AI-based sentiment analysis as a driver of digital marketing transformation through consumer perceptions, online sentiment and purchase behaviour

Krsmanović, Stefan and Baltezarević, Radoslav (2026) AI-based sentiment analysis as a driver of digital marketing transformation through consumer perceptions, online sentiment and purchase behaviour. Oditor - casopis za Menadzment finansije i pravo, 12 (2). pp. 83-105. ISSN 2217-401X

Text Rad+5-1.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (600kB)

Abstract

Understanding the emotions and attitudes of consumers expressed in the digital environment is one of the key challenges of modern digital marketing. Although AI-based sentiment analysis is increasingly used to interpret user-generated content, a limited amount of research simultaneously considers its perception along with online sentiment and consumer trust in explaining purchasing behavior. The aim of this paper is to examine the relationship between the perception of AI-based sentiment analysis, online sentiment, consumer trust and purchasing behavior in digital marketing. Empirical research was conducted using a structured questionnaire on a sample of 138 respondents. Cronbach's alpha coefficient was used to assess the reliability of the instrument, while the hypotheses were tested using Pearson's chi-square test, Pearson's correlation coefficient and Spearman's correlation coefficient. The results confirm statistically significant positive relationships between the observed constructs and indicate that the perception of sentiment analysis based on artificial intelligence, positive online sentiment and consumer trust are associated with more favorable purchasing behavior in the digital environment. Research findings contribute to a better understanding of the role of emotional and psychological factors in digital marketing and represent the basis for future research that will include objective models of sentiment analysis and more advanced methodological approaches.

Actions (login required)

View Item