دانلود مقاله تحلیل دو شبکه اجتماعی: شبکه مدارس و شبکه معامله گر
چکیده
مقدمه
مطالعات مرتبط
روش شناسی
آزمایش 1: شبکه مدارس نوجوانان
آزمایش 2: شبکه اعتماد بیت کوین
تجزیه و تحلیل نتایج و بحث
نتیجه گیری
منابع
Abstract
Introduction
Related works
Methodology
Experiment 1: adolescent school network
Experiment 2: bitcoin trust network
Analysis of results and discussion
Conclusion
References
چکیده
این مقاله تحلیل شبکه های اجتماعی را در دو آزمایش اعمال می کند. در آزمایش اول، تجزیه و تحلیل شبکه های اجتماعی بر روی شبکه های دوستی دانش آموزان برای یافتن الگوهای رابطه ای انجام می شود. سپس از سه روش تشخیص جامعه برای تقسیم شبکه دانش آموزی استفاده می شود. بسته RSiena برای نشان دادن تکامل شبکه های دوستی با رفتار سیگار کشیدن و نوشیدن الکل استفاده می شود. در این آزمایش مشخص شد که در شبکه بسته، روابط متقابل همجنس ترجیح داده می شود. آزمایش دوم یک شبکه اعتماد وزنی را تجزیه و تحلیل می کند که شامل معامله کاربران با بیت کوین در پلت فرم BTC-Alpha می شود. از آنجایی که فروشندگان بیت کوین ناشناس هستند، نیاز فوری به ثبت سابقه اعتباری هر فروشنده برای جلوگیری از کلاهبرداری و سایر مشکلات امنیتی وجود دارد. آزمایش دوم با هدف بهبود مشکلات امنیتی در شبکه اعتماد بیت کوین با استفاده از تجزیه و تحلیل شبکه های اجتماعی انجام می شود.
توجه! این متن ترجمه ماشینی بوده و توسط مترجمین ای ترجمه، ترجمه نشده است.
Abstract
This paper applies social network analysis in two experiments. In the first experiment, social network analysis is conducted on student friendship networks to find relational patterns. Then, three community detection methods are used to divide the student network. The RSiena package is used to illustrate the coevolution of friendship networks with smoking and drinking behavior. In this experiment, it was determined that in the closed network, same-sex reciprocated relationships are preferred. The second experiment analyzes a weighted trust network that involves users trading with Bitcoin on the BTC-Alpha platform. Since the dealers of Bitcoin are anonymous, there is an urgent need to record every dealer’s credit history to prevent fraud and other security problems. The second experiment aims to improve security problems within the Bitcoin trust network by applying social network analysis.
Introduction
Social network analysis (SNA) is a research method that analyzes the relationship of a group of entities, which can be individual persons and organizations, communities, companies, countries, or other collective groups. The phenomena or data reflected by their relationship models are the focus of network analysis.
This paper applies SNA techniques to two different networks. Firstly, an adolescent friendship network, and secondly, a Bitcoin trading network. The research aims of the network analysis are to analyze how the networks are organized and to discover how networks are affected by the behavior of the individuals within them. After applying various community detection algorithms, the results are evaluated, and their advantages and disadvantages are discussed. Finally, the behavior-related effects on network evolution are analyzed by using the R package ‘RSiena’ [1].
Conclusion
The results concluded in this report contribute to the literature on adolescents’ relational patterns in a closed network and the association between drinking and smoking behavior within the friendship network. When considering the parameters of density, reciprocity, transitivity, and centrality, it was discovered that the network is sparse and interaction between it is getting closely related. The important nodes are also highlighted. Three algorithms, including the Girvan-Newman Algorithm, Label Propagation and Fast Greedy, are used to detect the different communities. This paper visualizes the result of each community discovery and compares the strengths and weaknesses, concluding Label Propagation is more applicable for use in this case. It is also concluded that adolescents prefer a reciprocal relationship with the same gender. Drinkers tend to be more active in their social circle. In terms of the coevolution of the friendship network and alcohol consumption, drinkers will be influenced strongly by the drinking behavior of their friends. These findings are consistent with the findings of other studies.