برآورد تلفیقی احتمالات تأثیر برای مسأله بیشینه‌سازی گسترش تأثیر در شبکه‌های اجتماعی و کاربرد آن در صنعت برق
محورهای موضوعی : مهندسی کامپیوتر و فناوری اطلاعات
سهامه محمدی
1
,
محمد حسین ندیمی شهرکی
2
,
زهرا بهشتی
3
,
کامران زمانی فر
4
1 - دانشکده مهندسی کامپیوتر- واحد نجف آباد، دانشگاه آزاد اسلامی، نجف آباد، ایران
2 - دانشکده مهندسی کامپیوتر- واحد نجف آباد، دانشگاه آزاد اسلامی، نجف آباد، ایران
3 - دانشکده مهندسی کامپیوتر- واحد نجف آباد، دانشگاه آزاد اسلامی، نجف آباد، ایران
4 - دانشکده مهندسی کامپیوتر، دانشگاه اصفهان، اصفهان، ایران.
کلید واژه: شبکه‌های اجتماعی, بیشینه‌سازی تأثیر, مدلسازی انتشار اطلاعات, احتمالات تأثیر,
چکیده مقاله :
امروزه شبکه‌های اجتماعی آنلاین ارتباط ناگسستنی با زندگی روزمره بسیاری از مردم جهان دارند. کاربرد شبکه‌های اجتماعی در کسب و کارها جهت تبلیغات، بازاریابی، سیستم‌های پیشنهاد دهنده و همچنین در سیستم‌های مدیریت مصرف منابع و انرژی رو به افزایش می‌باشد. یکی از مهم‌ترین مسائل مطرح شده در رابطه با فرایند انتشار اطلاعات در شبکه‌های اجتماعی، مسأله بیشینه‌سازی گسترش تأثیر می‌باشد. در سال‌های اخیر، تحقیق‌هایی برای بهبود کیفیت پیش‌بینی مدل‌های انتشار اطلاعات در این مسأله انجام شده است. طی بررسی‌های انجام شده در مدل‌های موجود، تخمین احتمالات تأثیر کاربران بر روی یکدیگر به طور غیر واقعی محاسبه می‌شود. در این پژوهش با هدف بررسی و بهینه‌سازی فرایند گسترش تأثیر در شبکه‌های اجتماعی، روش جدیدی برای تعیین احتمالات تأثیر در میان کاربران پیشنهاد شده است. این روش تلفیقی از دو رویکرد اصلی محاسبه احتمالات تأثیر شامل بهره‌گیری از جدول لاگ فعالیت و روش یکنواخت مقدار از پیش تعیین شده است. عملکرد روش پیشنهادی بر روی مجموعه داده‌های مختلفی از شبکه‌های اجتماعی دنیای واقعی با روش‌های رقیب مورد ارزیابی و مقایسه قرار گرفت. نتایج حاصل از آزمایش¬ها نشان می‌دهد روش پیشنهادی می‌تواند باعث افزایش کارایی پیش¬بینی‌های مورد نظر جهت حل مسائل بیشینه‌سازی گسترش تأثیر گردد.
Nowadays, online social networks have an inseparable connection with the daily life of many people in the world. The applications of social networks are increasing in businesses for advertising, marketing, and recommender systems, as well as in resource and energy consumption management systems. One of the most important problems in the information diffusion process of social networks is the influence maximization. In recent years, some research has been conducted to improve the prediction quality of information diffusion models in this problem. In a review of existing models, the influence probabilities among users are estimated unrealistically. In this research, a new method has been proposed to determine the influence probabilities among social network users. This method is a combination of two main approaches in the calculation of influence probabilities, including the use of an action log table and the uniform method with a predetermined value. The performance of the proposed method was evaluated and compared with competitive methods on different real-world social network data sets. The results of the experiments show that the proposed method can increase the efficiency of the predictions in solving the influence maximization problems.
[1] C. Aslay, L. V. Lakshmanan, W. Lu, and X. Xiao, "Influence maximization in online social networks," in Proceedings of the eleventh ACM international conference on web search and data mining, 2018, pp. 775-776.
[2] Y. Li, W. Chen, Y. Wang, and Z.-L. Zhang, "Influence diffusion dynamics and influence maximization in social networks with friend and foe relationships," in Proceedings of the sixth ACM international conference on Web search and data mining, 2013, pp. 657-666.
[3] N. Girdhar and K. Bharadwaj, "Signed social networks: a survey," in International Conference on Advances in Computing and Data Sciences, 2016, pp. 326-335: Springer.
[4] M. Kaya, J. Kawash, S. Khoury, and M.-Y. Day, Social network based big data analysis and applications. Springer, 2018.
