ارائه مدلی برای تخمین میزان برون‌گرایی اعضای شبکه اجتماعی با استفاده از اطلاعات ساختار گراف

نویسندگان

دانشگاه اصفهان

چکیده

با آگاهی از شخصیت اعضای شبکه‌های اجتماعی می‌توان بسیاری از سرویس‌های ارائه شده به این افراد را بهبود بخشید و یا از این اطلاعات برای بهبود روابط اعضای شبکه اجتماعی با یکدیگر استفاده کرد. یک روش برای تخمین شخصیت اعضای شبکه‌های اجتماعی استفاده صریح از پرسشنامه‌های شخصیتی است. ولی بسیاری افراد این کار را نقض حریم شخصی خود می‌دانند و یا تمایلی به صرف وقت برای پرکردن پرسشنامه ندارند. به همین دلیل نیاز است ویژگی‌های شخصیتی اعضا به صورت غیرمستقیم تخمین زده شود. روش‌هایی که برای این منظور در تحقیقات پیشین ارائه شده‌اند همگی نیازمند دسترسی به پروفایل و اطلاعات محتوایی و متنی اعضا هستند. درحالیکه دسترسی به این اطلاعات همواره امکان‌پذیر نیست و می‌تواند موجب نقض حریم خصوصی افراد گردد. در این مقاله مدلی ارائه می‌شود که به صورت غیرمستقیم و بدون نقض حریم خصوصی افراد، تنها با در اختیار ‌داشتن اطلاعاتی راجع به ساختار گرافی که حول هر عضو شبکه اجتماعی وجود دارد، می‌تواند میزان برون‌گرایی آن عضو را تخمین بزند. برای ایجاد این مدل، ابتدا داده‌های مربوط به تعدادی از اعضای شبکه اجتماعی جمع‌آوری شده‌ است. سپس با استفاده از دو روش برنامه‌نویسی ژنتیک و قوانین رگرسیون M5 بر روی این داده‌ها، روابطی استخراج شده‌اند که با دریافت سه ویژگی از ساختار گراف هر عضو شبکه اجتماعی می‌توانند میزان برون‌گرایی او را تخمین بزنند. نتایج نشان می‌دهد که این دو روش با دقت بالایی این تخمین را انجام می‌دهند. همچنین، مدل حاصل از برنامه‌نویسی ژنتیک در مقایسه با رگرسیون M5، دقت بالا‌تر و پیچیدگی محاسباتی کمتری دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Developing a Model for Estimating the Extraversion Degree of Social Network Members Using the Information Extracted from the Graph Structure

نویسندگان [English]

  • Iman Golkar
  • Marjan Kaedi
چکیده [English]

Having knowledge about the personality of social network members can improve the social network services. This knowledge also can be applied to improve the interactions of social network members. The personality characteristics of social network members can be estimated via personality questionnaires. However, usually people are not interested in filling these questionnaires because it may violate their privacy. So, their personality characteristics should be estimated implicitly. In previous researches some methods have been presented to estimate the personality of social network members implicitly. However, these methods require the users’ profile and contextual information that is not accessible in most of the cases. In this paper, a model is presented which can estimate the extraversion degree of social network members implicitly using information extracted from the graph structure around each member. To develop this model, first, a dataset of social network members are collected. Then, by applying genetic programming and M5 regression on this dataset, some relations are extracted to estimate the extraversion degree of each member. The results of our model show high accuracy. In addition, the model extracted by genetic programming has higher accuracy and lower computational complexity compared to M5 regression.

کلیدواژه‌ها [English]

  • Personality modeling
  • Social networks
  • extraversion
  • Genetic programming
  • M5 regression
 

[1]           J. A. Golbeck, "Computing and applying trust in web-based social networks," PhD, College Park, University of Maryland, 2005.

[2]           J. Golbeck, C. Robles, and K. Turner, "Predicting Personality with Social Media," ACM 978-1-4503-0268, pp. 253-262, 2011.

