Sentiment Classification of Post-Earthquake Consumer Brand Hate on Social Media Using Machine Learning Techniques

Abstract

The widespread use of social media allows consumers to evaluate brands and to get into a direct interaction with brands and other followers of the same brands. After the devastating earthquake on February 6th, 2023, in ten provinces in Turkey a social media brand hatred was observed on two global brands Netflix and Starbucks. Brands were accused of not showing the necessary sensitivity and empathy towards the affected and the brand devotees. The objective of this study is to examine and classify brand hatred in online consumer-generated content using supervised machine learning methods. While the construct of brand hate has been extensively investigated in the discipline of marketing using different data collection methodologies, this is one of the first attempts to use machine learning methods for the analysis of the phenomenon. Unlike classic polarization, the labeling process was associated with the size of brand hatred; 0 denotes neutral reactions, -1 negative emotional reactions, and -2 negative relationship reactions. Support Vector Machines (SVM) was identified as the most successful algorithm for the explanation of the phenomenon.