Friend Recommendation Research Articles

Graph Structure Learning on User Mobility Data for Social Relationship Inference

With the prevalence of smart mobile devices and location-based services, uncovering social relationships from human mobility data is of great value in real-world spatio-temporal applications ranging from friend recommendation, advertisement targeting to transportation scheduling. While a handful of sophisticated graph embedding techniques are developed for social relationship inference, they are significantly limited to the sparse and noisy nature of user mobility data, as they all ignore the essential problem of the existence of a large amount of noisy data unrelated to social activities in such mobility data. In this work, we present Social Relationship Inference Network (SRINet), a novel Graph Neural Network (GNN) framework, to improve inference performance by learning to remove noisy data. Specifically, we first construct a multiplex user meeting graph to model the spatial-temporal interactions among users in different semantic contexts. Our proposed SRINet tactfully combines the representation learning ability of Graph Convolutional Networks (GCNs) with the power of removing noisy edges of graph structure learning, which can learn effective user embeddings on the multiplex user meeting graph in a semi-supervised manner. Extensive experiments on three real-world datasets demonstrate the superiority of SRINet against state-of-the-art techniques in inferring social relationships from user mobility data. The source code of our method is available at https://github.com/qinguangming1999/SRINet.

A survey of graph neural network based recommendation in social networks

With the widespread popularization of social network platforms, user-generated content and other social network data are growing rapidly. It is difficult for social users to select interested contents from the numerous social data. To alleviate information overload problem and enhance overall user experience of social networks, recommendation systems relying on historical behavioural data and social friendship relations of users, are widely used in social networks. Although researches on social recommendations have been conducted in recent years, recommendation systems of social networks still suffer from several challenges, such as data sparsity and lower performance. Since graph neural network has huge advantages in graph data learning by aggregating neighbors representations of the central node, it has been gathering pace in recent years. In this survey, we review graph neural network based literature for solving recommendation problems in social networks. We first introduce backgrounds of graph neural network and recommendation systems in social networks. Then, for different types of recommendation problems in social networks, we review different graph neural network based recommendation methods briefly. In particular, we first review GNN-based methods for general social recommendation and then review GNN-based methods for different social recommendation scenarios (such as friend recommendation and point-of-interest recommendation). Finally, we briefly discuss promising future directions of the graph neural network based recommendation in social networks.

The Impact of Marketing Information on the Decisions of Nautical Tourists Visiting Eastern Adriatic Regio

The information-seeking process of nautical tourists is essential for their decision-making when choosing a specific destination. Modern destination marketing is constantly changing due to the development of new technologies that are meant to attract and retain nautical tourists. Nautical destination managers use modern communication to build and maintain a better image and develop destinations as brands which can function sustainably even in the times of crisis. This paper examines modern and traditional marketing sources of information about Montenegro and Croatia as nautical tourist destinations. It was revealed that the largest share of the informed tourists had previous experience with a destination or were informed through internet sources. The results confirmed that the internet is increasingly used by the surveyed tourists, i.e., there is an increase in promotion through digital marketing tools in both destinations. The comparison of the trends between 2012 and 2021 indicated three common sources of information in both destinations: previous experience, the internet and the recommendations of friends and relatives. The study is based on cross-tabulation analysis which detects the differences in the method of obtaining information by the tourists whose age, gender and education level varied. The practical implication of this paper is the development of destination marketing in the Eastern Adriatic region. More precisely, the study might help the creators of developmental policies and destination operators to choose appropriate marketing strategies in order to adequately position a destination in the market.

Prevalence of Self-Medication Among Female University Students During Examinations: A Cross-Sectional Study in Saudi Arabia.

