People are constantly exposed to environmental stimuli that shape their decisions, mold habits and influence the behavior of whole communities. In social networks, content can spread either as independent cascades or through threshold-based processes—most notably the linear threshold model—which mimic how peers’ actions prompt individuals to adopt new information. To evaluate these diffusion dynamics, we look at three key measures: the ultimate network coverage, the time required to reach that coverage and the total campaign cost. Each of these outcomes depends on choices such as seeding strategy, activation thresholds, the number of initial spreaders and the ranking method used. Facing so many interdependent factors, a multicriteria decision-making approach helps balance resource expenditure against diffusion effectiveness. In this study, we apply such an approach to assess marketing campaigns under the linear threshold model, revealing the trade-offs between coverage, speed and cost.

The use of online video content plays a vital role in marketing strategies and is a significant component of internet usage.The challenge lies in evaluating the impact of video content on user engagement and finding ways to enhance its performance without employing techniques that overwhelm users or prompt ad avoidance behavior.This study investigates the correlation between video dynamics metrics and eye-tracking patterns to determine if user engagement, as indicated by fixations, is influenced by these metrics.The findings demonstrate that dynamic metrics can accurately predict eye-tracking patterns for brief videos and can be applied to measure both inter and intra-scene dynamics in multiscene videos.

Complex networks attract attention in various scientific fields due to their ability to model real world phenomena and potential for problem-solving.It is essential to evaluate these networks to simulate and solve various issues.Evaluating social networks is challenging due to the unequal status of nodes and their unknown impact on everall characteristics.Existing measures of centrality often need to consider the global structure of the network, which requires the involvement of experts and creates space for multi-criteria decision-making methods usage.Unfortunately, more access to established decision-making models is often needed for various reasons.In this article, we propose an innovative approach called Dynamic Stochastic IdenTifiCation Of Models (Dynamic SITCOM), which considers the preferences of characteristic objects and the characteristic values of criteria, enabling the re-identification of multi-criteria decision models.The approach evaluates nodes in Facebook's complex social network, focusing on prediction accuracy using similarity measures and Mean Absolute Error.The study shows that a stable decision model can be created and applied to evaluate nodes in complex networks.

In recent years, complex networks have gained significant attention for their practical potential in data analysis and decision-making.However, assessing node relevance in complex networks poses challenges, including subjectivity and difficulty reproducing criteria relationships.To address these issues, we propose MLP-COMET.This novel approach combines the Multi-Layer Perceptron (MLP) with the Characteristic Objects Method (COMET) in Multi-Criteria Decision Analysis (MCDA).MLP-COMET aims to re-identify decision models using MLP to evaluate characteristic objects.We evaluate the approach to assessing the complex network and demonstrate its effectiveness in evaluating without heavy reliance on domain experts.The MLP-COMET performance is evaluated through ranking comparisons, showing a strong correlation with reference expert rankings.We also analyze the impact of training sample size and number of characteristic objects on ranking similarity, observing high stability and similarity using the rw metric.MLP-COMET offers an effective and reliable tool for evaluating complex networks and facilitating decision-making processes.

Habituation is a common phenomenon in learning, where the response to a repeated stimulus decreases over time. In Multi-Armed Bandits (MAB) algorithms used for visual content delivery optimization, habituation can lead to suboptimal performance. For example, if an agent becomes habituated to a suboptimal arm, it may continue to choose that arm even if better options are available. Habituation can be modeled as a form of ”forgetting”, where the agent gradually loses confidence in its estimates of the reward probabilities for each arm as time passes. Proposed approach allows updating estimates according to habituation model, while also exploiting the arm with the highest estimated reward probability. The results showed that it is a very good solution to introduce breaks in the multi-armed bandit habit model, which was implemented and tested in our study.

Video content on the internet commands a substantial portion of online activities and holds immense value in driving effective marketing campaigns. The question is, how can we measure the potential of video content to capture user attention and how to improve video effectiveness without techniques that increase cognitive load and result in avoidance and skipping of advertisements. This study investigated how video dynamics represented by dedicated metrics is related to eye-tracking patterns and whether video dynamics can be a predictor of user engagement represented by the number of fixations and the duration of gaze on video content. The results showed that selected metrics can serve as predictors of eye movement patterns and that video dynamics have a real impact on user engagement with the viewed video content.

