User recommendation in Telegram messenger by graph analysis and mathematical modeling of users' behavior
Subject Areas :Davod Karimpour 1 , Mohammad Ali Zare Chahooki 2 , Ali Hashemi 3
1 - MSc. Student
2 - Yazd University
3 - Faculty of Computer Engineering, Yazd University,
Keywords: Recommender systems, Telegram messenger, graph analysis, users' behavior.,
Abstract :
Recommender systems on social networks and websites have been developed to reduce the production and processing of queries. The purpose of these systems is to recommend users various items such as books, music, and friends. Users' recommendation on social networks and instant messengers is useful for users to find friends and for marketers to find new customers. On social networks such as Facebook, finding target users for marketing is an integrated feature, but in instant messengers such as Telegram and WhatsApp, it is not possible to find the target community. In this paper, by using graph and modeling the intergroup behavior of users and also defining features related to groups, a method for recommending Telegram users has been presented. The proposed method consists of 8 steps and each step can be considered a separate method for user recommendation. The data used in this paper is a real data set including more than 900,000 supergroups and 120 million Telegram users crawled by the Idekav system. Evaluation of the proposed method on high-quality groups showed an average reduction in error by 0.0812 in RMSE and 0.128 in MAE.
[1] Durov, P. 2020. 400 Million Users, 20,000 Stickers, Quizzes 2.0 and €400K for Creators of Educational Tests, accessed 10 January 2021, < https://telegram.org/blog/400-million>.
[2] Iqbal, M. 2020. Telegram revenue and usage statistics, accessed 13 May 2021, < https://www.businessofapps.com/data/telegram-statistics/>.
[3] Clement, J. 2020. Most popular global mobile messenger apps as of October 2020, based on number of monthly active users, accessed 10 January 2021, < https://www.statista.com/statistics/258749/most-popular-global-mobile-messenger-apps/ >.
[4] میلانی، فرزانه. زنوزی، سیدجعفر. (1398) « بررسی تاثیر استفاده از انواع استراتژیهای بازاریابی در شبکه‌های اجتماعی بر جلب اعتماد مشتریان شورایی»، دوفصلنامه فناوری اطلاعات و ارتباطات ایران، دوره 11، شماره 39 (1398): 104-91.
[5] فتحیان، محمد. حضرتقلی‌زاده، رحیم. (1395) «ارائه روشی مناسب برای دسته‌بندی نامه‌های الکترونیکی تبلیغاتی بر مبنای پروفایل کاربران»، دوفصلنامه فناوری اطلاعات و ارتباطات ایران، دوره 8، شماره 27 (1395): 36-21.
[6] بهشتی‌نژاد، راحله. سمیع، محمدابراهیم. (1396) « بهبود سیستم‌های توصیه‌گر با کمک وب معنایی»، دوفصلنامه فناوری اطلاعات و ارتباطات ایران، دوره 9، شماره 31 (1396): 56-45.
[7] صابری، نفیسه. منتظر، غلامعلی. (1389) « شخصی سازی محیط یادگیری الکترونیکی به کمک توصیه گر فازی مبتنی برتلفیق سبک یادگیری و سبک شناختی»، دوفصلنامه فناوری اطلاعات و ارتباطات ایران، دوره 2، شماره 3 (1389): 109-91.
[8] هاشمی، سیدعلی. زارع چاهوکی، محمدعلی. (1397)، «توسعه بازاریابی با توصیه‌گر گروه‌های پیام‌رسان‌ها»، دوفصلنامه محاسبات و سامانه‌های توزیع شده، سال اول، شماره اول (1397): 30-21.
[9] G. Ramakrishnan, V. Saicharan, K. Chandrasekaran, M. V. Rathnamma, and V. Venkata Ramana. "Collaborative Filtering for Book Recommendation System", In: K. Das, J. Bansal, K. Deep, A. Nagar, P. Pathipooranam, R. Naidu (eds) Soft Computing for Problem Solving. Advances in Intelligent Systems and Computing, Vol. 1057, Springer, Singapore, 2020, pp. 325-338.
[10] A. B. Melchiorre, E. Zangerle, and M. Schedl, "Personality Bias of Music Recommendation Algorithms", in Fourteenth ACM Conference on Recommender Systems, New York, NY, USA, 2020, pp. 533–538.
