A model for estimating the posting frequency in an online social media with incomplete data using objective determinants of users' behaviour

V. F. Stoliarova ; A. Toropova ; A. L. Tulupyev

Nečetkie sistemy i mâgkie vyčisleniâ, Tome 16 (2021) no. 2, pp. 77-95.

Résumé

User profiling is related to the problem of estimation of frequency of certain user’s actions in an online social media, like posting. But due to limited resources the only information available may be imprecise information on several last episodes of posting, that can be gathered via an interview. The frequency of posting estimates with such limited data may be used in the individual risk assessment that is connected with the use of online social media, for example, in medicine or cybersecurity. In the paper the Bayes belief network (BBN) for this problem is constructed, that incorporates not only the limited data on times of several last posts in an online social media, but the objective data about the user’s profile: age, sex, and friends count. With the training dataset gathered via API VKontakte we estimated conditional probability tables for two expert BBN structures (existing reduced structure based only on dates of several last posts and novel extended structure with objective behavior determinants incorporated) and automatically learned the optimal structure for the training data. Both extended models (expert and learned) showed lower values of the information criteria (Akaike information criteria and bayesian information criteria). Then with the test dataset the classification problem of the true frequency value was assessed. All three models showed similar results based on accuracy, kappa and average accuracy characteristics. This result is related to the weak strength of arcs between frequency variable and objective behavior determinants. But nevertheless the use of such variables is important in the application in order to construct the comprehensive structure of the knowledge in the area of interest. The practical significance of the work lies in the possibility of applying the proposed model to assess the posting frequency in the online social network, in particular in the tasks of modeling risk in the field of public health and socio-cybersecurity.

Détail

Keywords: online social networks, posting frequency, Bayesian belief networks, behaviour determinants, user profiling.

Bibliographie

[1] Alalwan A. A., Rana N. P., Dwivedi Y. K., Algharabat R., “Social media in marketing: A review and analysis of the existing literature”, Telematics and Informatics, 34:7 (2017), 1177–1190 | DOI

[2] Basaran S., Ejimogu O. H., “A Neural Network Approach for Predicting Personality From Facebook Data”, SAGE Open, 11:3 (2021), 21582440211032156 | DOI | MR

[3] Busalim A. H., Masrom M., Binti Wan.Zakaria.W. N., “The impact of Facebook Addiction and self-esteem on students' academic performance: A multi-group analysis”, Computers Education, 142 (2019), 103651 | DOI

[4] Van Dam.J. W., Van De.Velden.M., “Online profiling and clustering of Facebook users”, Decision Support Systems, 70 (2015), 60–72 | DOI

[5] Ellison N. B., Steinfield C., Lampe C., “The Benefits of Facebook ‘`Friends:" Social Capital and College Students’ Use of Online Social Network Sites”, Journal of Computer-Mediated Communication, 4:12 (2007), 1143–1168 | DOI

[6] Giustini D., Ali S. M., Fraser M., Boulos M. N. K., “Effective uses of social media in public health and medicine: a systematic review of systematic reviews”, Online journal of public health informatics, 10:2 (2018), e215 | DOI

[7] Gosling S. D., Augustine A. A., Vazire S., Holtzman N., Gaddis S., “Manifestations of personality in online social networks: Self-reported Facebook-related behaviors and observable profile information”, Cyberpsychology, Behavior, and Social Networking, 14:9 (2011), 483–488 | DOI

[8] Ilakkuvan V., Johnson A., Villanti A. C., Evans W. D., Turner M., “Patterns of social media use and their relationship to health risks among young adults”, Journal of Adolescent Health, 64:2 (2019), 158–164 | DOI

[9] Inuwa-Dutse I., Liptrott M., Korkontzelos I., “Detection of spam-posting accounts on Twitter”, Neurocomputing, 315 (2018), 496–511 | DOI

[10] Junco R., “Too much face and not enough books: The relationship between multiple indices of Facebook use and academic performance”, Computers in human behavior, 28:1 (2012), 187–198 | DOI

[11] Kachamas P., Akkaradamrongrat S., Sinthupinyo S., Chandrachai A., “Application of artificial intelligent in the prediction of consumer behavior from Facebook posts analysis”, International Journal of Machine Learning and Computing, 9:1 (2019), 91–97 | DOI

[12] Kalimeri K., Beiro M. G., Bonanomi A., Rosina A., Cattuto C., “Traditional versus Facebook-based surveys”, Demographic research, 42 (2020), 133–148 | DOI

[13] Khlobystova A. O., Abramov M. V., Tulupyeva T. V., “Application of the Altematives Method Probabilities in Construction of Intensity of User Communications Estimates”, 2020 XXIII IEEE International Conference on Soft Computing and Measurements, SCM (St. Petersburg, Russia. 2020), 22–24 | DOI

[14] Koller D., Friedman N., Probabilistic Graphical Models: Principles and Techniques, The MIT Press, 2009, 1231 pp.

[15] Marino C., Gini G., Vieno A., Spada M. M., “A comprehensive meta-analysis on problematic Facebook use”, Computers in Human Behavior, 83 (2018), 262–277 | DOI

[16] Marino C., Finos L., Vieno A., Lenzi M., Spada M. M., “Objective Facebook behaviour: Differences between problematic and non-problematic users”, Computers in Human Behavior, 73 (2017), 541–546 | DOI

[17] Neapolitan R. E., Learning Bayesian Networks, Pearson Prentice Hall, 2003, 674 pp.