Introduction Those who practice self-care using over-the-counter (OTC) products believe that these medications are relatively safe. They can be used to treat mild illnesses that do not require medical consultation. However, improper self-medication using OTC medicines because of inadequate knowledge of their side effects and interactions can result in drug-related issues and even death. The current study was performed using the foundation year students of Princess Nourah Bint Abdul Rahman University (PNU) as subjects, to examine the use of OTC medicines during examination times. Methods This cross-sectional study was done on 213 (response rates 87.7%) foundation-year female students in the Health Colleges at PNU in Riyadh. Using a 26-item, self-administered, online questionnaire, data were collected. Results It was found that more than 50% of the students used OTC medicines habitually during exam periods. A majority (90.6%; p< 0.0001) of the students mentioned that the overuse of Panadol Extra was very safewhile 67.6% (p< 0.0001) of them declared that nonsteroidal anti-inflammatory drugs (NSAIDs) would not induce stomach ulcer formation. A higher percentage (67.6%; p<0.0001) of the students confirmed using OTC medicines during exam time for headache relief.A higher percentage (72.8%; p< 0.0001) of the students indicated that because the OTC medications were readily available and they believed these drugs were safe, they used sizable quantities during the time of the examinations. Furthermore, 69% (p< 0.0001) of the students confessed that because of a friend's recommendations, they started trying OTC medicine. Above 67% (p< 0.0001) stated that OTC medications are inexpensive and easily available in Saudi Arabia. Conclusion To conclude, the findings of this study reiterated the high usage of OTC medicines by female students during the time of examination, and the highest used were painkillers.

Friend Recommendation Engine for Facebook Users via Collaborative Filtering

Today’s internet consists of an abundant amount of information that makes it difficult for recommendation engines to produce satisfying outputs. This huge stream of unrelated data increases its sparsity, which makes the recommender system’s job more challenging. Facebook’s main recommendation task is to recommend a friendship connection based on the idea that a friend of a friend is also a friend; however, the majority of recommendations using this approach lead to little to no interaction. We propose a model using the matrix factorization technique that leverages interactions between Facebook users and generates a list of friendship connections that are very likely to be interactive. We tested our model using a real dataset with over 33 million interactions between users. The accuracy of the proposed algorithm is measured using the error rate of the predicted number of interactions between possible friends in comparison to the actual values.

A Novel Link Prediction Method for Social Multiplex Networks Based on Deep Learning

Due to the great advances in information technology, an increasing number of social platforms have appeared. Friend recommendation is an important task in social media, but newly built social platforms have insufficient information to predict entity relationships. In this case, platforms with sufficient information can help newly built platforms. To address this challenge, a model of link prediction in social multiplex networks (LPSMN) is proposed in this work. Specifically, we first extract graph structure features, latent features and explicit features and then concatenate these features as link representations. Then, with the assistance of external information from a mature platform, an attention mechanism is employed to construct a multiplex and enhanced forecasting model. Additionally, we consider the problem of link prediction to be a binary classification problem. This method utilises three different kinds of features to improve link prediction performance. Finally, we use five synthetic networks with various degree distributions and two real-world social multiplex networks (Weibo–Douban and Facebook–Twitter) to build an experimental scenario for further assessment. The numerical results indicate that the proposed LPSMN model improves the prediction accuracy compared with several baseline methods. We also find that with the decline in network heterogeneity, the performance of LPSMN increases.

