یک سیستم توصیه گر بر اساس تحلیل ویژگی شخصیتی افراد در شبکه اجتماعی تلگرام
محورهای موضوعی : هوش مصنوعی و رباتیکمحمدجواد شایگان فرد 1 , محدثه ولی زاده 2
1 - دانشگاه علم و فرهنگ
2 - گروه کامپیوتر، دانشگاه علم و فرهنگ، تهران، ایران
کلید واژه: رفتار کاربران, سیستم‌های توصیه‌گر, شبکه‌های اجتماعی, تلگرام, تحلیل شخصیت,
چکیده مقاله :
تحلیل ویژگی های شخصیتی افراد همواره یکی از موضوعات جذاب پژوهشی بوده است. علاوه بر این، دستیابی به ویژگی‌های شخصیتی براساس داده‌هایی که از رفتار اشخاص به دست می‌آید، یک موضوع چالش برانگیز است. براساس پژوهش‌های انجام شده؛ اغلب مردم، بیشتر وقت خود را در شبکه‌های اجتماعی صرف می‌کنند و ممکن است در این شبکه‌های اجتماعی، رفتارهایی را از خود بروز دهند که نمایانگر یک شخصیت در فضای مجازی باشد. امروزه شبکه‌های اجتماعی بسیاری وجود دارند که یکی از آن‌ها، شبکه اجتماعی تلگرام است. تلگرام در ایران نیز مخاطبان بسیاری دارد و افراد به منظور برقراری ارتباط، تعامل با دیگران، آموزش، معرفی محصولات و غیره از آن استفاده می‌کنند. این پژوهش به دنبال این موضوع هست که چگونه می توان یک سیستم توصیه گر را بر اساس ویژگی های شخصیتی افراد بنا نهاد. به این منظور، شخصیت کاربران یک گروه تلگرامی را با استفاده از سه الگوریتم Cosine Similarity، MLP و Bayes شناسایی شده و در نهایت با کمک یک سیستم توصیه‌گر، کانال‌های تلگرامی متناسب با شخصیت هر فرد ، به او پیشنهاد می‌شود. نتایج حاصل از تحقیق نشان می‌دهد که این سیستم توصیه‌گر به طور میانگین 42/65 درصد رضایت کاربران را جلب کرده است.
Analysis of personality traits of individuals has always been one of the interesting research topics. In addition, achieving personality traits based on data obtained from individuals' behavior is a challenging issue. Most people spend most of their time on social media and may engage in behaviors that represent a character in cyberspace. There are many social networks today, one of which is the Telegram social network. Telegram also has a large audience in Iran and people use it to communicate, interact with others, educate, introduce products and so on. This research seeks to find out how a recommendation system can be built based on the personality traits of individuals. For this purpose, the personality of the users of a telegram group is identified using three algorithms, Cosine Similarity, MLP and Bayes, and finally, with the help of a recommending system, telegram channels tailored to each individual's personality are suggested to him. The research results show that this recommending system has attracted 65.42% of users' satisfaction.
[1] S. Han, H. Huang, and Y. Tang, "Knowledge of words: An interpretable approach for personality recognition from social media," Knowledge-Based Systems, vol. 194, p. 105550, 2020.
[2] Y. Mehta, S. Fatehi, A. Kazameini, C. Stachl, E. Cambria, and S. Eetemadi, "Bottom-up and top-down: Predicting personality with psycholinguistic and language model features," in 2020 IEEE International Conference on Data Mining (ICDM), 2020: IEEE, pp. 1184-1189.
[3] M. J. Shayegan and M. Valizadeh, "A Method for Identifying Personality Traits in Telegram," in 2022 8th International Conference on Web Research (ICWR), 2022: IEEE, pp. 88-93.
[4] C. Solinger, L. Hirshfield, S. Hirshfield, R. Friendman, and C. Leper, "Beyond Facebook Personality Prediction," in International Conference on Social Computing and Social Media, 2014: Springer, pp. 486-493.
[5] K.-H. Peng, L.-H. Liou, C.-S. Chang, and D.-S. Lee, "Predicting personality traits of Chinese users based on Facebook wall posts," in 2015 24th Wireless and Optical Communication Conference (WOCC), 2015: IEEE, pp. 9-14.
[6] G. Seidman, "Self-presentation and belonging on Facebook: How personality influences social media use and motivations," Personality and individual differences, vol. 54, no. 3, pp. 402-407, 2013.
