Mining causal relations from maritime accident investigation reports

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.advisorLindh-Knuutila, Tiina
dc.contributor.advisorHänninen, Maria
dc.contributor.authorTirunagari, Santosh
dc.contributor.departmentTietotekniikan laitosfi
dc.contributor.schoolPerustieteiden korkeakoulufi
dc.contributor.schoolSchool of Scienceen
dc.contributor.supervisorOja, Erkki
dc.date.accessioned2020-12-28T15:11:34Z
dc.date.available2020-12-28T15:11:34Z
dc.date.issued2013
dc.description.abstractText mining is a process of extracting information of interest from text. Such a method includes techniques from various areas such as Information Retrieval (IR), Natural Language Processing (NLP), and Information Extraction (IE). In this thesis, text mining methods are applied to extract causal relations from maritime accident investigation reports collected from the Marine Accident Investigation Branch (MAIB). These causal relations provide information on various mechanisms behind accidents, including human and organizational factors relating to the accident. The objective of this thesis is to facilitate the analysis of the maritime accident investigation reports, by means of extracting contributory causes with more feasibility. A careful investigation of contributory causes from the reports provides opportunity to improve safety in future. Two methods have been employed in this thesis to extract the causal relations. They are 1) Pattern classification method and 2) Connectives method. The earlier one uses na'ive Bayes and Support Vector Machines (SVM) as classifiers. The latter simply searches for the words connecting cause and effect in sentences. The causal patterns extracted using these two methods are compared to the manual (human expert) extraction. The pattern classification method showed a fair and sensible performance with F-measure(average) = 65% when compared to connectives method with F-measure(average) = 58%. This study is evidence, that text mining methods could be employed in extracting causal relations from marine accidenten
dc.format.extentx + 58 s. + liitt. 6
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/100874
dc.identifier.urnURN:NBN:fi:aalto-2020122859705
dc.language.isoenen
dc.programme.majorInformaatiotekniikkafi
dc.programme.mcodeT-61fi
dc.rights.accesslevelclosedAccess
dc.subject.keywordpattern classificationen
dc.subject.keywordconnectives methoden
dc.subject.keywordcausal relationsen
dc.subject.keywordSVMen
dc.subject.keywordnaive Bayesen
dc.subject.keywordinformation extractionen
dc.subject.keywordMAIBen
dc.titleMining causal relations from maritime accident investigation reportsen
dc.type.okmG2 Pro gradu, diplomityö
dc.type.ontasotMaster's thesisen
dc.type.ontasotPro gradu -tutkielmafi
dc.type.publicationmasterThesis
local.aalto.digiauthask
local.aalto.digifolderAalto_07179
local.aalto.idinssi47260
local.aalto.openaccessno
Files