MP19-20 UNDERSTANDING PATIENT EXPERIENCES WITH OVERACTIVE BLADDER

You have accessJournal of UrologyCME1 Apr 2023MP19-20 UNDERSTANDING PATIENT EXPERIENCES WITH OVERACTIVE BLADDER Hannah Sitto, Casey Brodsky, Daniela Wittmann, Lauren Wallner, Courtney Streur, Melissa Dejonckheere, John Stoffel, Aruna Sarma, J. Quentin Clemens, and Giulia Lane Hannah SittoHannah Sitto More articles by this author , Casey BrodskyCasey Brodsky More articles by this author , Daniela WittmannDaniela Wittmann More articles by this author , Lauren WallnerLauren Wallner More articles by this author , Courtney StreurCourtney Streur More articles by this author , Melissa DejonckheereMelissa Dejonckheere More articles by this author , John StoffelJohn Stoffel More articles by this author , Aruna SarmaAruna Sarma More articles by this author , J. Quentin ClemensJ. Quentin Clemens More articles by this author , and Giulia LaneGiulia Lane More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003244.20AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Overactive bladder (OAB) is highly prevalent, affecting millions of Americans, and poses a significant symptom burden. The purpose of this study was to understand patient experiences with OAB and the impact of these experiences on OAB treatment. METHODS: People with symptoms of OAB were recruited from a tertiary care clinic and from an online health research portal to complete semi-structured interviews regarding their OAB experiences. The interviews were recorded, transcribed, coded, and inductively analyzed to identify emerging themes. RESULTS: We performed 19 interviews and identified several key themes central to the patient experience, including symptom impact and severity, knowledge, stigma, self-efficacy, and regret. We considered these themes along the following stages of the patient's OAB journey. Symptom Development and Awareness: The routine of self-care is insidious and normalized, making realization of a lifestyle that is centered around voiding less obvious to patients, leading to a delay of care-seeking. Participants noted restrictions on all aspects of life. Adjectives used to describe symptom impact included “annoyance, depression, humiliation and desperation.” Care-Seeking: Participants expressed coping behaviors during onset and gradual worsening of symptoms, however many recounted a “sentinel event” that heightened their severity perception and served as a cue to action. Routine primary care visit screenings and friend recommendations were additional cues to action. Reasons for care-seeking delay included lack of OAB knowledge, stigma, and embarrassment. Experiences with Therapy: Participants recognized that treatment outcomes depended on their engagement. Some individuals regretted their lack of self-advocacy and self-efficacy. Participants highlighted internal barriers (forgetfulness, doubting treatment effectiveness) and external barriers (comorbidities, COVID-19) to therapy adherence. Among those with high self-efficacy, fear of treatment failure, calendar tools, and social support networks facilitated treatment compliance (Figure 1). CONCLUSIONS: Living with OAB affects patients physically, mentally, and socially. Gaining a better understanding of OAB experiences can help physicians tailor their practice to meet patients’ needs. Source of Funding: NIDDK K-12 (Lane) © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e273 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Hannah Sitto More articles by this author Casey Brodsky More articles by this author Daniela Wittmann More articles by this author Lauren Wallner More articles by this author Courtney Streur More articles by this author Melissa Dejonckheere More articles by this author John Stoffel More articles by this author Aruna Sarma More articles by this author J. Quentin Clemens More articles by this author Giulia Lane More articles by this author Expand All Advertisement PDF downloadLoading ...

Friendship Inference in Mobile Social Networks: Exploiting Multi-Source Information With Two-Stage Deep Learning Framework

With the tremendous growth of mobile social networks (MSNs), people are highly relying on it to connect with friends and further expand their social circles. However, the conventional friendship inference techniques have issues handling such a large yet sparse multi-source data. The related friend recommendation systems are therefore suffering from reduced accuracy and limited scalability. To address this issue, we propose a Two-stage Deep learning framework for Friendship Inference, namely TDFI. This approach enables MSNs to exploit multi-source information simultaneously, rather than hierarchically. Therefore, there is no need to manually set which information is more important and the order in which the various information is applied. In details, we apply an Extended Adjacency Matrix (EAM) to represent the multi-source information. We then adopt an improved Deep Auto-Encoder Network (iDAEN) to extract the fused feature vector for each user. Our framework also provides an improved Deep Siamese Network (iDSN) to measure user similarity. To provide a substantial description and evaluation of the proposed methodology, we evaluate the effectiveness and robustness on three large-scale real-world datasets. Trace-driven evaluation results demonstrate that TDFI can effectively handle the sparse multi-source data while providing better accuracy for friendship inference. Through the comparison with numerous state-of-the-art methods, we find that TDFI can achieve superior performance via real-world multi-source information. Meanwhile, it demonstrates that the proposed pipeline can not only integrate structural information and attribute information, but also be compatible with different attribute information, which further enhances the overall applicability of friend-recommendation systems under information-rich MSNs.

