Paweł Ziemba

Fuzzy multi-objective modeling of effectiveness and user experience in online advertising

We analyze the impact of online advertisements on effectiveness and user experience.We combine results from online campaign and data from perceptual experiment.We use fuzzy multi-objective modeling for searching for trade-off solutions.We propose balanced approach to advertising resources exploitation. The focus placed on maximizing user engagement in online advertising negatively affects the user experience because of advertising clutter and increasing intrusiveness. An intelligent decision support system providing balance between user experience and profits from online advertising based on the fuzzy multi-objective optimization model is presented in this paper. The generalized mathematical model uses uncertain parameters for content descriptors that are difficult to be precisely defined and measured, such as the level of intrusiveness and the change in performance over time. The search for final decision solutions and the verification of the proposed model are based on experimental results from both perceptual studies, which are evaluating visibility and intrusiveness of marketing content as well as online campaigns providing interaction data for estimation of effectiveness. Surprisingly, the online response to the most noticeable advertisements with highly perceived visibility and intrusiveness was relatively low. During the field study performed in order to compute the model parameters, the best results were achieved for advertising content with moderate visual influence on web users. Simulations with the proposed model revealed that a growing level of persuasion can increase results only to a certain extent. Above a saturation point, a strategy based on extensive visual effects, such as high-frequency flashing, resulted in a very high increase of intrusiveness and a slightly better performance in terms of acquired interactions. Proposed balanced content design with the use of intelligent decision support system creates directions towards sustainable advertising and a friendlier online environment.

Towards the Tradeoff Between Online Marketing Resources Exploitation and the User Experience with the Use of Eye Tracking

Online systems are often overloaded with marketing content and as a result, perceived intrusiveness negatively affects the user experience and the evaluation of the website. Intentional and unintentional avoidance of the commercial content creates the need for compromise solutions from both the perspective of user experience and business goals. The presented research shows a unique approach to search for tradeoffs between the editorial content and the intensity of marketing components with the use of eye tracking and the multiple-criteria decision analysis methods.

Method of Criteria Selection and Weights Calculation in the Process of Web Projects Evaluation

The article outlines the issues of website quality assessment, reduction of website assessment criteria and factors that users employ in the assessment of websites. The research presents a selection procedure concerning significant choice criteria and revealing undisclosed user preferences based on the website quality assessment models. The formulated procedure utilizes feature selection methods derived from machine learning. Results concerning undisclosed preferences were verified through a comparison with those declared by website users.

Methodological aspects of Decision Support System for the location of renewable energy sources

The aim of this article is to present the methodological framework for Decision Support System for the process of selecting the location of renewable energy sources. For this purpose, the paper presents the methodology and MCDA methods sequentially structuralizing and modeling the decision space and exploiting the developed model. The detailed area of research and verification of proposed approach are related to the problem of offshore wind farm localization. Proposed framework defines input information together with methodological background required for decision support processes.

Knowledge Management in Website Quality Evaluation Domain

This paper deals with the problem of building a repository of knowledge about the methods and models of assessing the quality of Internet services. The repository has been constructed in the form of ontologies representing the various methods of quality assessment. For this purpose, the algorithm was developed based on ontologies with conceptualization of knowledge contained in the individual methods, and each completed ontology was evaluated. As a result of the research, domain ontologies were implemented reflecting the website quality assessment methods.

Modeling the Impact of Visual Components on Verbal Communication in Online Advertising

Together with the development of electronic marketing, the key factors that influence the effectiveness of interactive media were identified in the earlier research. This article presents approach which makes possible to determine the relationship between the textual and visual components and their impact on results of the campaign. The structure of interactive advertising unit with adjustable visual and verbal influence is presented followed by results from the field experiment performed with the usage of proposed approach.

Integration of domain ontologies in the repository of website evaluation methods

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.

NEAT F-PROMETHEE – A new fuzzy multiple criteria decision making method based on the adjustment of mapping trapezoidal fuzzy numbers

Abstract The Fuzzy PROMETHEE (Preference Ranking Organization METHod for Enrichment Evaluation) method allows one to capture uncertainty and imprecision of input data of a decision problem as well as the uncertainty of the decision-makers preferences. However, a considerable number of implementations of the Fuzzy PROMETHEE method are burdened with some imperfections related to, among other things, a high level of complexity, an applied computational procedure or the incompatibility with the classical PROMETHEE method paradigms. The article presents a new fuzzy MCDM method called NEAT F-PROMETHEE (New Easy Approach To Fuzzy PROMETHEE) characterized by low complexity, conformity with the methodological assumptions of the classical PROMETHEE method and the improvement of the process of mapping fuzzy numbers from a space X on Y with the use of the correction mechanism while mapping. Furthermore, other improvements have been introduced which are to simplify the computational procedure and increase its clarity for the sake of the decision-maker. The prepared method and its results have been compared to other Fuzzy PROMETHEE implementations, the classical PROMETHEE method as well as the Fuzzy TOPSIS method. In the research, it has been found out that the correction mechanism and other improvements applied in NEAT F-PROMETHEE make it possible to obtain a higher computational accuracy what results in a higher credibility of the solution of a decision problem in comparison with many other Fuzzy PROMETHEE implementations. The advantage of the prepared method over more complex implementations is its simplicity, easiness of application and interpretation of results. It has also been indicated that uncertainty of input data and uncertainty of the decision-makers preferences are related to each other and the relationship is expressed by grouped relations of preferences, that is, preference, J-preference and outranking.

Web Projects Evaluation Using the Method of Significant Website Assessment Criteria Detection

The research presented in the article consists of an examination of the applicability of feature selection methods in the task of selecting website assessment criteria, to which weights are assigned. The applicability of the chosen methods was examined against the approach in which the weightings of website assessment criteria are defined by users. The research shows a selection procedure concerning significant choice criteria and reveals undisclosed user preferences based on the website quality assessment models. Results concerning undisclosed preferences were verified through a comparison with those declared by website users.

Construction and Restructuring of the Knowledge Repository of Website Evaluation Methods

Many methods can be employed to evaluate the quality of websites. Although the methods can be used for different purposes and require various assessment approaches it is challenging to select a proper method adequate to the needs. The research presented in the article is focused on building a repository of knowledge about the methods for assessing the quality of a website. The repository in the form of ontologies covers a variety of quality assessment methods and makes their proper selection possible. The proposed approach was verified with major methods and the resulting ontology may act as a repository of domain knowledge.