Leveraging social influence based on users activity centers for point-of-interest recommendation

Recommender Systems (RSs) aim to model and predict the user preference while interacting with items, such as Points of Interest (POIs). These systems face several challenges, such as data sparsity, limiting their effectiveness. In this paper, we address this problem by incorporating social, geographical, and temporal information into the Matrix Factorization (MF) technique. To this end, we model social influence based on two factors: similarities between users in terms of common check-ins and the friendships between them. We introduce two levels of friendship based on explicit friendship networks and high check-in overlap between users. We base our friendship algorithm on users’ geographical activity centers. The results show that our proposed model outperforms the state-of-the-art on two real-world datasets. More specifically, our ablation study shows that the social model improves the performance of our proposed POI recommendation system by 31% and 14% on the Gowalla and Yelp datasets in terms of Precision@10, respectively.     

An empirical testing of user stereotypes of information retrieval systems

Stereotyping is a technique used in many information systems to represent user groups and/or to generate initial individual user models. However, there has been a lack of evidence on the accuracy of their use in representing users. We propose a formal evaluation method to test the accuracy or homogeneity of the stereotypes that are based on users' explicit characteristics. Using the method, the results of an empirical testing on 11 common user stereotypes of information retrieval (IR) systems are reported. The participants' memberships in the stereotypes were predicted using discriminant analysis, based on their IR knowledge. The actual membership and the predicted membership of each stereotype were compared. The data show that “librarians/IR professionals” is an accurate stereotype in representing its members, while some others, such as “undergraduate students” and “social sciences/humanities” users, are not accurate stereotypes. The data also demonstrate that based on the user's IR knowledge a stereotype can be made more accurate or homogeneous. The results show the promise that our method can help better detect the differences among stereotype members, and help with better stereotype design and user modeling. We assume that accurate stereotypes have better performance in user modeling and thus the system performance.Limitations and future directions of the study are discussed.     

Understanding followers’ stickiness to digital influencers: The effect of psychological responses

The ability of digital influencers to convert their followers into paying customers relies heavily on the followers’ “stickiness”, a topic that has not been adequately investigated in the existing literature. From a psychological perspective, this study develops a theoretical model of followers’ stickiness. Two forms of followers’ psychological responses to digital influencers are jointly considered: wishful identification and parasocial relationships. This study also categorizes and examines the moderating effects exerted by the genres of digital influencers’ revenue models, which represent a vital contextual factor for forming followers’ stickiness. A survey was conducted on Weibo, the Chinese equivalent to Twitter, with a sample of 319 followers of real digital influencers that are using different genres of revenue models. The findings indicate that both wishful identification and parasocial relationships have significant but different impacts on followers’ stickiness in different genres of influencers’ revenue models. This paper enriches our understanding of the phenomenon of followers’ stickiness toward digital influencers and provides practical guidance for digital influencers and social commerce/media platform providers.     

Negative Can Be Positive: Signed Graph Neural Networks for Recommendation

Most of the existing GNN-based recommender system models focus on learning users’ personalized preferences from these (explicit/implicit) positive feedback to achieve personalized recommendations. However, in the real-world recommender system, the users’ feedback behavior also includes negative feedback behavior (e.g., click dislike button), which also reflects users’ personalized preferences. How to utilize negative feedback is a challenging research problem. In this paper, we first qualitatively and quantitatively analyze the three kinds of negative feedback that widely existed in real-world recommender systems and investigate the role of negative feedback in recommender systems. We found that it is different from what we expected — not all negative items are ranked low, and some negative items are even ranked high in the overall items. Then, we propose a novel Signed Graph Neural Network Recommendation model (SiGRec) to encode the users’ negative feedback behavior. Our SiGRec can learn positive and negative embeddings of users and items via positive and negative graph neural network encoders, respectively. Besides, we also define a new Sign Cosine (SiC) loss function to adaptively mine the information of negative feedback for different types of negative feedback. Extensive experiments on four datasets demonstrate the proposed model outperforms several existing models. Specifically, on the Zhihu dataset, SiGRec outperforms the unsigned GNN model (i.e., LightGCN), 27.58% 29.81%, and 31.21% in P@20, R@20, and nDCG@20, respectively. We hope our work can open the door to further exploring the negative feedback in recommendations.     