HCoF: Hybrid Collaborative Filtering Using Social and Semantic Suggestions for Friend Recommendation

Today, people frequently communicate through interactions and exchange knowledge over the social web in various formats. Social connections have been substantially improved by the emergence of social media platforms. Massive volumes of data have been generated by the expansion of social networks, and many people use them daily. Therefore, one of the current problems is to make it easier to find the appropriate friends for a particular user. Despite collaborative filtering’s huge success, accuracy and sparsity remain significant obstacles, particularly in the social networking sector, which has experienced astounding growth and has a large number of users. Social connections have been substantially improved by the emergence of social media platforms. In this work, a social and semantic-based collaborative filtering methodology is proposed for personalized recommendations in the context of social networking. A new hybrid collaborative filtering (HCoF) approach amalgamates the social and semantic suggestions. Two classification strategies are employed to enhance the performance of the recommendation to a high rate. Initially, the incremental K-means algorithm is applied to all users, and then the KNN algorithm for new users. The mean precision of 0.503 obtained by HCoF recommendation with semantic and social information results in an effective collaborative filtering enhancement strategy for friend recommendations in social networks. The evaluation’s findings showed that the proposed approach enhances recommendation accuracy while also resolving the sparsity and cold start issues.

Efficient Retrieval of the Top-k Most Relevant Event-Partner Pairs

The proliferation of EBSN motivates studies on topics such as event, venue, and friend recommendation as well as event creation and organization. In this setting, the notion of event-partner recommendation has attracted attention. When recommending an event to a user, this functionality allows the recommendation of partners with whom to attend the event. However, in existing proposals, recommendations are pushed to users at the system's initiative. In contrast, EBSNs provide users with keyword-based search functionality to retrieve information in pull mode. We propose a new way of accessing information in EBSNs that combines pull and push, thus allowing users to not only conduct ad-hoc searches for events, but also to receive partner recommendations for retrieved events, namely kEP querying. This type of query retrieves event-partner pairs, taking into account the relevance of events to user-supplied keywords and so-called together preferences that indicate the extent of a user's preference to attend an event with a given partner. To compute kEP queries efficiently, we propose a rank-join based framework with three optimizations. Results of empirical studies with implementations of the proposed techniques demonstrate that the proposed techniques are capable of excellent performance.

A Personalized Explainable Learner Implicit Friend Recommendation Method

With the rapid development of social networks, academic social networks have attracted increasing attention. In particular, providing personalized recommendations for learners considering data sparseness and cold-start scenarios is a challenging task. An important research topic is to accurately discover potential friends of learners to build implicit learning groups and obtain personalized collaborative recommendations of similar learners according to the learning content. This paper proposes a personalized explainable learner implicit friend recommendation method (PELIRM). Methodologically, PELIRM utilizes the learner's multidimensional interaction behavior in social networks to calculate the degrees of trust between learners and applies the three-degree influence theory to mine the implicit friends of learners. The similarity of research interests between learners is calculated by cosine and term frequency–inverse document frequency. To solve the recommendation problem for cold-start learners, the learner's common check-in IP is used to obtain the learner's location information. Finally, the degree of trust, similarity of research interests, and geographic distance between learners are combined as ranking indicators to recommend potential friends for learners and give multiple interpretations of the recommendation results. By verifying and evaluating the proposed method on real data from Scholar.com, the experimental results show that the proposed method is reliable and effective in terms of personalized recommendation and explainability.

Group Recommendation Based on Heterogeneous Graph Algorithm for EBSNs

Emerging event-based social networks (EBSNs), such as Meetup, have grown rapidly and become popular in recent years. EBSNs differ from conventional social networks such as Facebook in that they not only involve online social interactions but also include offline, in-person interactions. Thus, EBSNs are naturally heterogeneous and possess more valuable social information. Group recommendations in EBSNs are typically only based on the interest information filled in by users, or friends’ group information. Both these methods may not well reflect users’ real intentions. In this study, we propose a recommender system to predict groups that may interest EBSN users, based on a novel heterogeneous augmented graph method and a random walk with restart algorithm. In this approach, online and offline social interactions are combined into a single heterogeneous augmented graph capturing all useful relationships, including user-to-group relationships, user-to-event relationships, user-to-attribute relationships, and group-to-attribute relationships, and among others. To our knowledge, this work is the first attempt to apply a random walk algorithm into group recommendation in EBSNs. Extensive experiments on Meetup datasets demonstrate that our proposed recommender system achieves better results in terms of recall, precision, F-Measure and MRR metrics in comparison with the other four commonly used algorithms, including random recommendation, interest-based recommendation, interest- and neighborhood-based recommendation, and Katz Centrality. The significant recommendation performance of our approach may further enhance user satisfaction of EBSNs. Moreover, our approach to group recommendation may also be extended to other recommendation-related applications such as event or friend recommendation.

