Last month I successfully completed my Master’s degree with a final dissertation on “Artificial Intelligence in Marketing: a text mining and topic modeling approach.” at NOVA IMS
This methodology created 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.
This research was conducted using:
- Pybliometrics: Python-based API-Wrapper to pull, cache, and extract data from the Scopus database
- Latent Dirichlet Allocation (LDA) a non-supervised Machine Learning Algorithm. This Bayesian network and, therefore, a generative statistical model explains a set of observations through unobserved groups, and each group explains why some parts of the data are similar. LDA is commonly used as a topic modeling technique that can classify text in a document to a particular topic.
- To visualize the results, pyLDAvis was adopted to help interpret the topics in a topic model fed with a corpus of text data. This Python notebook visualization extracts information from a fitted LDA topic to deliver an interactive web-based visualization. The visualization is intended to be used within an IPython notebook but can also be saved to a stand-alone HTML file for easy sharing.
- Also, a word cloud package was used, enabling a friendly visualization of each LDA-resulting topics.
This literature review provided a snapshot of the existing literature, serving as a summary and introduction to the existing literature on AI in Marketing, which can interest researchers operating in this field. The topic modeling produced in this research offered a granular view of the scholarly on AI in marketing. Unlike previous research on this topic, this work provides a new form of data collection using python libraries, prebuilt packages, and new visualizations.
Get to read the full Scientific Research at: https://run.unl.pt/handle/10362/152222