Classifying online corporate reputation with machine learning: a study in the banking domain

Abstract

<p>Purpose – User-generated social media comments can be a useful source of information for understanding<br />online corporate reputation. However, the manual classification of these comments is challenging due to their<br />high volume and unstructured nature. The purpose of this paper is to develop a classification framework and<br />machine learning model to overcome these limitations.<br />Design/methodology/approach – The authors create a multi-dimensional classification framework for the<br />online corporate reputation that includes six main dimensions synthesized from prior literature: quality,<br />reliability, responsibility, successfulness, pleasantness and innovativeness. To evaluate the classification<br />framework’s performance on real data, the authors retrieve 19,991 social media comments about two Finnish<br />banks and use a convolutional neural network (CNN) to classify automatically the comments based on<br />manually annotated training data.<br />Findings – After parameter optimization, the neural network achieves an accuracy between 52.7 and 65.2<br />percent on real-world data, which is reasonable given the high number of classes. The findings also indicate<br />that prior work has not captured all the facets of online corporate reputation.<br />Practical implications – For practical purposes, the authors provide a comprehensive classification<br />framework for online corporate reputation, which companies and organizations operating in various domains<br />can use. Moreover, the authors demonstrate that using a limited amount of training data can yield a<br />satisfactory multiclass classifier when using CNN.<br />Originality/value – This is the first attempt at automatically classifying online corporate reputation using<br />an online-specific classification framework.<br /></p>