Jaroslaw Jankowski

Presented research is based on the analysis of emotional states of web users within the social platform with applications towards affective computing.  The presented areas of application in the Internet are the basis for studies with use of affective technology without the involvement of sensor systems, which significantly increase the scope of method application and facilitates its implementation in the Internet systems. They are the potential source of knowledge on users' behaviours, which may be used in various fields of study.

Electronic marketing and advertisement emission and control systems require ade-quate representation of input data, processing algorithms and decision support. Modern market-ing is stimulated by new technological solutions as well as advertising server systems which are responsible for emission planning and control. One of the tasks is selecting and adjusting adver-tising content to suit audience parameters and web users' traversal paths. This article presents the applications of fuzzy methods in behavioral targeting and multi-objective optimization with un-certain parameters in media planning, which helps to build a more realistic representation of au-dience characteristics in a dynamic interactive environment, as well as improving efficiency and resource usage.

The paper proposes an extended approach to modeling online multiplayer systems users’ behavior and segmentation in terms of usage patterns with clusterization used. The solutions presented, are based on analysis of time series in the real and virtual time dimension. The proposed method can be applied in the field of community platforms, virtual worlds and massively multiplayer online systems to capture quantitative characteristics of online platforms usage.

Authors:  Sigi Goode, Greg Shailer, Mark Wilson, Jaroslaw Jankowski

ABSTRACT While profitable business models elude many virtual worlds, sales of virtual products are a potentially lucrative source of revenue. One new addition to this strategy is virtual gifting, whereby users purchase virtual products to give to other users. No prior study has examined this phenomenon. We apply theory from the economics literature to the virtual context, which obviates the need for many of the restrictive assumptions that have underpinned gift theory in that literature. We examine gifting behavior in a virtual world in which users’ social status is reflected in observable social connections (friendships) and interactions (personal messages). We find strong evidence that gifting is associated with future enhancements of the gift giver's social status, consistent with a social status-seeking motivation, thus confirming a theorized behavior that is difficult to study in the real world. Our study also has implications for system proprietors and managers because we show that gift-giving increases system use continuance. We identify various antecedents of gift-giving, which may assist a manager in identifying users who are most inclined to give gifts and enable the manager to signal the social exchange benefits to users as a way of improving their social connections.

Viral campaigns on the Internet may follow variety of models, de-pending on the content, incentives, personal attitudes of sender and recipient to the content and other factors. Due to the fact that the knowledge of the cam-paign specifics is essential for the campaign managers, researchers are constant-ly evaluating models and real-world data. The goal of this article is to present the new knowledge obtained from studying two viral campaigns that took place in a virtual world which followed the branching process. The results show that it is possible to reduce the time needed to estimate the model parameters of the campaign and, moreover, some important aspects of time-generations relation-ship are presented.

Authors propose a conceptual model of participation in viral diffu-sion process composed of four stages: awareness, infection, engagement and ac-tion. To verify the model it has been applied and studied in the virtual social chat environment settings. The study investigates the behavioural paths of ac-tions that reflect the stages of participation in the diffusion and presents shortcuts, that lead to the final action – the attendance in a virtual event. The re-sults show that the participation in each stage of the process increases the prob-ability of reaching the final action. Nevertheless, the majority of users involved in the virtual event did not go through each stage of the process but followed the shortcuts. That suggests that the viral diffusion process is not necessarily a linear sequence of human actions but rather a dynamic system.

Humans utilise multiple communication channels in their social interactions and also information diffusion as well as the spread of influence are practically related with many con-texts. Each such context (channel) may represent a different communication method or a different environment of a given person. This facilitates building multiple social networks, that are not independent. They share the same set of nodes connected with many links grounded on different layers – these networks are called multi-layered or multiplex social networks. The influ-ence process may vary in these kinds of social networks depend-ing on the network model, the level of influence for each layer and other factors such as the overlap of nodes and links across layers. In this paper, the influence processes in multi-layered social networks have been analysed showing that for almost all analysed network models, the success in convincing few more individuals may be crucial for the whole influence process. The results revealed that the process is not linear in terms of relation between the number of initially influenced individuals and the total number of influenced nodes. The linear threshold model has been utilized as a base influence model.

