Reinforcement of marketing content spreading processes in social media (in Polish: Wspomaganie procesów rozprzestrzeniania treści marketingowych w mediach społecznościowych)


Polish National Science Centre, Grant No. 2016/21/B/HS4/01562


Karczmarczyk, A., Jankowski, J., Wątróbski, J., Multi-criteria decision support for planning and evaluation of performance of viral marketing campaigns in social networks, PloS one 13 (12), e0209372, 2018

Jankowski, J., Waniek, M., Alshamsi, A., Bródka, P., Michalski, R., Strategic distribution of seeds to support diffusion in complex networks, PloS one 13 (10), e0205130, 2018

Karczmarczyk, A., Bortko, K., Bartków, P., Pazura, P., Jankowski, J., Influencing Information Spreading Processes in Complex Networks with Probability Spraying, 2018 IEEE/ACM International Conference on Advances in Social Networks, 2018

Jankowski, J., Zioło, M., Karczmarczyk, A., Wątróbski, J., Towards sustainability in viral marketing with user engaging supporting campaigns, Sustainability 10 (1), 15, 2017

Jankowski, J., Michalski, R., Bródka, P., A multilayer network dataset of interaction and influence spreading in a virtual world, Scientific data 4, 170144, 2017

Jankowski, J., Bródka, P., Michalski, R., Kazienko, P., Seeds buffering for information spreading processes, International Conference on Social Informatics, 628-641, 2017

Jankowski, J., Michalski, R., Bródka, P., Karczmarczyk, A., Increasing Coverage of Information Diffusion Processes by Reducing the Number of Initial Seeds, Proceedings of the 2017 IEEE/ACM International Conference on Advances, 2017

Jankowski, J., Michalski, R., Increasing coverage of information spreading in social networks with supporting seeding, International Conference on Data Mining and Big Data, 209-218, 2017

Jankowski, J., Bródka, P., Kazienko, P., Szymanski, B.K., Michalski, R., T Kajdanowicz, Balancing speed and coverage by sequential seeding in complex networks, Scientific reports 7 (1), 891, 2017

Jankowski, J., Mixture seeding for sustainable information spreading in complex networks, Asian Conference on Intelligent Information and Database Systems, 191-201, 2017

Jankowski, J., Dynamic rankings for seed selection in complex networks: Balancing costs and coverage, Entropy 19 (4), 170


Network structures and information spreading processes are observed in many aspects of the surrounding world. For example; in the biological systems, signals are transmitted in networks at molecular level [Bray, 2003], within genetic interaction networks [Tong et al., 2004] or neural connections [Bullmore & Sporns, 2009]. Propagation of viruses among organisms is observed when infectious diseases are spreading, and they take the form of epidemics after reaching an epidemic threshold [Allen, 1994]. From the social perspective, information is transmitted during communication between individuals connected within social networks, and is resulting in knowledge diffusion [Rozewski & Jankowski, 2015] or spreading the rumors [Nekovee et al., 2007]. Apart from being natural systems, networks are direct effects of human activity in a form of transportation connections [Bell & Lida, 1997], computer networks [Broido, 2001], telecommunication systems [Barnett, 2001] or online social networking platforms [Ellision, 2007].

Network structures create routes and physical or logical infrastructures for spreading marketing content, information, products in intentional and unintentional ways. The power of spreading mechanisms especially in social media is used for propagation information about products [Schulze, 2014], diffusion of innovation [Peres, 2010], as an important mechanism for political marketing campaigns [Garcia et al., 2012] and takes form of viral marketing [Watts et al. 2007].

Analysis of the spreading processes was not easy a few decades ago because of the inability to collect detailed data from marketing campaigns. Nowadays, electronic systems and social media deliver detailed information about processes and their performance. Research in this field is concentrated on the analysis of real systems [Zaman, 2010], identification of factors affecting content spreading processes [Ho & Dempsey, 2010], mathematical models describing and predicting processes [Khelil et al., 2002], simulations with the agent based environments [Hui et al. 2010] and selection of initial nodes within networks for starting diffusion and marketing campaigns [Hinz et al., 2011]. Selection of initial nodes is analyzed from the perspective of marketing and from the methodological point of view is backed by social sciences [Kimura et al. 2007] as well as by combinatorial optimization [Ackerman et al., 2010][Ben-Zwi et al. 2011][Chiang et al., 2013] and theoretical methods from physics [Morone & Makse, 2015] for quantitative approaches. Presented project has the potential for knowledge transfer from the computer science and computational social science to marketing science towards better understand processes of marketing content spreading. In research will be used background from computer science for creation of new approaches for supporting viral marketing processes.

