A great deal of valuable information included in maritime accident reports needs to be excavated to contribute to accident prevention or risk defence. In the present study, data mining technologies are applied to explore the potential causation correlations among the risk factors associated with maritime accidents. A collection of 285 accident reports is subjected to database analysis by using text mining technology to extract keywords, and the critical factors are then determined with reference to objective reports. The FP-Growth (frequent pattern growth) algorithm is then applied to identify the association rules hidden in the causations leading accidents, and the strength level of the identified association rules is evaluated quantitatively. The results show that the data mining technologies are applicable for identifying correlations hidden among factors contributing to maritime accidents. In addition, single factors do not significantly lead to accidents, while the integration of factors can easily cause accidents even under the condition of a good navigation environment. Therefore, stakeholders involved in maritime activities are advised to systematically assess risk factors, and prevent maritime accidents by interrupting the correlations among the factors.
MaXDengWQiaoW, et al. A methodology to quantify the risk propagation of hazardous events for ship grounding accidents based on directed CN. Reliab Eng Syst Saf2022; 221: 108334.
7.
SonerOAsanUCelikM.Use of HFACS–FCM in fire prevention modelling on board ships. Saf Sci2015; 77: 25–41.
8.
QiaoWLiuYMaX, et al. A methodology to evaluate human factors contributed to maritime accident by mapping fuzzy FT into ANN based on HFACS. Ocean Eng2020; 197: 106892.
9.
WróbelK.Searching for the origins of the myth: 80% human error impact on maritime safety. Reliab Eng Syst Saf2021; 216: 107942.
10.
LanHMaXQiaoW, et al. A methodology to assess the causation relationship of seafarers’ unsafe acts for ship grounding accidents based on Bayesian SEM. Ocean Coast Manag2022; 225: 106189.
11.
ToffoliALefèvreJMBitner-GregersenE, et al. Towards the identification of warning criteria: analysis of a ship accident database. Appl Ocean Res2005; 27: 281–291.
12.
O’ConnorPJO’ConnorN.Causes and prevention of boating fatalities. Accid Anal Prev2005; 37: 689–698.
13.
KnappSKumarSSakuradaY, et al. Econometric analysis of the changing effects in wind strength and significant wave height on the probability of casualty in shipping. Accid Anal Prev2011; 43: 1252–1266.
14.
AntãoPSoaresCG.Analysis of the influence of human errors on the occurrence of coastal ship accidents in different wave conditions using Bayesian belief networks. Accid Anal Prev2019; 133: 105262.
15.
WengJYangDChaiT, et al. Investigation of occurrence likelihood of human errors in shipping operations. Ocean Eng2019; 182: 28–37.
16.
PazoukiKForbesNNormanRA, et al. Investigation on the impact of human-automation interaction in maritime operations. Ocean Eng2018; 153: 297–304.
17.
SharmaANazirSErnstsenJ.Situation awareness information requirements for maritime navigation: a goal directed task analysis. Saf Sci2019; 120: 745–752.
18.
MurrayBPereraLP.Ship behavior prediction via trajectory extraction-based clustering for maritime situation awareness. J Ocean Eng Sci2022; 7: 1–13.
19.
RaiyanADasSIslamMR.Event tree analysis of marine accidents in Bangladesh. Procedia Eng2017; 194: 276–283.
20.
UğurluÖKöseEYıldırımU, et al. Marine accident analysis for collision and grounding in oil tanker using FTA method. Marit Pol Manag2015; 42: 163–185.
21.
KujalaPHänninenMArolaT, et al. Analysis of the marine traffic safety in the Gulf of Finland. Reliab Eng Syst Saf2009; 94: 1349–1357.
22.
ChauvinCLardjaneSMorelG, et al. Human and organisational factors in maritime accidents: analysis of collisions at sea using the HFACS. Accid Anal Prev2013; 59: 26–37.
23.
YıldırımUBaşarEUğurluÖ.Assessment of collisions and grounding accidents with human factors analysis and classification system (HFACS) and statistical methods. Saf Sci2019; 119: 412–425.
24.