Diffusion of information in social networks takes more and more attention from marketers. New methods and algorithms are constantly developed towards maximizing reach of the campaigns and increasing their effectiveness. One of the important research directions in this area is related to selecting initial nodes of the campaign to result with maximizing its effects represented as total number of infections. To achieve this goal, several strategies were developed and they are based on different network measures and other characteristics of users. The prob-lem is that most of these strategies base on static network proper-ties while typical online networks change over time and are sensi-tive to varying activity of users. In this work a novel strategy is proposed which is based on multiple measures with additional parameters related to nodes availability in time periods prior to the campaign. Presented results show that it is possible to com-pensate users with high network measures by others having high frequency of system usage, which, instead, may be easier or cheaper to acquire.

Diffusion of information and viral content, social
contagion and influence are still topics of broad evaluation. As
theory explaining the role of influentials moves slightly to reduce
their importance in the propagation of viral content, authors of
the following paper have studied the information epidemic in a
social networking platform in order to confirm recent theoretical
findings in this area. While most of related experiments focus on
the level of individuals, the elementary entities of the following
analysis are dyads. The authors study behavioral motifs that are
possible to observe at the dyadic level. The study shows
significant differences between dyads that are more vs less
engaged in the diffusion process. Dyads that fuel the diffusion
proccess are characterized by stronger relationships (higher
activity, more common friends), more active and networked
receiving party (higher centrality measures), and higher
authority centrality of person sending a viral message.

Recommending systems are used in various areas of electronic commerce. Social platforms make it possible to design recommender systems based on social network analysis and connections between users. This paper presents an alternative approach, which uses graph cellular automata. Empirical research was based on datasets from social platforms that confirmed the effectiveness of the proposed solution and is a motivation for extended research in this area.

Modelling the diffusion of information is one of the key areas related to activity within social networks. In this field, there is recent research associated with the use of community detection algorithms and the analysis of how the structure of communities is affecting the spread of information. The purpose of this article is to examine the mecha-nisms of diffusion of viral content with particular emphasis on cross community diffusion.

Web design requires consideration of many factors related to the usability, user experience and business objectives. In many cases conflict of interest can be observed and the desire can arise to improve the results represented by the conversions even at the expense of the user experience. This paper proposes a balanced approach which provides the ability to improve effects with a limited negative impact on users using interactive objects with adjustable levels of persuasion.

Recommending interfaces are usually integrated with marketing processes and are targeted to increasing sales with the use of persuasion and influence methods to motivate users to follow recommendations. In this paper is presented an approach based on decomposition of recommending interface into elements with adjustable influence levels. A fuzzy inference model is proposed to represent the system characteristics with the ability to adjust the parameters of the interface to acquire results and increase customer satisfaction.

A user’s behavior on a website is usually based on a sequence of loaded pages and repetition of content and this is a natural part of communication with a website. Changes of persuasion on a user between repetitions can lead to the increased number of interactions expected by a website operator but can affect user experience as well. In this paper we propose the modeling of the parameters of objects used in repetitions based on the fuzzy inference system towards increased conversions with limited negative impact on a user.

The paper proposes an approach to modelling the behaviour and segmentation of online multiplayer systems’ users, based on frequency and patterns of visits. The results presented are based on the analysis of time series both in real and virtual time, with the objective to quantitatively capture the characteristics of usage of online multiplayer platforms.

The process of applications design focused on the Internet is usually based on continuous optimization and analysis of response from web users. The knowledge acquired from the target environment improves this process and can be used in design space modeling. This paper proposes an approach for fuzzy modeling of interactive objects’ structure to determine the dependencies and provide the additional input towards increasing website effectiveness.

There is observed the evolution of Internet systems that combine features of both technical and economic aspects. In this context, there appears a problem with respect to solutions related to modeling and the management of different aspects of system organization. The article thus employs hybrid system based on fuzzy modeling to identify dependencies between user’s characteristics and digital goods evaluation for the purpose of developing a dynamic pricing system.