Growing awareness of the impact of business activity on the environment increases the pressure for governing bodies to address this issue. One possibility is to encourage or force the market into green behaviours. However, it is often hard to predict how different actions affect the market. Thus, to help with that, in this paper, we have proposed the green behaviour spreading model in the bank-company multilayer network. This model allows assessing how various elements like the duration of external influence, targeted market segment, or intensity of action affect the outcome regarding market greening level. The model evaluation results indicate that governing bodies, depending on the market "openness" to green activities, can adjust the duration and intensity of the proposed action. The strength of the impact can be changed by the public or private authority with the use of obligatory or voluntary rules and the proportion of influenced banks. This research may be helpful in the process of creating the optimal setups and increasing the performance of greening policies implementation.

Abstract The paper introduces a modified version of a genetic algorithm with aggressive mutation (GAAM) called fGAAM (fast GAAM) that significantly decreases the time needed to find feature subsets of a satisfactory classification accuracy. To demonstrate the time gains provided by fGAAM both algorithms were tested on eight datasets containing different number of features, classes, and examples. The fGAAM was also compared with four reference methods: the Holland GA with and without penalty term, Culling GA, and NSGA II. Results: (i) The fGAAM processing time was about 35% shorter than that of the original GAAM. (ii) The fGAAM was also 20 times quicker than two Holland GAs and 50 times quicker than NSGA II. (iii) For datasets of different number of features, classes, and examples, another number of individuals, stored for further processing, provided the highest acceleration. On average, the best results were obtained when individuals from the last 10 populations were stored (time acceleration: 36.39%) or when the number of individuals to be stored was calculated by the algorithm itself (time acceleration: 35.74%). (iv) The fGAAM was able to process all datasets used in the study, even those that, because of their high number of features, could not be processed by the two Holland GAs and NSGA II.

Designing user interfaces requires the efficient management of elements that interact with the user and attract their attention. In the development of technologies supporting the development of chatbots, few studies have focused on the visual aspects of the interface. Changes in the chatbot area can be of different natures, such as increasing or decreasing the number of messages. Due to habituation (change blindness), messages delivered by chatbots may not be noticed. The main goal of the present study was to examine the impact of changes within the chatbot on user behaviour and the possibility of directing user attention to the chatbot area. This study showed that the intensity and types of changes within the chatbot can improve performance and successful message delivery to users.

Design of applications requires proper management of content, interaction elements and space. In web systems flow of interactions is often based on attention catching components in a form of elements of navigation or advertising content. Distance from central part of interface is affecting user behavior, what can be overcome by scaling size of the objects within the interface according to Fitts’s law. Here we examine the effects of flickering elements with different frequency, direction and distance from central elements of webpage on user attention and habituation reduction. The aim of the study was to examine how to overcome users’ resistance to stimuli based on objects flickering with different frequencies located in different directions and distances. We wanted to check if the higher flicker frequency can compensate the larger distance and increase and user focus depending on whether the element is located nearest or farthest, similarly like objects sizes for Fitts’s law. Results showed that flicker increases the attention to objects with higher distance but has no effect on nearest objects. I was possible to improve total time attracted by distance objects by twenty percent, however the higher performance was observed to nearest objects, no matter what frequency was used for them.

The design of recommending systems is mainly related to algorithms targeting customer needs, products, and service selection. However, even the most effective algorithms will not increase the performance of an e-commerce platform if the recommendation interface is not noticed by the user. Recommendations, like all other visual stimuli, can be subconsciously eliminated by users as a result of habituation identified for online environment as a banner blindness. This article presents the results of an experiment, in which the influence of the intensity of graphic elements within the interface on user attention was examined. The study explores the visual space and survival of graphic objects, analysed with the use of survival analysis instead of typical perceptual studies. Results show that an increase in visual intensity does not always lead to an increase in user attention, and survival analysis makes it possible to identify the differences between design variants and between users targeted with the same stimuli.

Social networks create routes for information transmission with the use of social influence mechanisms. While one of goals can be to increase the dynamics of processes within the networks, from the perspective of the spread of harmful content or misleading information, efforts should be focused on limiting the spread. One possible strategy is the initialisation of competing processes as a reaction to negative spread. Depending on the parameters of the limiting process and the network topologies, actions can succeed or fail. In this paper, we focused on a linear threshold competing model and analysed the effects of the limiting processes within scale-free networks with different characteristics, as well as the process parameters and timing. The results showed how the parameters of the limiting process should be adjusted to achieve substantial coverage within the network depending on the network characteristics and the intervals between the positive and negative processes.

In recent years, bustling online communities have focused a lot of attention on research dealing with information spreading. Through acquired knowledge about the characteristics of information spreading processes, we are able to influence their dynamics via the enhancement of propagation properties or by changing them to decrease their spread within a network. One of approaches is adding or removing connections within a network. While optimal linking within complex networks requires extensive computational resources, in this investigation, we focus on the optimization of the topology of small graphs within larger network structures. The study shows how the enhancement of propagation properties within small networks is preserved in bigger networks based on connected smaller graphs. We compare the results from combined small graphs with added links providing optimal spread and networks with additional random linking. The results show that improvements in linking within small sub-graphs with optimal linking improves the diffusional properties of the whole network.

