contact recommendation methods. We provide further empirical analysis of the additional effectiveness that can be achieved by the integration of IR models into kNN and learning to rank schemes. Our research shows that the IR models are effective in three roles: as direct contact recommenders, as neighbor selectors in collaborative filtering and as samplers and features in learning to rank.

Exploiting User Check-In Data for Geo-Friend Recommendations in Location-Based Social Networks

The development of Web 2.0 technologies has meant that online social networks can both help the public facilitate sharing and communication and help them make new friends through their cyberspace social circles. Generating more accurate and geographically related results to help users find more friends in real life is gradually becoming a research hotspot. Recommending geographically related friends and alleviating check-in data sparsity problems in location-based social networks allows those to divide a day into different time slots and automatically collect user check-in data at each time slot over a certain period. Second, some important location points or regions are extracted from raw check-in trajectories, temporal periodic trajectories are constructed, and a geo-friend recommendation framework is proposed that can help users find geographically related friends. Finally, empirical studies from a real-world dataset demonstrate that this paper's method outperforms other existing methods for geo-friend recommendations in location-based social networks.

M-Payment as Financial Inclusion Strategy in Islamic Boarding School Cooperatives

Financial inclusion refers to the use of financial services such as electronic money. Digital money receives tremendous attention globally, from buyers to sellers, as an alternative form of payment. The passions on this technology enormous and infectious, therefore attracting more followers from large merchant to smaller one including the cooperative. School cooperative serves as a center of economic with a wide range of activities, such as mini market, canteen, to serve the needs of students, teachers, and people in the surrounding area. One of the programs launched by the Central Bank of Indonesia is a financial inclusion to increase the financial literacy of people living in the remote area. In this case, Islamic conventional boarding school cooperative can become influencers in most of the surrounding community to attract people’s interest to adopt the technology. The purpose of this inquiry is to find out factors influencing the adoption of mobile payment and user’s intention and decision to adopt m-payment. Authors proposed an innovative research model based on the theory of technology acceptance model with the innovation characteristics of the diffusion of innovations, perceived security and intention to recommend the technology. The research model has empirically tested at 205 employees Islamic boarding schools across four regions. The independent variables under study include perceived ease of use, perceived usefulness, perceived credibility, subjective norms, and trust while the dependent variables are mobile payment adoption and intention to recommend the technology. The study uses structural equation modeling as a tool for analysis. The result indicated that perceived ease of use, perceived usefulness, and subjective norms have a significant influence on the adoption of mobile payment. The study also confirmed the relevance of users’ intention to recommend mobile payment technology. Thus, future research needs to include social media campaigns and technology adoption studies. For researchers, the result of this study act as a basis for further refinement of personal technology acceptance model. For practitioners, understanding the key constructs is crucial to design, refine, and implement mobile payment services, applications, and products that achieve high consumer acceptance, value, and high rates of positive recommendations in social networks.

Integrated Mobile Payment Technology for High Speed Financial Literacy in Cooperatives

Digital money receives tremendous attention globally, from buyers to sellers, as an alternative form of payment. The passions on this technology enormous and infectious, therefore attracting more followers from large merchant to smaller one including the cooperative. School cooperative serves as a center of economic with a wide range of activities, such as mini market, canteen, to serve the needs of students, teachers, and people in the surrounding area. One of the programs launched by the Central Bank of Indonesia is a financial inclusion to increase the financial literacy of people living in the remote area. In this case, Islamic conventional boarding school cooperative can become influencers in most of the surrounding community to attract people’s interest to adopt the technology. The purpose of this inquiry is to find out factors influencing the adoption of mobile payment and user’s intention and decision to adopt m-payment. Authors proposed an innovative research model based on the theory of technology acceptance model with the innovation characteristics of the diffusion of innovations, perceived security and intention to recommend the technology. The research model has empirically tested at 205 employees Islamic boarding schools across four regions. The independent variables under study include perceived ease of use, perceived usefulness, perceived credibility, subjective norms, and trust while the dependent variables are mobile payment adoption and intention to recommend the technology. The study uses structural equation modeling as a tool for analysis. The result indicated that perceived ease of use, perceived usefulness, and subjective norms have a significant influence on the adoption of mobile payment. The study also confirmed the relevance of users’ intention to recommend mobile payment technology. Thus, future research needs to include social media campaigns and technology adoption studies. For researchers, the result of this study act as a basis for further refinement of personal technology acceptance model. For practitioners, understanding the key constructs is crucial to design, refine, and implement mobile payment services, applications, and products that achieve high consumer acceptance, value, and high rates of positive recommendations in social networks.

Link prediction model based on dynamic network representation

Link prediction is an important issue in network analysis tasks, which aims at detecting missing, spurious or evolving links in a network, based on the topology information of the network and/or the attributes of the nodes. It has been applied to many real-world applications, such as information integration, social network analysis, recommendation systems, and bioinformatics. Existing link prediction methods focus on static networks and ignore the transmission of dynamic information in the network. However, many graphs in practical applications are dynamic and evolve constantly over time. How to capture time information in a dynamic network and improve the accuracy of link prediction remains a conspicuous challenge. To tackle these challenges, we propose a dynamic network representation based link prediction model, named DNRLP. DNRLP can be mainly divided into two modules: a representation learning module on dynamic network and a link prediction module, where the representation learning module is composed of a node information dynamic update unit and a node neighborhood update unit. Node information dynamic update unit leverages the benefits of the long short-term memory (LSTM) in capturing time information and uses a Time Interval based Filter Unit (TIFU) to introduce time interval information between two links, while for the node neighborhood update unit we present a random walk algorithm based on connection strength to simulate the diffusion of dynamic information. Through the above two parts, the model can obtain the node representation at the new moment, then link prediction is performed by the link prediction module by measuring the similarity between the node representations. The experiment uses MRR and <i>Recall</i>@<i>k</i> indicators to evaluate performance of model on four public dynamic network datasets. The experiments demonstrate the effectiveness and the credibility of the proposed model in link prediction tasks as compared with the comparison models, the MNR index of the DNRLP is increased by 30.8%. The model proposed in this paper not only learns the dynamic information in the network, but also considers its influence on neighbors and the impact of time interval on information update. Therefore, the model has learned more abundant dynamic information and has obvious advantages for link prediction tasks.