SarıalioğluSUğurluÖAydınM, et al. A hybrid model for human-factor analysis of engine-room fires on ships: HFACS-PV&FFTA. Ocean Eng2020; 217: 107992.
25.
ChenS-TWallADaviesP, et al. A human and organisational factors (HOFs) analysis method for marine casualties using HFACS-Maritime Accidents (HFACS-MA). Saf Sci2013; 60: 105–114.
26.
QiaoWLiuYMaX, et al. Human Factors Analysis for maritime accidents based on a dynamic fuzzy Bayesian network. Risk Anal2020; 40: 957–980.
27.
LeeSMohYBTabibzadehM, et al. Applying the AcciMap methodology to investigate the tragic Sewol ferry accident in South Korea. Appl Ergon2017; 59: 517–525.
28.
UddinMIAwalZI.Systems-theoretic approach to safety of inland passenger ship operation in Bangladesh. Saf Sci2020; 126: 104629.
29.
FanSZhangJBlanco-DavisE, et al. Effects of seafarers’ emotion on human performance using bridge simulation. Ocean Eng2018; 170: 111–119.
30.
FanSBlanco-DavisEYangZ, et al. Incorporation of human factors into maritime accident analysis using a data-driven Bayesian network. Reliab Eng Syst Saf2020; 203: 107070.
31.
SarbayevMYangMWangH.Risk assessment of process systems by mapping fault tree into artificial neural network. J Loss Prev Process Ind2019; 60: 203–212.
32.
SabirZManzarMARajaMAZ, et al. Neuro-heuristics for nonlinear singular Thomas-Fermi systems. Appl. Soft Comput2018; 65: 152–169.
33.
YanHYangNPengY, et al. Data mining in the construction industry: present status, opportunities, and future trends. Autom Constr2020; 119: 103331.
34.
HuiSCJhaG.Data mining for customer service support. Inf Manage2000; 38: 1–13.
35.
MinerGDelenDElderJ, et al. Practical text mining and statistical analysis for non-structured text data applications. 1st ed.Academic Press, 2012.
36.
SuhY.Sectoral patterns of accident process for occupational safety using narrative texts of OSHA database. Saf Sci2021; 142: 105363.
37.
JeeheeLJune-SeongY.Predicting project’s uncertainty risk in the bidding process by integrating unstructured text data and structured numerical data using text mining. Appl Sci2017; 7: 1141.
38.
MacêdoJBdas Chagas MouraMAicheleD, et al. Identification of risk features using text mining and BERT-based models: application to an oil refinery. Process Saf Environ Prot2022; 158: 382–399.
39.
BoggsAMWaliBKhattakAJ.Exploratory analysis of automated vehicle crashes in California: a text analytics & hierarchical Bayesian heterogeneity-based approach. Accid Anal Prev2020; 135: 105354.
40.
YangZBaraldiPZioE.A novel method for maintenance record clustering and its application to a case study of maintenance optimization. Reliab Eng Syst Saf2020; 203: 107103.
41.
KimJSKimBS.Analysis of fire-accident factors using Big-Data analysis method for construction areas. KSCE J Civil Eng2018; 22: 1535–1543.
42.
XuNMaLLiuQ, et al. An improved text mining approach to extract safety risk factors from construction accident reports. Saf Sci2021; 138: 105216.
43.
KimDSeoDChoS, et al. Multi-co-training for document classification using various document representations: TF–IDF, LDA, and Doc2Vec. Inf Sci2019; 477: 15–29.
44.
BeelJGippBLangerS, et al. Research-paper recommender systems: a literature survey. Int J Digit Libr2016; 17: 305–338.
45.
LiuGBoydMYuM, et al. Identifying causality and contributory factors of pipeline incidents by employing natural language processing and text mining techniques. Process Saf Environ Prot2021; 152: 37–46.
ZhouYLiCDingL, et al. Combining association rules mining with complex networks to monitor coupled risks. Reliab Eng Syst Saf2019; 186: 194–208.
48.
SharmaASharmaA.Design & Analysis of Fuzzy based Association rule mining. Int J Comput Appl Inf Technol2013; 3: 12–17.
49.