Spreading of information within social media and techniques related to viral marketing take more and more attention from companies focused on targeting audiences within electronic systems.Recent years resulted in extensive research centered around spreading models, selection of initial nodes within networks and identification of campaign characteristics affecting the assumed goals.While social networks are usually based on complex structures and high number of users, the ability to perform detailed analysis of mechanics behind the spreading processes is very limited.The presented study shows an approach for selection of campaign parameters with the use of network samples and theoretical models.Instead of processing simulations on large network, smaller samples and theoretical networks are used.Results showed that knowledge derived from relatively smaller structures is helpful for initialization of spreading processes within the target network of larger size.Apart from agent based modeling, multi-criteria methods were used for evaluation of results from the perspective of costs and performance.

The growing intensity of visual marketing content may result in limited user attention and dropping performance. The main reason is a habituation effect observed for repeated stimuli causing the banner blindness phenomenon. To overcome that marketers resort to various techniques based on visual effects, such as animations or vividness, with possible side effects like negative brand perception. The same can be observed for recommending systems and the presented study investigates varying visual intensity in a recommending interface with the use of eye tracking. Multi-criteria analysis is performed to evaluate results from the perspective of user experience, attention allocated to visual objects and their intensity with the main goal to recommend the most viable solutions.

Information spreading processes are main drivers of viral campaigns. They are usually conducted within large scale social networks. Parametrisation of online campaigns is usually related to allocation of budgets, number of seeds and strategies of their selection. It is hard to predict campaign effects. Proposed in this paper approach uses network samples to select appropriate strategy for use within complete network. Results showed how scaling of samples is affecting approximation quality. Multi-criteria analysis of performance allows for strategy selection according to preferences and goals.

This paper provides a comparative study of ICT (information and communication technologies) and SIS (sustainable information society) measurement in Polish households using a MCDA-based approach in aim to advance the information society research and practice by examining and understanding the ICT adoption in households for improving SIS. This study employs a quantitative approach to measure the ICT adoption in Polish households. Survey questionnaires were used and data collected from 679 households were analyzed to identify the levels of ICT adoption. Multi-criteria decision analysis (MCDA) Analytic Hierarchy Process (AHP) method was used for evaluation of the collected data. This study advances the information society research and practice by developing an approach to measure the ICT adoption.

Research related to information diffusion within complex networks tends to focus on the effective ways to maximize its reach and dynamics. Most of the strategies are based on seeding nodes according to their potential role for social influence. The presented study shows how the seeding can be supported by changes in the target users' motivation to spread the content, thus modifying the propagation probabilities. The allocation of propagation probabilities to nodes takes the form of a spraying process following a given probability distribution, projected from the nodes' rankings. The results showed how different spraying strategies affect the results when compared to the commonly used uniform distribution. Apart from the performance analysis, the empirical study shows to which extent the seeding of nodes with high centrality measures can be compensated by seeding the nodes which are ranked lower, but are having higher motivation and propagation probabilities.

The process of sustainable supplier selection is crucial to a company's business continuity.Distortions in poorly chosen suppliers can lead to an impediment or even complete downtime of the company's operations.The paper proposes a new unique approach in which classical MCDA paradigm is extended with aspects of temporal evaluation and various temporal aggregation strategies are provided.The partial MCDA evaluations are performed with three MCDA methods -AHP, TOPSIS and COMET -to allow for hierarchical structuring of the decision problem, creation of a reference model and avoiding rank reversal.The proposed approach is verified on a case study with an actual company and its supplier selection from a group of 30 potential suppliers.

Initialization of information spreading processes within complex networks is usually based on selection of initial nodes as a seed set. While most methods are choosing seeds in a single stage, another possible option is a partial budget usage in the first stage and spending the remaining budget while the process develops. In this paper we analyze how the ratio of seeds used in the primary and supporting stages affects the performance in terms of number of activated nodes and its duration. We have used real networks and agent based simulations with various parameters including different propagation probabilities, nodes selection strategies and number of seeds. Results show that coverage can be improved by minimizing the number of seeds used in primary seeding and increasing it in supporting seeding. Delaying the use of supporting seeds better supports natural diffusion processes and avoids selection of seeds with high potential to be activated anyway.

