Sentiment Analysis on Gender Pay Gap from Twitter (Renamed 'X'): Using Artificial Neural Network Approach

This study introduces a targeted approach to sentiment analysis, focusing on people's views and emotions on the persistent problem of the gender pay gap. Employing an Artificial Neural Network as a supervised machine learning technique, we examine the unique linguistic characteristics of Twitter (Renamed 'X'), discourse and the sentiments expressed on the gender pay gap at the British Broadcasting Corporation (BBC). We show that disclosure of the gender pay gap triggers discussion on other gender-related issues, including gender stereotypes, gender inequality, gender imbalance, gender parity and gender diversity. We suggest that the salience attributed to these other gender-related issues by the public could eclipse the significance of reducing the gender pay differential. We also show that gender stereotype was found to contribute significantly to public sentiment on the gender pay gap. Furthermore, we argue that it is important to consider a broad range of gender-related concerns when crafting policies aimed at reducing the gender pay gap, to ensure resolution of one does not inadvertently worsen other related issues of importance to stakeholders. Additionally, we contend that an integrative approach between stakeholder theory and institutional theory should be adopted when investigating/discussing the effects of the relationship between stakeholders and organisations.