ОНЛАЙН-МЕРЧАНДАЙЗИНГ ЯК ІНСТРУМЕНТ АКТИВІЗАЦІЇ МАРКЕТИНГОВОЇ ПОВЕДІНКИ ПІДПРИЄМСТВА НА ОНЛАЙН-РИНКУ

The article examines the prerequisites for the activation of the marketing behavior of the enterprise on the online market, which is an urgent issue today. It was found that the introduction of new modern marketing technologies is an indispensable condition for successful promotion of products and gaining the trust of online-consumers. Considering that the volume of online sales of goods is growing every year, it is advisable to use online merchandising technologies when selling goods in online stores: make an attractive web-site design, offer convenient navigation and search, apply personalization techniques, and advertise goods and services in Internet, including using social media. It was found that one of the modern tools for promoting goods on the online market and communicating with online buyers is online merchandising – orderly placement of goods on the web-site of an online store to increase sales of goods. That is why the purpose of the article is to formulate proposals for the use of directions for the development of online merchandising in online stores to attract consumers, stimulate sales in order to activate the marketing behavior of the enterprise on the online market. With the help of an Internet survey of young people, the importance of certain criteria in online shopping was determined. Among them: personalization of offers, globalization and the possibility of delivery of goods to other countries, quality of site design, adaptation for mobile phones, interesting content (reviews, entertainment, news, breadth of assortment, recommendations of relatives, friends and users in social networks, home delivery of goods, availability of information about the product (3D visualization, convenience of purchase (quick purchase, possibility to buy 24/7), better price offer compared to competitors, availability of discounts and loyalty program, convenient navigation. Some criteria are related to online merchandising: design, web-site navigation, assortment presentation, personalization. It should be noted that international studies show additional benefits that online stores receive, using the technologies of a personalized approach: increasing sales, increasing customer loyalty. Therefore, it is advisab

Multi-feature fusion friend recommendation algorithm based on complex network

Multi-feature fusion friend recommendation algorithm based on complex network

Denizcilik Alanındaki Liselerde Öğrenim Gören Öğrencilerin Balık Tüketim Alışkanlıklarının Belirlenmesi: Türkiye Örneği

In this study, it has been aimed to determine the fish consumption habits of the students studying at high schools in the field of Maritime. This research is cross-sectional in nature. It has been found that the participants give importance to fish consumption, they prefer to eat fish because it is healthy, and it is the recommendation of family and friends that make them willing to consume a new fish species. In the consumption of fish, they prefer to consume fresh, fried fish, which are hunted and purchased from the fishermen’s stall. It is thought that the necessity of health education for the development of fish consumption habits and increasing the fish consumption rate and the carrying out of these training with family and peer support can increase fish consumption.

Medical Tourists’ Satisfaction and Decision-Making Factors with a focus on the Czech Republic

Abstract Medical tourism in the Czech Republic is a relatively new phenomenon, so far, no research has been conducted in this area to collect relevant data. This research aims to analyse and evaluate the experience of medical tourists and find out what is important and what influences them in choosing a destination where they will undergo the selected procedure. Based on qualitative research, which was conducted in the form of interviews with medical tourists who underwent medical intervention in the Czech Republic, the problems faced by medical tourists, and factors influencing their decision-making processes were identified. Finally, suggestions for improvement were found. The research focused on the areas of communication, behaviour, decision-making processes, and factors that lead to patient satisfaction. The results are important not only for the healthcare facilities themselves but also for the creation of an adequate marketing strategy, as it was found that the most important tool in the decision-making process is the word of mouth. It was found that medical tourists choose the country mostly based on the recommendation of family or friends, mostly those who have already undergone medical treatment in that country. Therefore, it is important that patients leave satisfied so that they can continue to recommend going for treatment abroad or particularly in the Czech Republic.