[18] Orosz G., Toth-Kiraly I., Bothe B., “Four facets of Facebook intensity — The development of the Multidimensional Facebook Intensity Scale”, Personality and Individual Differences, 100 (2016), 95–104 | DOI

[19] Rathore S., Loia V., Park J. H., “SpamSpotter: an efficient spammer detection framework based on intelligent decision support system on facebook”, Applied Soft Computing, 67 (2018), 920–932 | DOI

[20] Schiaffino S., Amandi A., “Intelligent user profiling”, Artificial Intelligence An International Perspective, Lecture Notes in Artificial Intelligence, 5640, ed. M. Bramer, Springer, Berlin, Heidelberg, 2009, 193–216 | DOI

[21] Scutari M., “Learning Bayesian Networks with the bnlearn R Package”, Journal of Statistical Software, 35:3 (2010), 1–22 | DOI

[22] Stoliarova V. F., Tulupyev A. L., “Regression Model for the Problem of Parameter Estimation in the Gamma Poisson Model of Behavior: an Application to the Online Social Media Posting Data”, Conference proceedings of XXI International conference on Soft Computing and Measurements, SCM-2021 (St. Petersburg) (to appear)

[23] Toropova A., Tulupyeva T., “Comparison of Behavior Rate Models Based on Bayesian Belief Network”, Recent Research in Control Engineering and Decision Making. ICIT 2020, Studies in Systems, Decision and Control, 337, eds. Dolinina O. et al., Springer, Cham, 2021, 510–521 | DOI

[24] Tulupyev A., Suvorova A., Sousa J., Zelterman D., “Beta prime regression with application to risky behavior frequency screening”, Statistics in medicine, 32:23 (2013), 4044–4056 | DOI | MR

[25] Wilson R. E., Gosling S. D., Graham L. T., “A review of Facebook research in the social sciences”, Perspectives on psychological science, 7:3 (2012), 203–220 | DOI

[26] Wu T., Wen S., Xiang Y., Zhou W., “Twitter spam detection: Survey of new approaches and comparative study”, Computers Security, 76 (2018), 265–284 | DOI

[27] Abramov M. V., “Automation of social network analysis to assess security against socioengineering attacks”, Automation of management processes, 1:51 (2018), 34–40 (in Russian)

[28] Abramov M. V., Tulupeva T. V., Tulupev A. L., Socioengineering attacks: Social networks and user security assessments, GUAP, SPb., 2018, 266 pp. (in Russian)

[29] Azarov A. A., Tulupeva T. V., Suvorova A. V., Tulupev A. L., Abramov M. V., Yusupov R. M., Socioengineering attacks: problems of analysis, Nauka Publ., SPb., 2016, 349 pp. (in Russian)

[30] VKontakte summed up the results of the first quarter of 2021: the company's revenue grew by 21%, and the audience - by 6%, https://vk.com/press/q1-2021-results (in Russian)

[31] Korepanova A. A., Abramov M. V., Tulupeva T. V., “Identification of user accounts in social networks Vkontakte and Odnoklassniki”, Sbornik nauchnykh trudov semnadtsatoj natsionalnoj konferentsii po iskusstvennomu intellektu s mezhdunarodnym uchastiem, KII-2019 (21–25 oktyabrya 2019 g., g. Ulyanovsk, Rossiya), UlSTU Publ., Ulyanovsk, 2019, 153–163 (in Russian)

[32] Kornienko D. S., Gorbushina E. A., “Features of user profiles, intensity and obsession in using the social network and perfectionist self-presentation”, Bulletin of the Perm State Humanitarian Pedagogical University. Series No. 1. Psychological and pedagogical sciences, 2020, no. 1, 14–25 (in Russian)

[33] Pashchenko A. E., Tulupev A. L., Tulupeva T. V., Krasnoselskikh T. V., Sokolovskij E. V., “Indirect assessment of the probability of HIV infection based on data on recent episodes of risky behavior”, Healthcare of the Russian Federation, 2010, no. 2, 32–35 (in Russian)

[34] Stepanov D. V., Musina V. F., Suvorova A. V., Tulupev A. L., Sirotkin A. V., Tulupeva T. V., “Likelihood function with heterogeneous arguments in the identification of the Poisson model of risky behavior in the case of information deficiency”, Computer Science and automation, 2012, no. 23, 157–184

[35] Suvorova A. V., Models and algorithms for the analysis of ultrashort granular time series based on Bayesian trust networks, PhD Thesis, 2013 (in Russian)

[36] “Bayesian belief networks for risky behavior rate estimates”, Fuzzy Systems and Soft Computing, 9:2 (2014), 115–129 (in Russian)

[37] Tulupev A. L., Nikolenko S. I., Sirotkin A. V., Fundamentals of Bayesian network theory, Handbook, Saint-Petersburg State University Publ., SPb., 2019, 399 pp. (in Russian)

[38] Tulupeva T. V., Pashchenko A. E., Tulupev A. L., Krasnoselskikh T. V., Kazakova O. S., Models of HIV-risky behavior in the context of psychological protection and other adaptive styles, Monograph, 2008, 346 pp. (in Russian)