Theory-enhanced automation of the digital publics' relationship assessments

Abstract

The current dissertation aims to develop a Machine Learning (ML) method for automating the assessment of digital public relations by incorporating the Organization-Public Relationship Assessment (OPRA) developed from the public relations theory. The study targets customers/consumers and employees. For methods, Natural Language Processing (NLP) techniques, specifically text-embedding and classification, are used to analyze the crawled data and three survey data. The results demonstrate that TF-IDF, BERT embedding, and the SVM classification model perform best. The case study outcomes using TripAdvisor and Glassdoor review data validate the previous results. This dissertation project can serve as a pioneering effort to enhance the theoretical foundation of most current data analytics tools in public relations.