This paper aims to investigate tugboat accidents using various association rule mining algorithms. A total of 477 tugboat accident records obtained from the Information Handling Services (IHS) Sea-Web database for the period of 2008-2017 were analysed. Apriori, Predictive Apriori and FP-Growth algorithms were employed to extract the association rules of the tugboat accidents dataset. The present study revealed that tugboats aged over 20 years are crucial indicators for serious accidents. Hull/machinery damage and collision type accidents, on the other hand, constitute more than half of the total tugboat accidents. Association rule mining also showed that four of the five rules for serious accidents are attributed to hull/machinery damage. The results of this study are thought to be beneficial for tugboat and ship operators, port management and public authorities regarding the awareness of the factors affecting tugboat accidents.