Existing problems. Typically, the modeling of spreading marketing content within social media is based on the assumption that once a process is started through initial seeds selection, it continues without any additional support [Hinz et al., 2011]. Decisions related to planning the process and selection of initial candidates are taken before the process starts and are based on the incomplete knowledge and theoretical models [Liu-Thompkins, 2012]. At the beginning of the process, only predictions are available about future process characteristics. Running processes deliver more knowledge about dynamics, characteristics of activated and not activated nodes within the network. As a result, additional decisions influencing the process can be more accurate than those taken at the beginning. However, in most solutions, only initially selected seeds are the main catalyst of the process and they launch information cascades within the network. After the start, the process is based only on natural propagation mechanisms. A typical process lasts until there are no more nodes activated.

The problem appears when initially selected seeds do not deliver the estimated number of activations and the natural diffusion processes in a form of viral marketing were not launched with enough intensity. In such cases, total coverage and a number of activations of nodes in the network can be much lower than expected. Another problem is related to the selection of too few initial seeds or their wrong allocation within the social network structures. It can result low dynamics of marketing process. Minimizing the initial seed set was the subject of earlier research; however, it assumes stable conditions within the network and unchanging process parameters. Changing process parameters, like propagation probabilities, affect the dynamics of the process and final results can be smaller than was initially planned.

Most of earlier models assume the same propagation probabilities for all nodes and during the entire process; however, in real systems, this kind of assumption is rarely met.

For dynamic networks with temporal characteristics, conditions after launching the marketing content spread, can be different than expected. For example, the availability of nodes (potential customers) within the social network can be low but it is crucial for the spreading processes and final coverage. Low activity of network nodes with not enough engagement in marketing campaign, negatively influence the whole process. Varying over the time conditions within a social network can be observed and its structure can be changing. Edges between network nodes based in example on communication, phone calls can appear and disappear and it affects the dynamics of the process as well.

Apart from process characteristics, the performance is related to specific social network structures. For example, with many groups of customers which are not communicated and segments which are difficult to reach, the process will not achieve high dynamics. Other problems are related to reaching individual customers within networks with specific attributes. Typical seed selection methods use centrality measures, but they don’t represent structural characteristics of specific regions within the network. As a result, achieving less communicated segments of the network can be difficult and target groups of customers will be not contacted.

The solutions proposed in this project, planned research and experiments will increase knowledge about the processes of spreading marketing content in social networks. The introduced analytical methods will allow analysis of phenomena occurring in them, as well as the selection of appropriate methods of supporting marketing processes. The project fills important gaps and introduces its own methods, which complement the current state of research.


Anderson, R. M., May, R. M., & Anderson, B. (1992). Infectious diseases of humans: dynamics and control (Vol. 28). Oxford: Oxford university press.

Bakshy, E., Karrer, B., & Adamic, L. A. (2009, July). Social influence and the diffusion of user-created content. In Proceedings of the 10th ACM conference on Electronic commerce (pp. 325-334). ACM.

Bampo, M., Ewing, M. T., Mather, D. R., Stewart, D., & Wallace, M. (2008). The effects of the social structure of digital networks on viral marketing performance. Information systems research, 19(3), 273- 290.

Becker, N. G. (1989). Analysis of infectious disease data (Vol. 33). CRC Press.

Berger, J., & Milkman, K. L. (2012). What makes online content viral?. Journal of marketing research, 49(2), 192-205.

Camarero, C., & San José, R. (2011). Social and attitudinal determinants of viral marketing dynamics. Computers in Human Behavior, 27(6), 2292-2300.

Chen, W., Wang, Y., & Yang, S. (2009, June). Efficient influence maximization in social networks. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 199-208). ACM.

Dobele, A., Lindgreen, A., Beverland, M., Vanhamme, J., & van Wijk, R. (2007). Why pass on viral messages? Because they connect emotionally. Business Horizons, 50(4), 291-304.

Even-Dar, E., & Shapira, A. (2007). A note on maximizing the spread of influence in social networks. In Internet and Network Economics (pp. 281-286). Springer Berlin Heidelberg.