Due to high availability of e-commerce websites providing similar services and products, the website usability becomes one of the most critical factors affecting online businesses' success.Therefore, website quality and user experience evaluation is an important research task.There are multiple methodologies for performing the evaluation.The proposed in our earlier studies PEQUAL methodology extends the classical eQual method by taking into account different aspects of preference modeling and aggregation derived from Multi-Criteria Decision Analysis (MCDA).This paper extends the PEQUAL methodology further by incorporating eye tracking based measurement and analysis into the criteria set.The results of the conducted empirical verification of proposed approach are presented.

There are billions of images available on the Internet. With such a rich collection available and such a great diversity of users and their various needs, content-based image retrieval becomes a problem. Luckily, this is partially solved by publicly available image search engines; however, a question what their linguistic quality is arises. An approach to evaluate linguistic query based quality of image search engines is proposed in this paper and a sample test set and queries are presented.

DOAJ is a unique and extensive index of diverse open access journals from around the world, driven by a growing community, committed to ensuring quality content is freely available online for everyone.

The design of web applications includes the use of components that attempt to increase influence on target audience to achieve expected results in the form of interactions. In this area, conflicts between user experience and business goals are observed, especially when primary tasks within a website are negatively affected by intrusive marketing messages. The proposed in this paper approach based on perceptual experiments is related to modeling the structure of interactive objects and building an inference model, with the main purpose being to determine the response from web users using different levels of influence. The obtained results, compared with online responses from an actual campaign, provide the possibility to adopt compromise solutions through designing Internet applications with an expected outcome and minimizing negative responses without interfering with user experience.

Studying information diffusion and the spread of goods in the real world and in many digital services can be extremely difficult since information about the information flows is challenging to accurately track. How information spreads has commonly been analysed from the perspective of homophily, social influence, and initial seed selection. However, in virtual worlds and virtual economies, the movements of information and goods can be precisely tracked. Therefore, these environments create laboratories for the accurate study of information diffusion characteristics that have been difficult to study in prior research. In this paper, we study how content visibility as well as sender and receiver characteristics, the relationship between them, and the types of multilayer social network layers affect content absorption and diffusion in virtual world. The results show that prior visibility of distributed content is the strongest predictor of content adoption and its further spread across networks. Among other analysed factors, the mechanics of diffusion, content quality, and content adoption by users’ neighbours on the social activity layer had very strong influences on the adoption of new content.

Multi-criteria decision analysis (MCDA) methods have become increasingly popular in decision-making.Numerous methods in this field were developed to solve realworld decision problems including various engineering and scientific areas.Unfortunately, the proper use of each method is difficult due to the dispersion of the domain knowledge and lack of knowledge databases in this area.The paper presents research focused on knowledge management aspects in MCDA domain.In order to achieve a high level of practicality on different levels of decision making, the ontology as a form of conceptualization is implemented.

Many methods can be used for the evaluation of website quality.While they can be used for different purposes and require different assessment approaches it is not easy to select proper method adequate to the needs.Presented research is focused on building a repository of knowledge about the methods for the assessing the quality of website.The repository in the form of ontologies covers various methods of quality assessment and makes possible their proper selection.Proposed approach was verified with main methods and the resulting ontology can act as a repository of domain knowledge.

This article presents the results from research in which 3 different remote control interfaces were compared to assess the impact of interface structure on the performance of the operator for remotely controlled mobile inspection robots. The primary control interface of a mobile robot consists of a head-mounted display, data gloves for gripper control, joystick for movement control of the robot platform, and a motion tracking system for measuring head orientation and hand position. In order to compare different control interfaces, an additional system, based on a Liquid Crystal Display monitor and joystick, was prepared. Results of this study show that the use of virtual reality techniques in the interfaces of mobile inspection robots increases operator productivity, the level of spatial presence, and distance evaluation while facilitating the execution of tasks, as well as improving and speeding up their execution and reducing the operator’s time needed to adapt to the control interface. The latter is achieved with the increased level of intuitive control while ensuring comfort.

Methods of social network analysis are evolving into the practice of analyzing multi-layer networks, which represent different dimensions of activity and relationships. This also applies to methods oriented to detect communities in order to analyze the relationship between groups on different layers. In this context, the purpose of this article is to answer the question of how much the communities in cyberspace overlap when studying a variety of forms of interactions. The authors analyzed the structure of user groups formed on different layers of a social network created among users in a virtual world. By extracting groups and analyzing their structure and relationship with one another, some interesting properties are shown, especially in the area of the groups' overlapping. By performing this research, the authors were able to discover how similar the worlds we create can be when we are using different forms of communication in the same virtual environment.

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 problem is that most of these strategies base on static network properties while typical online networks change over time and are sensitive 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 compensate 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 process 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.