Explore publications.

This paper aims to evaluate the effects of demographic targeting, platform selection, and engagement metrics on the effectiveness of social media advertising campaigns. In this paper, it is also aimed to provide a comprehensive understanding of how these factors influence conversion outcomes. We employed a hybrid analytics method combining ANOVA, correlation, and regression analysis to examine patterns of user engagement and ad performance. A dataset of 200,235 ad campaign records conducted in the United States was analyzed to assess variations across gender, age groups, and platforms. The main findings of the study demonstrate that (i) women consistently exhibited higher conversion rates compared to men, highlighting the potential of gender-specific content strategies; (ii) users aged 35–44 achieved the highest engagement, suggesting that middle-aged audiences may be more responsive to targeted campaigns; and finally, (iii) among platforms, Instagram led in conversion performance, while Facebook showed comparable engagement rates, and both significantly outperformed other platforms in terms of overall impact. Click-through rate was found to be moderately correlated with conversions, whereas impressions showed weak returns, indicating diminishing value at higher exposure levels. These results underscore the importance of optimizing both message and delivery channel to specific audience segments.This study contributes to digital marketing literature by integrating demographic variables, engagement indicators, and platform performance into a unified model. The insights derived offer practical implications for businesses and advertisers aiming to enhance return on investment and optimize campaign strategies in a fast-paced, digitally driven advertising landscape.

This study aims to examine the importance of feature selection in machine learning, specifically in predicting user engagement with social media post photographs on university Facebook pages. The paper uses a thorough analysis to demonstrate the crucial significance of choosing suitable features and their corresponding algorithms. The research intends to demonstrate how this strategic approach affects the accuracy of prediction findings in social media interaction. The research presents a compelling case study involving 24 leading universities from Australia, the United Kingdom, and the United States. The results underscore the efficacy of the method, stressing that the meticulous selection of characteristics and the use of appropriate algorithms are crucial elements for attaining the best results in social media forecasts. Implications: The study's results have important consequences, particularly within the changing environment of machine learning and its use in social media. Feature selection and algorithm choice are vital for optimizing social media initiatives for institutions.

The subject of scientific research is the examination of the difference in brand loyalty factors according to the socio-demographic characteristics (age, education, income level) of confectionary consumers, as well as the examination of the connection between brand loyalty factors and brand loyalty of confectionary consumers in Serbia. 200 respondents completed the structured questionnaire. Determining the difference in brand loyalty factors according to socio-demographic characteristics of confectionary consumers was performed using the f test, while the correlation between the brand loyalty factors and brand loyalty was performed using Spearman's rank correlation as a non-parametric alternative to Pearson's correlation. It was determined that there is a significant difference in brand loyalty factors according to the age, education, and income level of confectionary consumers. There is also a statistically significant correlation between all brand loyalty factors and brand loyalty.

The basic objective of this paper was to determine the importance and potential restoration of brownfield sites in terms of economic prosperity of a particular region or country. In addition, in a theoretical sense, this paper presents the methods used in the identification of brownfield sites such as Smart Growth Network model and Thomas GIS model, and methods for evaluation of brownfield sites or the indexing method, cost-benefit and multivariate analysis.