Artificial Intelligence in Marketing: a text mining and topic modeling approach

Abstract

This research uses a Text Mining approach to analyze the literature. This methodology creates Artificial Intelligence (AI) dimensions and clusters in literature to find patterns and trends about its application in Marketing, resulting in a dataset of 2,255 articles on the AI and marketing topic by the leading publishers up to 2023. Since textual sources take big data format, this paper's techniques present several scalable advantages compared to other methodologies. This approach uses two methods to overcome the limitations: an API, a visual pictorial representation that summarizes the topics discovered. The results show that Data Modeling systems are the three most frequent terms in all the abstract tokens showing more than 2,000 occurrences. Trends such as Natural Language processing (sentiment, analysis, text, image, video, and language), Machine Learning, Algorithms, Expert Systems, and Social Media, particularly Twitter, have been unveiled from the data analysis. However, a clear description of AI in Marketing is still needed. Overall, this paper presents an approach with several scalability advantages compared to previous methods, a crucial aspect of dealing with big data.