Large-scale evaluation framework for local influence theories in Twitter

Influence theories constitute formal models that identify those individuals that are able to affect and guide their peers through their activity. There is a large body of work on developing such theories, as they have important applications in viral marketing, recommendations, as well as information retrieval. Influence theories are typically evaluated through a manual process that cannot scale to data voluminous enough to draw safe, representative conclusions. To overcome this issue, we introduce in this paper a formalized framework for large-scale, automatic evaluation of topic-specific influence theories that are specialized in Twitter. Basically, it consists of five conjunctive conditions that are indicative of real influence exertion: the first three determine which influence theories are compatible with our framework, while the other two estimate their relative effectiveness. At the core of these two conditions lies a novel metric that assesses the aggregate sentiment of a group of users and allows for estimating how close the behavior of influencers is to that of the entire community. We put our framework into practice using a large-scale test-bed with real data from 75 Twitter communities. In order to select the theories that can be employed in our analysis, we introduce a generic, two-dimensional taxonomy that elucidates their functionality. With its help, we ended up with five established topic-specific theories that are applicable to our settings. The outcomes of our analysis reveal significant differences in their performance. To explain them, we introduce a novel methodology for delving into the internal dynamics of the groups of influencers they define. We use it to analyze the implications of the selected theories and, based on the resulting evidence, we propose a novel partition of influence theories in three major categories with divergent performance.     

Investigating the COVID-19 vaccine discussions on Twitter through a multilayer network-based approach

Modeling discussions on social networks is a challenging task, especially if we consider sensitive topics, such as politics or healthcare. However, the knowledge hidden in these debates helps to investigate trends and opinions and to identify the cohesion of users when they deal with a specific topic. To this end, we propose a general multilayer network approach to investigate discussions on a social network. In order to prove the validity of our model, we apply it on a Twitter dataset containing tweets concerning opinions on COVID-19 vaccines. We extract a set of relevant hashtags (i.e., gold-standard hashtags) for each line of thought (i.e., pro-vaxxer, neutral, and anti-vaxxer). Then, thanks to our multilayer network model, we figure out that the anti-vaxxers tend to have ego networks denser (+14.39%) and more cohesive (+64.2%) than the ones of pro-vaxxer, which leads to a higher number of interactions among anti-vaxxers than pro-vaxxers (+393.89%). Finally, we report a comparison between our approach and one based on single networks analysis. We prove the effectiveness of our model to extract influencers having ego networks with more nodes (+40.46%), edges (+39.36%), and interactions with their neighbors (+28.56%) with respect to the other approach. As a result, these influential users are much more important to analyze and can provide more valuable information.     

Quantifying the structural and temporal characteristics of negative links in signed citation networks

Although the citation relationships among papers can help in tracking and understanding the development of knowledge, few studies have noted that the content and sentiments of citations of a paper differ. Here, we use sentiment-labeled citation data to construct a directed signed citation network, in which an author may agree with or criticize the cited paper and these represent different ways of inheriting knowledge. The dataset we use consists of 9,038 papers in the field of Computational Linguistics, including 25,275 citations, with 20.8% positive citations, 8.6% negative citations and 70.6% neutral citations. We systematically quantify the structural patterns of negative citations, impact assortativity of involved papers, occurrence time distribution and consequences of receiving negative attention. Remarkably, we find that papers with different impacts have a similar probability of receiving negative citations, and highly cited papers tend to give negative citations to low-impact papers around but avoid giving negative citations to high-impact papers. Our research also reveals the random occurrence rules and colocation patterns of negative citation distribution. In addition, we show that, in the short term, around 60% of multiple negative citations is positively related to the impact of the cited paper while more than 80% are negatively related to the impact in the long run. Our findings explain the pattern by which negative citations occur and deepen the understanding of negative citations.     

Who do you trust? The digital destruction of shared situational awareness and the COVID-19 infodemic

Developments in centrally managed communications (e.g. Twitter, Facebook) and service (e.g. Uber, airbnb) platforms, search engines and data aggregation (e.g. Google) as well as data analytics and artificial intelligence, have created an era of digital disruption during the last decade. Individual user profiles are produced by platform providers to make money from tracking, predicting, exploiting and influencing their users’ decision preferences and behavior, while product and service providers transform their business models by targeting potential customers with more accuracy. There have been many social and economic benefits to this digital disruption, but it has also largely contributed to the digital destruction of mental model alignment and shared situational awareness through the propagation of mis-information i.e. reinforcement of dissonant mental models by recommender algorithms, bots and trusted individual platform users (influencers). To mitigate this process of digital destruction, new methods and approaches to the centralized management of these platforms are needed to build on and encourage trust in the actors that use them (and by association trust in their mental models). The global ‘infodemic’ resulting from the COVID-19 pandemic of 2020, highlights the current problem confronting the information system discipline and the urgency of finding workable solutions.     