[3]           N. B. Ellison, "Social network sites: Definition, history, and scholarship," Journal of Computer Mediated Communication, vol. 13, pp. 210-230, 2007.

[4]           Y. Amichai-Hamburger and G. Vinitzky, "Social network use and personality," Computers in Human Behavior, vol. 26, pp. 1289-1295, 2010.

[5]           J. Feist, G. J. Feist, and T.-A. Roberts, Theories of personality: McGraw-Hill New York, 2006.

[6]           M. D. Back, J. M. Stopfer, S. Vazire, S. Gaddis, S. C. Schmukle, B. Egloff, and S. D. Gosling, "Facebook profiles reflect actual personality, not self-idealization," Psychological Science, vol. 21, pp. 372-374, 2010.

[7]           P. Bonhard and M. Sasse, "’Knowing me, knowing you’—Using profiles and social networking to improve recommender systems," BT Technology Journal, vol. 24, pp. 84-98, 2006.

[8]           M. Goeksel and C. P. Lam, "System and method for utilizing social networks for collaborative filtering," ed: Google Patents, 2010.

[9]           Y.-M. Li, C.-Y. Lai, and C.-H. Lin, "Discovering Influential Nodes for Viral Marketing," in the 42nd Hawaii International Conference on System Sciences - IEEE, Hawaii, USA, 2009.

[10]         Y.-M. Li, C.-H. Lin, and C.-Y. Lai, "Identifying influential reviewers for word-of-mouth marketing," Electronic Commerce Research and Applications, pp. 294–304, 2010.

[11]         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.

[12]         Z. Zhu, "Discovering the influential users oriented to viral marketing based on online social network," Physica A: Statistical Mechanics and its Applications, 2013.

[13]         K. Wakita and T. Tsurumi, "Finding community structure in mega-scale social networks:[extended abstract]," in Proceedings of the 16th international conference on World Wide Web, 2007, pp. 1275-1276.

[14]         Y. Zhao, E. Levina, and J. Zhu, "Community extraction for social networks," Proceedings of the National Academy of Sciences, vol. 108, pp. 7321-7326, 2011.

[15]         P. P. Zubcsek and M. Sarvary, "Advertising to a social network," Quantitative Marketing and Economics, vol. 9, pp. 71-107, 2011.

[16]         P.-T. Chen and H.-P. Hsieh, "Personalized mobile advertising: Its key attributes, trends, and social impact," Technological Forecasting and Social Change, vol. 79, pp. 543-557, 2012.

[17]         R. R. McCrae and O. P. John, "An introduction to the five‐factor model and its applications," Journal of personality,vol. 60, pp. 175-215, 1992.

[18]         C. Sand, A Guide to the Big Five Personality Traits: Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism: Webster's Digital Services, 2012.

[19]         R. R. McCrae and P. T. Costa, "Validation of the five-factor model of personality across instruments and observers," Journal of personality and social psychology, vol. 52, pp. 81-90, 1987.

[20]         T. Oren and N. Ghasem-Aghaee, "Personality representation processable in fuzzy logic for human behavior simulation," in Summer Computer Simulation Conference, 2003, pp. 11-18.

[21]         P. T. Costa and R. R. MacCrae, Revised NEO Personality Inventory (NEO PI-R) and NEO Five-Factor Inventory (NEO FFI): Professional Manual: Psychological Assessment Resources, 1992.

[22]         B. E. de Raad and M. E. Perugini, Big five assessment: Hogrefe & Huber Publishers, 2002.

[23]         A. Aly and A. Tapus, "A model for synthesizing a combined verbal and nonverbal behavior based on personality traits in human-robot interaction," in Proceedings of the 8th ACM/IEEE international conference on Human-robot interaction, 2013, pp. 325-332.

[24]         A. Zoumpoulaki, N. Avradinis, and S. Vosinakis, "A multi-agent simulation framework for emergency evacuations incorporating personality and emotions," in Artificial Intelligence: Theories, Models and Applications, ed: Springer, 2010, pp. 423-428.