Improving Friend Recommendation for Online Learning with Fine-Grained Evolving Interest.

The online version contains supplementary material available at 10.1007/s11390-021-2124-z.

MOTIVATION OF FARMERS IN CULTIVATION OF PLANTS (Pogostemon cablin Benth) IN TIWORO VILLAGE, TIWORO DISTRICT, WEST MUNA DISTRICT

This studied aimed to determine: (1) the motivation of farmers in cultivating patchouli; and (2) factors that motivate farmers with the motivation of farmers in cultivating patchouli; and (3) the relationship between the factors that motivate farmers and the motivation of farmers in cultivating patchouli in Tiworo Village, Tiworo Islands District, West Muna Regency. This research was conducted in Tiworo Village, Tiworo Islands District, Muna Regency. The research respondents were 32 who were determined by census, namely taking the entire population, namely farmers who cultivate patchouli plants. The analysis in this research is by using Spearman Rank Correlation Analysis. The results showed that: (1) the motivation of farmers in cultivating patchouli was categorized as high; and (2) the factors that were significantly related to the motivation of farmers were capital, the availability of production facilities, the availability of technological facilities, the recommendation of agricultural extension workers and the market, while the factors that were not significantly related to the motivation of farmers in cultivating patchouli plants were the recommendations of friends or neighbors.

Factors Affecting the Preference, Choice, and Selection of Saudi Women Towards Jewelry

The study aimed to identify the factors affecting the preference, choice, and selection of jewelry among Saudi women. The study employed a descriptive research design to examine consumers&amp;rsquo; preferences, choices, and attitudes toward buying jewelry products. For the study purpose, 500 consumers were randomly selected from different regions of Saudi Arabia. The data were collected using a structured questionnaire based on; consumer preferences, recommendations of family and friends, information sources, and other factors related to the attitude of consumers toward buying jewelry. The analysis revealed some significant factors that affect the buying behavior of women towards jewelry, such as convenient shopping, individual perspectives, product dimension, quality assurance, financial dimension, and promotional dimension. The study concluded that variety, brand name, social status, word-of-mouth publicity, price, and advertisements significantly affect the purchasing behavior of consumers.

Exploring the antecedents of internalization, identification, and compliance social influence for mobile banking adoption

PurposeSocial media users can now create, exchange, modify and consume socially generated experiences which can enhance social influence toward mobile banking (MB). This study aims to provide understanding of how social actor interactions through social networking platforms (SNPs) can create social influence for MB adoption and present a research framework that can help to understand which social actors have higher social influence toward MB adoption in conventional and Islamic banks.Design/methodology/approachSNP users have different levels of perceptions and experiences about the usability and credibility of MB. Therefore, their experiences are subjective realties which can generate socially constructed knowledge. To understand these subjective realties, a social constructivist approach is adopted. Data were collected from interviews with 60 individuals from diverse occupational backgrounds.FindingsIdentification element of social influence explained that the shared reviews and recommendations of opinion leaders, industry experts, celebrities and friends were highly positive for conventional banks; therefore, there is high word-of-mouth for MB of conventional banks. Internalization of social influence highlighted that people are more likely to accept the wisdom of the crowd and close friends, which can generate their engagement and connection with MB. Finally, the compliance factor of social influence explained that people can only adopt MB when they perceive high usability and credibility.Research limitations/implicationsThis study has provided understanding to the marketers of how social actors on SNPs can play a role in the creation, exchange, modification and consumption of socially generated influence that can impact the MB adoption intention for conventional and Islamic banks.Originality/valueAlthough many theories and models have been presented about the marketing strategies and antecedents of MB adoption, the extensive use of SNPs has changed marketing strategies. For example, this study has found that social media users are highly influenced by the social reviews and recommendations they receive from their close friends. Therefore, socially generated influence on SNPs can create an adoption intention toward MB.