[7] T. C. Marshall, K. Lefringhausen, and N. Ferenczi, "The Big Five, self-esteem, and narcissism as predictors of the topics people write about in Facebook status updates," Personality and Individual Differences, vol. 85, pp. 35-40, 2015.
[8] J. Golbeck, C. Robles, M. Edmondson, and K. Turner, "Predicting personality from twitter," in 2011 IEEE third international conference on privacy, security, risk and trust and 2011 IEEE third international conference on social computing, 2011: IEEE, pp. 149-156.
[9] J. W. Pennebaker, M. E. Francis, and R. J. Booth, "Linguistic inquiry and word count: LIWC 2001," Mahway: Lawrence Erlbaum Associates, vol. 71, no. 2001, p. 2001, 2001.
[10] M. Coltheart, "The MRC psycholinguistic database," The Quarterly Journal of Experimental Psychology Section A, vol. 33, no. 4, pp. 497-505, 1981.
[11] D. Karanatsiou, P. Sermpezis, D. Gruda, K. Kafetsios, I. Dimitriadis, and A. Vakali, "My tweets bring all the traits to the yard: Predicting personality and relational traits in Online Social Networks," ACM Transactions on the Web (TWEB), vol. 16, no. 2, pp. 1-26, 2022.
[12] A. Khosravi and H. Abdolhosseini, "Personality in social networks using thematic modeling of user feedback," Soft Computing Journal, 2023.
[13] D. Wan, C. Zhang, M. Wu, and Z. An, "Personality prediction based on all characters of user social media information," in Chinese National Conference on Social Media Processing, 2014: Springer, pp. 220-230.
[14] R. Wald, T. Khoshgoftaar, and C. Sumner, "Machine prediction of personality from Facebook profiles," in 2012 IEEE 13th International Conference on Information Reuse & Integration (Iri), 2012: IEEE, pp. 109-115.
[15] L. Liu, D. Preotiuc-Pietro, Z. R. Samani, M. E. Moghaddam, and L. Ungar, "Analyzing personality through social media profile picture choice," in Tenth international AAAI conference on web and social media, 2016.
[16] L. C. Lukito, A. Erwin, J. Purnama, and W. Danoekoesoemo, "Social media user personality classification using computational linguistic," in 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE), 2016: IEEE, pp. 1-6.
[17] S. Kedar and D. Bormane, "Automatic personality assessment: A systematic review," in 2015 International Conference on Information Processing (ICIP), 2015: IEEE, pp. 326-331.
[18] R. Lambiotte and M. Kosinski, "Tracking the digital footprints of personality," Proceedings of the IEEE, vol. 102, no. 12, pp. 1934-1939, 2014.
[19] S. Ouni, F. Fkih, and M. N. Omri, "A survey of machine learning-based author profiling from texts analysis in social networks," Multimedia Tools and Applications, vol. 82, no. 24, pp. 36653-36686, 2023/10/01 2023, doi: 10.1007/s11042-023-14711-8.
[20] K. Biswas, P. Shivakumara, U. Pal, T. Chakraborti, T. Lu, and M. N. B. Ayub, "Fuzzy and genetic algorithm based approach for classification of personality traits oriented social media images," Knowledge-Based Systems, p. 108024, 2021.
[21] T. A. Mooradian and J. B. Nezlek, "Comparing the NEO-FFI and Saucier's Mini-Markers as measures of the Big Five," Personality and Individual Differences, vol. 21, no. 2, pp. 213-215, 1996.
[22] A. Furnham, "The big five versus the big four: the relationship between the Myers-Briggs Type Indicator (MBTI) and NEO-PI five factor model of personality," Personality and Individual Differences, vol. 21, no. 2, pp. 303-307, 1996.
[23] S. Jabri, A. Dahbi, T. Gadi, and A. Bassir, "Ranking of text documents using TF-IDF weighting and association rules mining," in 2018 4th International Conference on Optimization and Applications (ICOA), 2018: IEEE, pp. 1-6.
[24] B. Li and L. Han, "Distance weighted cosine similarity measure for text classification," in International Conference on Intelligent Data Engineering and Automated Learning, 2013: Springer, pp. 611-618.
[25] J. Bergstra, D. Yamins, and D. D. Cox, "Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms," in Proceedings of the 12th Python in science conference, 2013: Citeseer, pp. 13-20.
[26] M. W. Gardner and S. Dorling, "Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences," Atmospheric environment, vol. 32, no. 14-15, pp. 2627-2636, 1998.