Frauenthal, J. C. (2012). Mathematical modeling in epidemiology. Springer Science & Business Media.

Fulford, G., Forrester, P., & Jones, A. (1997). Modelling with differential and difference equations (Vol. Cambridge University Press.

Ho, J. Y., & Dempsey, M. (2010). Viral marketing: Motivations to forward online content. Journal of Business Research, 63(9), 1000-1006.

Huffaker, D. A., Teng, C. Y., Simmons, M. P., Gong, L., & Adamic, L. A. (2011, October). Group membership and diffusion in virtual worlds. In Privacy, Security, Risk and Trust (PASSAT) and 2011 IEEE Third Inernational Conference on Social Computing (SocialCom), 2011 IEEE Third International Conference on (pp. 331-338). IEEE.

Jankowski, J., Michalski, R., & Kazienko, P. (2013, August). Compensatory seeding in networks with varying avaliability of nodes. In Advances in Social Networks Analysis and Mining (ASONAM), 2013 IEEE/ACM International Conference on (pp. 1242-1249). IEEE.

Jankowski, J., Michalski, R., Bródka, P., Kazienko, P., & Utz, S. (2015). Knowledge acquisition from social platforms based on network distributions fitting. Computers in Human Behavior, 51, 685-693.

Leskovec, J., Adamic, L. A., & Huberman, B. A. (2007). The dynamics of viral marketing. ACM Transactions on the Web (TWEB), 1(1), 5.

Li, P., Xing, K., Wang, D., Zhang, X., & Wang, H. (2013). Information diffusion in facebook-like social networks under information overload. International Journal of Modern Physics C, 24(07), 1350047.

Michalski, R., Kajdanowicz, T., Bródka, P., & Kazienko, P. (2014). Seed selection for spread of influence in social networks: Temporal vs. static approach. New Generation Computing, 32(3-4), 213- 235.

Mochalova, A., & Nanopoulos, A. (2014). A targeted approach to viral marketing. Electronic Commerce Research and Applications, 13(4), 283-294.

Perez, L., & Dragicevic, S. (2009). An agent-based approach for modeling dynamics of contagious disease spread. International journal of health geographics, 8(1), 1.

Salehi, M., Sharma, R., Marzolla, M., Magnani, M., Siyari, P., & Montesi, D. (2015). Spreading processes in multilayer networks. Network Science and Engineering, IEEE Transactions on, 2(2), 65-83.

Seeman, L., & Singer, Y. (2013, October). Adaptive seeding in social networks. In Foundations of Computer Science (FOCS), 2013 IEEE 54th Annual Symposium on (pp. 459-468). IEEE.

Stewart, D.B., Ewing, M.T. & Mather, D.R. (2009) A Conceptual Framework for Viral Marketing, ANZMAC 2009.

Stieglitz, S., & Dang-Xuan, L. (2013). Emotions and information diffusion in social media—sentiment of microblogs and sharing behavior. Journal of Management Information Systems, 29(4), 217-248.

25. Stonedahl, F., Rand, W., & Wilensky, U. (2010, July). Evolving viral marketing strategies. In Proceedings of the 12th annual conference on Genetic and evolutionary computation (pp. 1195-1202). ACM.

Taxidou, I., & Fischer, P. M. (2014). Online analysis of information diffusion in twitter. In Proceedings of the companion publication of the 23rd international conference on World wide web companion (pp. 1313-1318). International World Wide Web Conferences Steering Committee.

Touibia, O., Stephen, A. T., & Freud, A. (2011). Viral marketing: A large-scale field experiment. Economics, Management and Financial Markets, 6(3), 43.

Wang, C., Chen, W., & Wang, Y. (2012). Scalable influence maximization for independent cascade model in large-scale social networks. Data Mining and Knowledge Discovery, 25(3), 545-576.

Wang, T. S. (2008). An Agent-Based Model of Viral Marketing: Comparing online-based viral and traditional marketing in a closed system for fashion trends in a competitive setting.

Bray, D. (2003). Molecular networks: the top-down view. Science, 301(5641), 1864.

Tong, A. H. Y., Lesage, G., Bader, G. D., Ding, H., Xu, H., Xin, X., ... & Chen, Y. (2004). Global mapping of the yeast genetic interaction network. science, 303(5659), 808-813.

