Experts In Social Network Research Articles

Forecasting the cryptocurrency exchange rate based on the ranking of expert opinions

To date, most existing cryptocurrency exchanges do not have in their arsenal tools that would allow them to verify and investigate the information disseminated on social networks regarding a particular cryptocurrency. This makes it possible to conduct a relevant research with the subsequent development of a tool that, if used correctly, will provide users with advisory advice on further actions in relation to the cryptocurrency under study in the system. Based on this advice, interested parties will be able to adjust their decisions regarding further financial steps. The basis of most recommender systems is always the need to identify some influencing factors, which are later given certain weights to facilitate and simplify the formulation of further advice for users. In this paper, we study the influence of celebrity publications on the formation of prices for a particular cryptocurrency at a certain point in time. The importance and existence of this influence was previously proven by statistical methods. The purpose of the study is to develop an algorithm for studying the level of influence of posts of each of the selected group of experts in social networks on the cryptocurrency rate. The object of the study is the forecast of cryptocurrency rates. The input data used were the list of experts whose level of influence will be studied, the time interval of the study, the number of posts made by each of the experts in question over the specified period of time, and the actual cryptocurrency rates for the relevant period. The experts were well-known personalities who are either knowledgeable in the field of finance in general and cryptocurrencies in particular, or whose activities are somehow related to a particular cryptocurrency. Research methods. Experts are ranked based on the full probability and Bayesian formulas. Forecasting of cryptocurrency rates in a selected period of time is carried out using the algorithm for forecasting cryptocurrency rates based on expert posts on social networks (AUDSM). To control the accuracy of forecasts, the relative average error is calculated. Recommendations for financial transactions with cryptocurrencies are formed by entering the critical value of the exchange rate and calculating the arithmetic mean of cryptocurrency exchange rates for a specified period of time. Results. As a result of the research, an algorithm has been developed that allows taking into account the impact of the posts of each of the selected ranked group of experts on changes in the rates of a particular cryptocurrency. On the basis of the obtained forecasts, the paper presents a methodology for forming recommendations for financial transactions with them.

Learning to Extract Expert Teams in Social Networks

Finding a set of suitable experts with minimized communication overhead to perform a complex task finds a wide spectrum of applications in industry, education, and other scenarios. This class of problems, widely formulated as forming a team of experts in social networks (i.e., team formation problem), is very challenging due to its NP-hardness and has attracted much research attention. Although various effective and elegant algorithms have been proposed to address this important problem, the methods are usually manually designed and handcrafted, which require considerable human efforts. In this article, we make our first attempt to automate the algorithm design with a machine learning-based approach, named reinforcement learning-based expert team identification (RELEXT). Moreover, we also propose two novel graph embedding methods to consider two important dimensions of the team formation problem, i.e., the skill and social dimensions. We evaluate the proposed approaches on multiple large-scale real datasets. The experimental results show that our proposed approaches outperform the other baselines in terms of solution quality and efficiency.

Expertise in Social Networks: How Do Experts Differ from Other Users?

Expertise location is a difficult task, with expertise often being implied and liable to change. In this paper we propose a heuristic-based approach for automated identification of expertis eon Twitter. We collect tweets from experts and non-experts in different domains and compute different types of features based on the heuristics regarding properties of the messages written and re-tweeted by the experts. We show that these heuristics provide us with interesting insights regarding how experts differ from other user groups which can help guide future studies in this areas and algorithms for expertise location.

An Interval-Valued Best–Worst Method with Normal Distribution for Multi-criteria Decision-Making

A novel three-stage multi-criteria decision-making (MCDM) method considering the interval-valued best–worst method (BWM) and social networks including the following three main modules is put forward: (1) the weights of experts; (2) the weights of criteria; (3) the weighted sum method (WSM). Firstly, a new framework for computing the weights of experts in social networks is construct. Let the values of trust and distrust be interval values rather than fixed values, and then construct a complete trust preference matrix through trust propagation. Subsequently, trust score obtained by synthesizing the trust preference matrix is used to assign the weights of experts. Secondly, an interval-valued BWM model with normal distribution is developed to compute the weights of criteria. The proposed BWM model innovatively uses interval fuzzy numbers with normal distribution to represent the preference degree of experts instead of the fixed values in the basic BWM model. Thirdly, considering the WSM, this paper constructs a novel three-stage MCDM method considering the proposed novel BWM model and social networks. The proposed MCDM model innovatively aims at the situation where both the weights of experts and criteria are not known, and provides mathematical models for solving them respectively. Finally, a case is used to prove the utility and availability of the novel MCDM method. The results show that the novel MCDM method can not only reduce the subjectivity in decision making, but also can effectively solve the MCDM problems.

Identifying a Team of Experts in Social Networks using a Cultural Algorithm

We study the problem of identifying a team of experts in a social network. In this problem, each individual (i.e., expert) posses a set of skills based on its past experience or training. Experts form a social network based on their past collaboration with each other: if two experts work on the same project in the past, they are connected in the underlying social network. The success of a project depends on finding the right experts that cover all the required skills. In addition to covering the required skills, we prefer the experts in the same team have past collaboration. Past collaboration expedites the completion of the project since team members already know each other and get along well. In order to differentiate different teams from each other, we use the notion of the communication cost among team members. Clearly, the lower the communication cost, the more collaborative the team is. We use the diameter and the sum of distances as communication cost functions. Therefore, our goal is to find a team of experts that while covering all the required skills, also has minimum communication cost. Optimizing each of these functions are proved to be NP-hard. In this paper we propose a knowledge-based evolutionary optimization algorithm to solve this problem. We perform extensive experiments on large DBLP network to show the viability of our approach in comparison to the state of the art.

The Distribution and Determinants of Socially Supplied Political Expertise

Recent work on social influence has highlighted the importance of socially supplied political expertise, crediting it with strengthening attitudes, resolving ambivalence, and encouraging political participation. However, in focusing on the consequences of socially supplied political expertise, scholars have made the implicit assumption that citizens have equal access to this resource and have largely ignored its distribution. Given that individuals are constrained by their social contexts, we are particularly troubled by this oversight, and thus use two nationally representative data sources to explore the distribution of expertise among and throughout the social networks of citizens. We find consistent evidence that existing resource inequalities reinforce the unequal distribution of expertise in social networks—a gender-moderated pattern that involvement in civil society may help remedy.

EXPERTS SEARCH AND RANK WITH SOCIAL NETWORK: AN ONTOLOGY-BASED APPROACH

Experts finding, one of the most important tasks in social networks, is aimed at identifying individuals with relevant expertise or experience in a given topic. Several approaches have been proposed for finding experts in social networks from documents or web repositories. However, the semantic approach for modeling the information to find experts has not yet been explored. In this paper, we propose a novel method to index the academic information in an ontology-based model for finding and ranking the experts in a particular domain. Additionally, we propose an effective method to construct the academic social network by exploring the relations among the experts and measuring the score of each expert. The score of an expert is measured considering the contributions of relevant publications and relationships among other expert candidates. It is very efficient to find and ranking experts to take advantage of the millions of candidate experts being with relationships. An experiment conducted to evaluate our model shows that experts finding and ranking with an ontological approach integrated with the social network is more effective than other approaches.