[25]         M. A. S. Nunes and R. Hu, "Personality-based recommender systems: an overview," in Proceedings of the sixth ACM conference on Recommender systems, 2012, pp. 5-6.

[26]         M. D. Ekstrand, J. T. Riedl, and J. A. Konstan, "Collaborative filtering recommender systems," Foundations and Trends in Human-Computer Interaction, vol. 4, pp. 81-173, 2011.

[27]         L. F. Capretz and F. Ahmed, "Making sense of software development and personality types," IT professional, vol. 12, pp. 6-13, 2010.

[28]         H. Keller and S. J. Karau, "The importance of personality in students’ perceptions of the online learning experience," Computers in Human Behavior, vol. 29, pp. 2494-2500, 2013.

[29]         O. Nov, O. Arazy, C. López, and P. Brusilovsky, "Exploring personality-targeted UI design in online social participation systems," in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2013, pp. 361-370.

[30]         T. Zhou and Y. Lu, "The effects of personality traits on user acceptance of mobile commerce," Intl. Journal of Human–Computer Interaction, vol. 27, pp. 545-561, 2011.

[31]         D. Quercia, M. Kosinski, D. Stillwell, and J. Crowcroft, "Our Twitter profiles, our selves: Predicting personality with Twitter," in Privacy, security, risk and trust (passat), 2011 ieee third international conference on and 2011 ieee third international conference on social computing (socialcom), 2011, pp. 180-185.

[32]         Y. Kalish and G. Robins, "Psychological predispositions and network structure: The relationship between individual predispositions, structural holes and network closure," Social Networks, vol. 28, pp. 56-84, 2006.

[33]         L. Qiu, H. Lin, J. Ramsay, and F. Yang, "You are what you tweet: Personality expression and perception on twitter," Journal of Research in Personality, vol. 46, pp. 710-718, 2012.

[34]         D. O. Olguın, P. A. Gloor, and A. S. Pentland, "Capturing individual and group behavior with wearable sensors," in Proceedings of the 2009 aaai spring symposium on human behavior modeling, SSS, 2009.

[35]         S. G. Roberts, R. Wilson, P. Fedurek, and R. Dunbar, "Individual differences and personal social network size and structure," Personality and Individual Differences, vol. 44, pp. 954-964, 2008.

[36]         J. Golbeck, C. Robles, M. Edmondson, and K. Turner, "Predicting personality from twitter," in Privacy, security, risk and trust (passat), 2011 ieee third international conference on and 2011 ieee third international conference on social computing (socialcom), 2011, pp. 149-156.

[37]         D. Quercia, R. Lambiotte, D. Stillwell, M. Kosinski, and J. Crowcroft, "The personality of popular facebook users," in Proceedings of the ACM 2012 conference on Computer Supported Cooperative Work, 2012, pp. 955-964.

[38]         J. Staiano, B. Lepri, N. Aharony, F. Pianesi, N. Sebe, and A. Pentland, "Friends don't lie: inferring personality traits from social network structure," in Proceedings of the 2012 ACM Conference on Ubiquitous Computing, 2012, pp. 321-330.

[39]         L. Li, A. Li, B. Hao, Z. Guan, and T. Zhu, "Predicting Active Users' Personality Based on Micro-Blogging Behaviors," PloS one, vol. 9, p. e84997, 2014.

[40]         م. گ. فرشی, رویکردی نوین در ارزیابی شخصیت. تبریز: نشر جامعه پژوه, 1380.

[41]         J. Scott, Social network analysis: SAGE Publications Limited, 2012.

[42]         G. Holmes, M. Hall, and E. Prank, Generating rule sets from model trees: Springer, 1999.

[43]         M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten, "The WEKA data mining software: an update," ACM SIGKDD explorations newsletter, vol. 11, pp. 10-18, 2009.

[44]         R. Poli and J. Koza, Genetic Programming: Springer, 2014.

[45]         D. Searson, "GPTIPS: Genetic programming & symbolic regression for MATLAB," Available from gptips. sourceforge. net,[Accessed 10 February, 2010], 2009.