Knowledge Transfer Mechanisms Using Text Mining and Sentiment Analysis – Case in an Online Collaboration

Abstract

This study aims to test, examine, and validate text-based human-machine knowledge transfer (KT) by comparing it with human-human KT. The online discussion experiment was carried out via WhatsApp group chats. Chat sentiment was determined using text mining and sentiment analysis and then compared with the respondent's understanding of the knowledge obtained from interviews. The results have shown that human-machine KT is close to human-human KT. By analyzing the correlation coefficient between the two, it is proven that sentiment indicates an understanding of knowledge. Positive sentiment shows similar or in-line understanding between the source and recipient of knowledge and indicates the achievement of KT objectives. Neutral sentiment indicates incomprehension due to the failure of KT. Meanwhile, negative sentiment is ambiguous; it may indicate an incomprehension or a misunderstanding of the knowledge received. This study contributes to the area of knowledge and sentiments, showing that the effectiveness of text-based KT activity can be identified using the sentiment analysis approach.