Mining direct antagonistic communities in signed social networks

Social networks provide a wealth of data to study relationship dynamics among people. Most social networks such as Epinions and Facebook allow users to declare trusts or friendships with other users. Some of them also allow users to declare distrusts or negative relationships. When both positive and negative links co-exist in a network, some interesting community structures can be studied. In this work, we mine Direct Antagonistic Communities (DACs) within such signed networks. Each DAC consists of two sub-communities with positive relationships among members of each sub-community, and negative relationships among members of the other sub-community. Identifying direct antagonistic communities is an important step to understand the nature of the formation, dissolution, and evolution of such communities. Knowledge about antagonistic communities allows us to better understand and explain behaviors of users in the communities.     

Mining user interests over active topics on social networks

Inferring users’ interests from their activities on social networks has been an emerging research topic in the recent years. Most existing approaches heavily rely on the explicit contributions (posts) of a user and overlook users’ implicit interests, i.e., those potential user interests that the user did not explicitly mention but might have interest in. Given a set of active topics present in a social network in a specified time interval, our goal is to build an interest profile for a user over these topics by considering both explicit and implicit interests of the user. The reason for this is that the interests of free-riders and cold start users who constitute a large majority of social network users, cannot be directly identified from their explicit contributions to the social network. Specifically, to infer users’ implicit interests, we propose a graph-based link prediction schema that operates over a representation model consisting of three types of information: user explicit contributions to topics, relationships between users, and the relatedness between topics. Through extensive experiments on different variants of our representation model and considering both homogeneous and heterogeneous link prediction, we investigate how topic relatedness and users’ homophily relation impact the quality of inferring users’ implicit interests. Comparison with state-of-the-art baselines on a real-world Twitter dataset demonstrates the effectiveness of our model in inferring users’ interests in terms of perplexity and in the context of retweet prediction application. Moreover, we further show that the impact of our work is especially meaningful when considered in case of free-riders and cold start users.     

学术社交网络用户知识共享意愿的影响因素研究

[目的/意义] 从动机、机会、能力3个维度揭示学术社交网络用户知识共享意愿的影响因素。[方法/过程] 基于MOA理论,构建学术社交网络用户知识共享意愿影响因素模型,搜集数据并采用结构方程模型方法对模型研究假设进行验证。[结果/结论] 利他动机、声誉动机、社区认同动机、知识获取动机、信息质量、系统质量、自我效能对学术社交网络用户的知识共享意愿影响显著,社交关系动机、服务质量对学术社交网络用户的知识共享意愿影响并不显著。该模型对解释我国学术社交网络用户的知识共享意愿和指导学术社交平台建设具有指导意义。     

What makes a review a reliable rating in recommender systems?

The way that users provide feedback on items regarding their satisfaction varies among systems: in some systems, only explicit ratings can be entered; in other systems textual reviews are accepted; and in some systems, both feedback types are accommodated. Recommender systems can readily exploit explicit ratings in the rating prediction and recommendation formulation process, however textual reviews -which in the context of many social networks are in abundance and significantly outnumber numeric ratings- need to be converted to numeric ratings. While numerous approaches exist that calculate a user's rating based on the respective textual review, all such approaches may introduce errors, in the sense that the process of rating calculation based on textual reviews involves an uncertainty level, due to the characteristics of the human language, and therefore the calculated ratings may not accurately reflect the actual ratings that the corresponding user would enter. In this work (1) we examine the features of textual reviews, which affect the reliability of the review-to-rating conversion procedure, (2) we compute a confidence level for each rating, which reflects the uncertainty level for each conversion process, (3) we exploit this metric both in the users’ similarity computation and in the prediction formulation phases in recommender systems, by presenting a novel rating prediction algorithm and (4) we validate the accuracy of the presented algorithm in terms of (i) rating prediction accuracy, using widely-used recommender systems datasets and (ii) recommendations generated for social network user satisfaction and precision, where textual reviews are abundant.     