WuBREltahlaAAKeoshkerianE, et al. A method for detecting hepatitis C envelope specific memory B cells from multiple genotypes using cocktail E2 tetramers. J Immunol Methods2019; 472: 65–74.
50.
XuRLuoF.Risk prediction and early warning for air traffic controllers’ unsafe acts using association rule mining and random forest. Saf. Sci2021; 135: 105125.
51.
HongJTamakloeRParkD.Application of association rules mining algorithm for hazardous materials transportation crashes on expressway. Accid Anal Prev2020; 142: 105497.
52.
JiaXZhangD.Prediction of maritime logistics service risks applying soft set based association rule: an early warning model. Reliab Eng Syst Saf2021; 207: 107339.
53.
AgrawalRImieli’NskiTSwamiA. Mining association rules between sets of items in large databases. In: BunemanPJajodiaS, (eds.). SIGMOD’93: Proceedings of the 1993 ACM SIGMOD international conference on Management of data. Washington, United States: Association for Computing Machinery, New York, United States, 1993; 22: 207–216.
54.
BaguiSDevulapalliKCoffeyJ.A heuristic approach for load balancing the FP-growth algorithm on MapReduce. Array2020; 7: 100035.
55.
ShabtayLFournier-VigerPYaariR, et al. A guided FP-Growth algorithm for mining multitude-targeted item-sets and class association rules in imbalanced data. Inf Sci2021; 553: 353–375.
56.
HanJPeiJYinY.Mining frequent patterns without candidate generation. SIGMOD Rec2000; 29: 1–12.
57.
MazaheriAMontewkaJNisulaJ, et al. Usability of accident and incident reports for evidence-based risk modeling – A case study on ship grounding reports. Saf Sci2015; 76: 202–214.
QiaoWLiuQLiX, et al. Using data mining techniques to analyze the influencing factor of unsafe behaviors in Chinese underground coal mines. Resour Policy2018; 59: 210–216.
KangARenLHuaC, et al. Environmental management strategy in response to COVID-19 in China: based on text mining of government open information. Sci Total Environ2021; 769: 145158–158.
62.
JonesKS.A statistical interpretation of term specificity and its application in retrieval. J Document1972; 28: 11–21.
63.
ChenKZhangZLongJ, et al. Turning from TF-IDF to TF-IGM for term weighting in text classification. Expert Syst Appl2016; 66: 245–260.
64.
ChengYYuW-DLiQ.GA-based multi-level association rule mining approach for defect analysis in the construction industry. Autom Constr2015; 51: 78–91.
65.
ChenDPeiYXiaQ. Research on human factors cause chain of ship accidents based on multidimensional association rules. Ocean Eng2020; 218: 107717.
66.
WangHLiuZWangX, et al. An analysis of factors affecting the severity of marine accidents. Reliab Eng Syst Saf2021; 210: 107513.
67.
PangRZhangX.Achieving environmental sustainability in manufacture: A 28-year bibliometric cartography of green manufacturing research. J Clean Prod2019; 233: 84–99.
68.
DasSDuttaAJalayerM, et al. Factors influencing the patterns of wrong-way driving crashes on freeway exit ramps and median crossovers: exploration using ‘Eclat’ association rules to promote safety. Int J Transp Sci Technol2018; 7: 114–123.
69.
WengJZhuJZYanX, et al. Investigation of work zone crash casualty patterns using association rules. Accid Anal Prev2016; 92: 43–52.
70.
XuCBaoJWangC, et al. Association rule analysis of factors contributing to extraordinarily severe traffic crashes in China. J Saf Res2018; 67: 65–75.
71.
ÇakırEFışkınRSevgiliC. Investigation of tugboat accidents severity: An application of association rule mining algorithms. Reliab Eng Syst Saf. 2021; 209: 107470.
72.
LanHMaXQiaoW, et al. On the causation of seafarers’ unsafe acts using grounded theory and association rule. Reliab Eng Syst Saf2022; 223: 108498.
73.
ZhangXChenWXiY, et al. Dynamics simulation of the risk coupling effect between maritime pilotage human factors under the HFACS framework. J Mar Sci Eng2020; 8: 144.