[5] S. Peng, S. Yu, and P. Mueller, "Social networking big data: Opportunities, solutions, and challenges," vol. 86, ed: Elsevier, 2018, pp. 1456-1458.
[6] M. Richardson and P. Domingos, "Mining knowledge-sharing sites for viral marketing," in Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, 2002, pp. 61-70.
[7] E. Even-Dar and A. Shapira, "A note on maximizing the spread of influence in social networks," Information Processing Letters, vol. 111, no. 4, pp. 184-187, 2011.
[8] S. Kumar, A. Mallik, A. Khetarpal, and B. Panda, "Influence maximization in social networks using graph embedding and graph neural network," Information Sciences, 2022.
[9] K. Senanayaka, "Impact of Social Network Advertising towards Consumer Purchase Intention (Special Reference to Apparel Products Advertising in Facebook)," Uva Wellassa University of Sri Lanka, 2017.
[10] H. Wu, S. Wang, and H. Fang, "LP-UIT: A Multimodal Framework for Link Prediction in Social Networks," in 2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), 2021, pp. 742-749: IEEE.
[11] M. H. Nadimi-Shahraki and M. Adami-Dehkordi, "K-indicators Method for Community Detection in Social Networks," Int. J. Advance Soft Compu. Appl, vol. 8, no. 3, pp. 137-159, 2016.
[12] J. Yang, C. Yao, W. Ma, and G. Chen, "A study of the spreading scheme for viral marketing based on a complex network model," Physica A: Statistical Mechanics and its Applications, vol. 389, no. 4, pp. 859-870, 2010.
[13] M. Alshahrani, Z. Fuxi, A. Sameh, S. Mekouar, and S. Huang, "Efficient Algorithms based on Centrality Measures for Identification of Top-K Influential Users in Social Networks," Information Sciences, 2020.
[14] J. Cheriyan and G. Sajeev, "Spreadmax: a scalable cascading model for influence maximization in social networks," in 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2018, pp. 1290-1296: IEEE.
[15] C. Wang, Y. Liu, X. Gao, and G. Chen, "A Reinforcement Learning Model for Influence Maximization in Social Networks," in International Conference on Database Systems for Advanced Applications, 2021, pp. 701-709: Springer.
[16] O. Gil-Or, "The potential of Facebook in creating commercial value for service companies," Advances in Management, vol. 3, no. 2, pp. 20-25, 2010.
[17] Ö. OKAT and K. KADİRHAN, "ARTIFICIAL INTELLIGENCE-ASSISTED PROGRAMMATIC ADVERTISING," New Communication Approaches in the Digitalized World, p. 87, 2020.
[18] P. Domingos and M. Richardson, "Mining the network value of customers," in Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, 2001, pp. 57-66.
[19] D. Kempe, J. Kleinberg, and É. Tardos, "Maximizing the spread of influence through a social network," in Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, 2003, pp. 137-146.
[20] J. Zhang and P. S. Yu, "Information diffusion," in Broad Learning Through Fusions: Springer, 2019, pp. 315-349.
[21] D. Kempe, J. Kleinberg, and É. Tardos, "Influential nodes in a diffusion model for social networks," in International Colloquium on Automata, Languages, and Programming, 2005, pp. 1127-1138: Springer.
[22] Y. Ni, L. Xie, and Z.-Q. Liu, "Minimizing the expected complete influence time of a social network," Information Sciences, vol. 180, no. 13, pp. 2514-2527, 2010.
[23] A. Goyal, F. Bonchi, and L. V. Lakshmanan, "Learning influence probabilities in social networks," in Proceedings of the third ACM international conference on Web search and data mining, 2010, pp. 241-250.
[24] M. Hosseini-Pozveh, K. Zamanifar, and A. R. Naghsh-Nilchi, "Assessing information diffusion models for influence maximization in signed social networks," Expert Systems with Applications, vol. 119, pp. 476-490, 2019.
[25] S. Ahmed and C. Ezeife, "Discovering influential nodes from trust network," in Proceedings of the 28th annual acm symposium on applied computing, 2013, pp. 121-128.
[26] S. Kumar, B. Hooi, D. Makhija, M. Kumar, C. Faloutsos, and V. Subrahmanian, "Rev2: Fraudulent user prediction in rating platforms," in Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, 2018, pp. 333-341.
[27] S. Kumar, F. Spezzano, V. Subrahmanian, and C. Faloutsos, "Edge weight prediction in weighted signed networks," in 2016 IEEE 16th International Conference on Data Mining (ICDM), 2016, pp. 221-230: IEEE.