试论社会科学学术网站的类型与特点

本文对社会科学学术网站作了界定和基本的归类,探讨了社会科学学术网站与社会科学学术活动的关系。并从信息内容的综合程度、网站所属机构的不同、用户的特点、网站设置的不同目的等四个角度分析了各种社会科学学术网站的特点,建立了相关模型以供参考。并在系统分析的基础上,对社会科学学术网站的发展趋势作了初步的分析,指出了社会科学学术网站建设中存在的问题。     

Deep strategic mediatization: Organizational leaders’ knowledge and usage of social bots in an era of disinformation

We identified a lack of theoretical concepts and empirical knowledge about the perception and usage of social bots from the organizational and communication management perspective. Therefore, we first introduce social bots in the realm of communication and information management by using a profound literature review. Second, by building on mediatization theory and strategic communication, we introduce the concept of deep strategic mediatization. By surveying the attitudes towards and usage of social bots of leading European communication professionals (n = 2,247) from 49 European countries, we thirdly offer first indications how diverse European organizations in different European regions use social bots. Results indicate, that leading communication professionals in Central and Western Europe as well as Scandinavia perceive highly ethical challenges, while in Southern and Eastern Europe professionals are less skeptical regarding the usage of social bots. Only 11.5 percent (n = 257) declare their organization uses or are making plans to use social bots for strategic communication. They are used primarily for identifying and following social networks users. This refers specifically to the usage of digital traces for strategic communication purposes e.g., to identify topic area opinion leaders or social media influencers. However, this represents only a small minority of the sample – leading to the conclusion that only a small minority of organizations already practice deep strategic mediatization.     

Measuring user influence on Twitter: A survey

Centrality is one of the most studied concepts in social network analysis. There is a huge literature regarding centrality measures, as ways to identify the most relevant users in a social network. The challenge is to find measures that can be computed efficiently, and that can be able to classify the users according to relevance criteria as close as possible to reality. We address this problem in the context of the Twitter network, an online social networking service with millions of users and an impressive flow of messages that are published and spread daily by interactions between users. Twitter has different types of users, but the greatest utility lies in finding the most influential ones. The purpose of this article is to collect and classify the different Twitter influence measures that exist so far in literature. These measures are very diverse. Some are based on simple metrics provided by the Twitter API, while others are based on complex mathematical models. Several measures are based on the PageRank algorithm, traditionally used to rank the websites on the Internet. Some others consider the timeline of publication, others the content of the messages, some are focused on specific topics, and others try to make predictions. We consider all these aspects, and some additional ones. Furthermore, we include measures of activity and popularity, the traditional mechanisms to correlate measures, and some important aspects of computational complexity for this particular context.     

Effective influence estimation in twitter using temporal,profile, structural and interaction characteristics

Influence diffusion is extensively studied in social networks for product or service promotion and viral-marketing applications. This paper proposes two models for social influence estimation, namely Time Decay Features Cascade Model (TDF-C) and Time Decay Features Cascade Threshold Model (TDF-CT). These models overcome three main existing challenges - first, measure the strength of user's influence as an influencer; second, identify the set of users influenced by an influencer; third, estimate the time frame of the influence. TDF-C is an M-TAP based diffusion model, which learns influence probabilities between users using four types of features, namely temporal, interaction, structural, and profile features, and uses Independent Cascade (IC) model for influence estimation. TDF-CT is an extension of the TDF-C model, which uses temporal and interaction features to calculate the diffusion through the Progressive Feedback Estimation (PFE) model in place of IC model. PFE model is a fusion of two diffusion models, i.e., Linear Threshold (LT) and Independent Cascade. TDF-CT handles the limitations of the contemporary diffusion models, i.e., IC and LT. The efficacy of proposed models is evaluated with respect to existing models Independent Cascade (IC), Time Constant Cascade (TC-C), Time Decay Cascade (TD-C), and Time-Depth Decay Cascade (TDD-C). Experimental evaluation over two benchmark datasets namely Darwin and MelCup17 reveal that proposed models are able to make the predictions very close to the real-time in a given time frame. TDF-CT and TDF-C are most suitable for applications requiring high precision and high recall, respectively. Results of spread shape establish the efficacy of models to spread the influence with good coverage of the social network. Results are obtained with improved accuracy by up to 39%.     