[11] محمدرضایی لرکی، رضوان. روان‌مهر، رضا. امراللهی، میلاد. (1398) «سيستم توصيه گر زمينه آگاه سفر با بهرهگيری از اطلاعات عکسهای برچسبدار جغرافيايی»، دوفصلنامه فناوری اطلاعات و ارتباطات ایران، دوره 11، شماره 41 (1398): 96-75.
[12] L. Sang, M. Xu, S. Qian, M. Martin, P. Li, and X. Wu, "Context-Dependent Propagating based Video Recommendation in Multimodal Heterogeneous Information Networks", IEEE Transactions on Multimedia, July 2020, p. 1.
[13] A. Zare, M. R. Motadel, and A. Jalali, "Presenting a hybrid model in social networks recommendation system architecture development", AI & SOCIETY, Vol. 35, No. 2, June 2020, pp. 469-483.
[14] D. M. JIMÉNEZ-BRAVO, J. F. D. Paz, and G. Villarrubia, "Twitter’s Experts Recommendation System Based on User Content,” In: International Symposium on Distributed Computing and Artificial Intelligence, Springer, Cham, 2018, pp. 251-258.
[15] X. Cai et al., "Learning Collaborative Filtering and Its Application to People to People Recommendation in Social Networks," 2010 IEEE International Conference on Data Mining, 2010, pp. 743-748.
[16] L. Berkani, "A semantic and social‐based collaborative recommendation of friends in social networks", Software: Practice and Experience, Vol. 50, No. 8, August 2020, pp. 1498-1519.
[17] P. Kumar and G. R. Mohana Reddy, “Friendship Recommendation System Using Topological Structure of Social Networks,” in Proc. of Progress Intelligent Computing Techniques: Theory, Practice, and Applications, Singapore, Aug. 2018, pp. 237–246.
[18] S. Huang, J. Zhang, L. Wang, and X.-S. Hua, “Social Friend Recommendation Based on Multiple Network Correlation,” IEEE Transactions on Multimedia, vol. 18, no. 2, pp. 287–299, Feb. 2016.
[19] A. Alshammari, S. Kapetanakis, R. Evans, N. Polatidis, and G. Alshammari, "User modeling on twitter with exploiting explicit relationships for personalized recommendations", In: International Conference on Hybrid Intelligent Systems, Springer, Cham, 2018, pp. 135-145.
[20] D. F. Gurini, F. Gasparetti, A. Micarelli, and G. Sansonetti, “A Sentiment-Based Approach to Twitter User Recommendation,” in Proc. of Recommender System and the Social Web (CEUR Workshop), Hong kong, China, Oct. 2013.
[21] K. Xu et al., “Improving user recommendation by extracting social topics and interest topics of users in uni-directional social networks,” Knowledge-Based Systems, vol. 140, pp. 120–133, Jan. 2018.
[22] H. J. Jeong, K. H. Lee, and M. H. Kim, "DGC: Dynamic group behavior modeling that utilizes context information for group recommendation", Knowledge-Based Systems, Vol. 213, December 2020, p. 106659.
[23] S. Guo, S. J. Ji, C. Zhang, X. Wang, and J. Zhao, "A New Multi-criteria Recommendation Algorithm for Groups of Users", In: International Conference on Genetic and Evolutionary Computing, Springer, Singapore, 2019, pp. 735-742.
[24] F. Ortega, R. Hurtado, J. Bobadilla, and R. Bojorque, "Recommendation to groups of users using the singularities concept", IEEE Access, Vol. 6, July 2018, pp. 39745-39761.
[25] D. Karimpour, M. A. Zare Chahooki and A. Hashemi, "User recommendation based on Hybrid filtering in Telegram messenger," 2021 26th International Computer Conference, Computer Society of Iran (CSICC), 2021, pp. 1-7.
[26] E. Yalcin, F. Ismailoglu, and A. Bilge, "An entropy empowered hybridized aggregation technique for group recommender systems", Expert Systems with Applications, Vol. 166, October 2020, p. 114111.
[27] H. Yin, Q. Wang, K. Zheng, Z. Li, and X. Zhou, "Overcoming Data Sparsity in Group Recommendation", IEEE Transactions on Knowledge and Data Engineering, September 2020.
[28] A. Hashemi and M. A. Z. Chahooki, "Telegram group quality measurement by user behavior analysis", Social Network Analysis and Mining, Vol. 9, No. 1, July 2019, p. 33.