Bullmore, E., & Sporns, O. (2009). Complex brain networks: graph theoretical analysis of structural and functional systems. Nature Reviews Neuroscience, 10(3), 186-198.

Allen, L. J. (1994). Some discrete-time SI, SIR, and SIS epidemic models. Mathematical biosciences, 124(1), 83-105.

Rozewski, P., & Jankowski, J. (2015). Model of Multilayer Knowledge Diffusion for Competence Development in an Organization. Mathematical Problems in Engineering, 501, 529256.

Nekovee, M., Moreno, Y., Bianconi, G., & Marsili, M. (2007). Theory of rumour spreading in complex social networks. Physica A: Statistical Mechanics and its Applications, 374(1), 457-470.

Bell, M. G., & Iida, Y. (1997). Transportation network analysis.

Ellison, N. B. (2007). Social network sites: Definition, history, and scholarship. Journal of Computer‐ Mediated Communication, 13(1), 210-230.

Broido, A. (2001, July). Internet topology: Connectivity of IP graphs. In ITCom 2001: International Symposium on the Convergence of IT and Communications (pp. 172-187). International Society for Optics and Photonics.

Barnett, G. A. (2001). A longitudinal analysis of the international telecommunication network, 1978- 1996. American Behavioral Scientist, 44(10), 1638-1655.

Schulze, C., Schöler, L., & Skiera, B. (2014). Not all fun and games: Viral marketing for utilitarian products. Journal of Marketing, 78(1), 1-19.

Peres, R., Muller, E., & Mahajan, V. (2010). Innovation diffusion and new product growth models: A critical review and research directions. International Journal of Research in Marketing, 27(2), 91-106.

Garcia, D., Mendez, F., Serdült, U., & Schweitzer, F. (2012, November). Political polarization and popularity in online participatory media: an integrated approach. In Proceedings of the first edition workshop on Politics, elections and data (pp. 3-10). ACM.

Zaman, T. R., Herbrich, R., Van Gael, J., & Stern, D. (2010, December). Predicting information spreading in twitter. In Workshop on computational social science and the wisdom of crowds, nips (Vol. 104, No. 45, pp. 17599-601).

Ho, J. Y., & Dempsey, M. (2010). Viral marketing: Motivations to forward online content. Journal of Business Research, 63(9), 1000-1006.

Khelil, A., Becker, C., Tian, J., & Rothermel, K. (2002, September). An epidemic model for information diffusion in MANETs. In Proceedings of the 5th ACM international workshop on Modeling analysis and simulation of wireless and mobile systems (pp. 54-60). ACM.

Hui, C., Goldberg, M., Magdon-Ismail, M., & Wallace, W. A. (2010). Simulating the diffusion of information: An agent-based modeling approach. International Journal of Agent Technologies and Systems (IJATS), 2(3), 31-46.

Hinz, O., Skiera, B., Barrot, C., & Becker, J. U. (2011). Seeding strategies for viral marketing: An empirical comparison. Journal of Marketing, 75(6), 55-71.

Morone, F., & Makse, H. A. (2015). Influence maximization in complex networks through optimal percolation. Nature.

Ackerman, E., Ben-Zwi, O., & Wolfovitz, G. (2010). Combinatorial model and bounds for target set selection. Theoretical Computer Science, 411(44), 4017-4022.

Ben-Zwi, O., Hermelin, D., Lokshtanov, D., & Newman, I. (2011). Treewidth governs the complexity of target set selection. Discrete Optimization, 8(1), 87-96.

Chiang, C. Y., Huang, L. H., Li, B. J., Wu, J., & Yeh, H. G. (2013). Some results on the target set selection problem. Journal of Combinatorial Optimization, 25(4), 702-715.

Kimura, M., Saito, K., & Nakano, R. (2007, July). Extracting influential nodes for information diffusion on a social network. In AAAI (Vol. 7, pp. 1371-1376).

Stonedahl, F., Rand, W., & Wilensky, U. (2010, July). Evolving viral marketing strategies. In Proceedings of the 12th annual conference on Genetic and evolutionary computation (pp. 1195-1202). ACM.

Liu-Thompkins, Y. (2012). Seeding viral content. Journal of Advertising Research, 52(4), 465-478.

Domingos, P., & Richardson, M. (2001, August). Mining the network value of customers. In Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 57-66). ACM.