社会化网络、情境因素与知识协同关系实证研究——基于安徽大学学生的样本调查

[目的/意义]知识经济时代,社会化网络越来越得到重视,而探究其对于知识协同的作用一直处于摸索阶段。[方法/过程]本文基于对社会化网络、知识协同基本定义的界定上,利用维度衡量、模型构建为架构,利用数据对模型进行验证分析。并引入情境因素作为外生环境因素探究其对于社会化网络及知识协同的影响。[结果/结论]通过实证分析,表明社会化网络对于知识协同以及情境因素中部分维度有着显著影响;用户因素对于知识协同存在显著影响,情境因素在社会化网络与知识协同之间存在部分中介效应。     

Exploiting user experience from online customer reviews for product design

Understanding user experience (UX) becomes more important in a market-driven design paradigm because it helps designers uncover significant factors, such as user’s preference, usage context, product features, as well as their interrelations. Conventional means, such as questionnaire, survey and self-report with predefined questions and prompts, are used to collect information about users’ experience during various UX studies. However, such data is often limited and restricted by initial setups, and they won’t easily allow designers to identify all critical elements such as user profile, context, related product features, etc. Meanwhile, with widely accessible social media, the volume and velocity of customer-generated data are fast-increasing. While it is generally acknowledged that such data contains important elements in understanding and analyzing UX, extracting them to assist product design remains a challenging issue. In this study, how UX data underlying product design can be isolated and restored from customer online reviews is examined. A faceted conceptual model is proposed to elucidate the crucial factors of UX, which serves as an operational mechanism connecting to product design. A methodology of establishing a UX knowledge base from customer online reviews is then proposed to support UX-centered design activities, which consists of three stages, i.e., UX discovery to extract UX data from a single review, UX data integration to group similar data and UX network formalization to build up the causal dependencies among UX groups. Using a case study on smart mobile phone reviews, examples of UX data discovered are demonstrated and both customers and designers concerned key product features and usage situations are exemplified. This study explores the feasibility to discover valuable UX data as well as their relations automatically for product design and business strategic plan by analyzing a large volume of customer online data.     

Towards a real-time processing framework based on improved distributed recurrent neural network variants with fastText for social big data analytics

Big data generated by social media stands for a valuable source of information, which offers an excellent opportunity to mine valuable insights. Particularly, User-generated contents such as reviews, recommendations, and users’ behavior data are useful for supporting several marketing activities of many companies. Knowing what users are saying about the products they bought or the services they used through reviews in social media represents a key factor for making decisions. Sentiment analysis is one of the fundamental tasks in Natural Language Processing. Although deep learning for sentiment analysis has achieved great success and allowed several firms to analyze and extract relevant information from their textual data, but as the volume of data grows, a model that runs in a traditional environment cannot be effective, which implies the importance of efficient distributed deep learning models for social Big Data analytics. Besides, it is known that social media analysis is a complex process, which involves a set of complex tasks. Therefore, it is important to address the challenges and issues of social big data analytics and enhance the performance of deep learning techniques in terms of classification accuracy to obtain better decisions.In this paper, we propose an approach for sentiment analysis, which is devoted to adopting fastText with Recurrent neural network variants to represent textual data efficiently. Then, it employs the new representations to perform the classification task. Its main objective is to enhance the performance of well-known Recurrent Neural Network (RNN) variants in terms of classification accuracy and handle large scale data. In addition, we propose a distributed intelligent system for real-time social big data analytics. It is designed to ingest, store, process, index, and visualize the huge amount of information in real-time. The proposed system adopts distributed machine learning with our proposed method for enhancing decision-making processes. Extensive experiments conducted on two benchmark data sets demonstrate that our proposal for sentiment analysis outperforms well-known distributed recurrent neural network variants (i.e., Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Unit (GRU)). Specifically, we tested the efficiency of our approach using the three different deep learning models. The results show that our proposed approach is able to enhance the performance of the three models. The current work can provide several benefits for researchers and practitioners who want to collect, handle, analyze and visualize several sources of information in real-time. Also, it can contribute to a better understanding of public opinion and user behaviors using our proposed system with the improved variants of the most powerful distributed deep learning and machine learning algorithms. Furthermore, it is able to increase the classification accuracy of several existing works based on RNN models for sentiment analysis.