Analysis of Employee Capabilities Using Sentiment Analysis and Machine Learning Methods

Employee capability is a critical factor that affects the organization's performance. However, many organizations find it challenging to analyze due to its complexity. This paper aims to analyze employee capability using sentiment analysis and machine learning algorithms. To extract and classify those hidden capabilities from employee social media data, sentiment analysis examines employee comments on the social media platform ‘X’ by identifying words and emotions that are frequently used. Five Machine learning (ML) algorithms are employed: the Multinomial Naive Bayes Classifier, Random Forrest Classifier, Extra-Trees Classifier, Gradient Boosting Classifier, and Support Vector Classifier. The Machine Learning algorithms' performance in accurately classifying the sentiment is evaluated based on precision, recall, F1 score, and accuracy. The results reveal that the Random Forest Classifier and Extra-Trees Classifier exhibit superior performance in accurately classifying sentiments within the text data, achieving high precision, recall, F1 score, and accuracy scores of 90% and 92%, respectively. In contrast, the Gradient Boosting Classifier demonstrates relatively lower performance. This study contributes to the existing literature by applying artificial intelligence tools to analyze employee capabilities, which provides insights and makes informed decisions about employees and enhances hiring process. The study presents opportunities for further research using machine learning and natural language processing techniques to analyze the employee capabilities and therefore enhance hiring procedures. The study also highlights the need for capabilities frameworks to address specific issues that require further investigation. Furthermore, it is essential to develop comprehensive ethical frameworks and guidelines that address informed consent, data privacy, fairness, and bias mitigation.