What type of study is this?

This is a Quantitative Study study.

October 15, 2025Open Access

Sentiment Analysis on Social Networks as a Tool to Support Decision Making in Reputational Risk Management in the Banking Sector

Key Points

The model shows an overall accuracy of up to 69.27% for sentiment classification.
Positive and negative emotional polarities were classified, aiding in reputational risk management.
Data preprocessing and Naive Bayes algorithm implementation enhanced the model's effectiveness.
Monitoring sentiments on social networks may bolster decision-making strategies within the banking sector.

Abstract

The growing digital exposure of financial institutions highlights the need for effective reputational risk monitoring. This study proposes the development of a sentiment analysis model applied to texts collected from the X social network (formerly Twitter), aiming to automatically classify user comments based on emotional polarity (positive, neutral, or negative). The methodology includes data collection via API, text preprocessing, class balancing, and the implementation of the Naive Bayes algorithm through supervised learning techniques in Python. Results showed an overall accuracy of up to 69.27% in the original dataset, with performance improvements for minority classes using upsampling. The model proved most effective in detecting negative sentiments, which are crucial in managing reputational risk. The proposed solution is intended to support decision-making in the banking sector by enhancing institutional image monitoring and crisis prevention strategies

Sentiment Analysis on Social Networks as a Tool to Support Decision Making in Reputational Risk Management in the Banking Sector

Key Points

Abstract

Cite This Study