Kiss, C. & Bichler, M. Identification of influencers - measuring influence in customer networks. Decis. Support Syst. 46, 233–253 (2008).

Nejad, M. G., Amini, M. & Babakus, E. Success factors in product seeding: The role of homophily. Journal of Retailing 91, 68 – 88 (2015).

Long, C., & Wong, R. C. W. (2011, December). Minimizing seed set for viral marketing. In Data Mining (ICDM), 2011 IEEE 11th International Conference on (pp. 427-436). IEEE.

Lehmann, D. & Esteban-Bravo, M. When giving some away makes sense to jump-start the diffusion process. Marketing Letters 17, 243–254 (2006).

Libai, B., Muller, E. & Peres, R. The role of seeding in multi-market entry. International Journal of Research in Marketing 22, 375 – 393 (2005).

Ackerman, E., Ben-Zwi, O. &Wolfovitz, G. Combinatorial model and bounds for target set selection. Theoretical Computer Science 411, 4017 – 4022 (2010).

Ben-Zwi, O., Hermelin, D., Lokshtanov, D. & Newman, I. Treewidth governs the complexity of target set selection. Discret. Optim. 8, 87–96 (2011).

Chiang, C.-Y., Huang, L.-H., Li, B.-J., Wu, J. & Yeh, H.-G. Some results on the target set selection problem. Journal of Combinatorial Optimization 25, 702–715 (2013).

Galstyan, A., Musoyan, V. & Cohen, P. Maximizing influence propagation in networks with community structure. Phys. Rev. E 79, 056102 (2009).

He, J.-L., Fu, Y. & Chen, D.-B. A novel top-k strategy for influence maximization in complex networks with community structure. PloS one 10, e0145283 (2015).

Morone, F. & Makse, H. A. Influence maximization in complex networks through optimal percolation. Nature 524, 65–68 (2015).

Michalski, R., Kajdanowicz, T., Br´odka, P. & Kazienko, P. Seed selection for spread of influence in social networks: Temporal vs. static approach. New Generation Computing 32, 213–235 (2014).

Jankowski, J., Michalski, R. & Kazienko, P. Compensatory seeding in networks with varying availability of nodes. In Advances in Social Networks Analysis and Mining (ASONAM), 2013 IEEE/ACM International Conference on, 1242–1249 (IEEE, 2013).

Michalski, R., Kazienko, P. & Jankowski, J. Convince a dozen more and succeed–the influence in multilayered social networks. In Signal-Image Technology & Internet-Based Systems (SITIS), 2013 International Conference on, 499–505 (IEEE, 2013).

Seeman, L. & Singer, Y. Adaptive seeding in social networks. In Foundations of Computer Science (FOCS), 2013 IEEE 54th Annual Symposium on, 459–468 (IEEE, 2013).

Horel, T. & Singer, Y. Scalable methods for adaptively seeding a social network. In Proceedings of the 24th International Conference on World Wide Web, 441–451 (International World Wide Web Conferences Steering Committee, 2015).

Sela, A., Ben-Gal, I., Pentland, A. & Shmueli, E. Improving information spread through a scheduled seeding approach. In The international conference on Advances in Social Network Analysis and Mining 2015 (2015).

Bulut, E., Wang, Z. & Szymanski, B. Cost-effective multiperiod spraying for routing in delay-tolerant networks. Networking, IEEE/ACM Transactions on 18, 1530–1543 (2010).

Liu, Y. Y., Slotine, J. J., & Barabási, A. L. (2011). Controllability of complex networks. Nature, 473(7346), 167-173.

Sorrentino, F., di Bernardo, M., Garofalo, F., & Chen, G. (2007). Controllability of complex networks via pinning. Physical Review E, 75(4), 046103.

Cheng, D., & Qi, H. (2009). Controllability and observability of Boolean control networks. Automatica, 45(7), 1659-1667.

Jankowski J., Kazienko P., Bródka P., Szymański B., Michalski R., Kajdanowicz T. Sequential Seeding in Complex Networks: Trading Speed for Coverage, final preparation to be submitted for PNAS in 07.2016

Jankowski J., Kajdanowicz T., Bródka P., Michalski R. Kazienko P.. Sequential Seeding in Social Networks, NetSci Conference 2016, Wrocław, Poster Session

Watts, D. J., Peretti, J., & Frumin, M. (2007). Viral marketing for the real world. Harvard Business School Pub.