Pregled bibliografske jedinice broj: 1226359
Identification of Features Associated with University Dropout-a case study of University of Split, Faculty of Maritime Studies
Identification of Features Associated with University Dropout-a case study of University of Split, Faculty of Maritime Studies // Proceedings of the International Association of Maritime Universities (IAMU) Conference / Kurshubadze, Nino ; Sviličić, Boris (ur.).
Batumi: Batumi State Maritime Academy, Georgia, 2022. str. 308-316 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1226359 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Identification of Features Associated with University Dropout-a case study of University of Split, Faculty of Maritime Studies
Autori
Gudelj, Anita ; Ukić Boljat, Helena ; Slišković, Merica
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the International Association of Maritime Universities (IAMU) Conference
/ Kurshubadze, Nino ; Sviličić, Boris - Batumi : Batumi State Maritime Academy, Georgia, 2022, 308-316
Skup
22nd Annual General Assembly of the International Association of Maritime Universities
Mjesto i datum
Batumi, Gruzija, 19.10.2022. - 22.10.2022
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
maritime higher education ; dropout ; machine learning ; feature selection ; Faculty of Maritime Studies Split
Sažetak
The primary goal of higher education institutions is to provide a quality educational process. Maritime higher education is an essential element in acquiring the knowledge, and skills needed on board a ship. One of the indicators of potential problems in this educational process may be a high number of dropouts in the early years. Predicting student success and dropout, or identifying students who are at higher risk for dropping out, is critical to improving the quality of higher education. An analysis of the academic performance of students at the University of Split, Faculty of Maritime Studies (PFST) was conducted a high dropout rate was revealed. This research aims to improve early prediction of student dropout by identifying the most relevant features. The data is processed and the features that influence dropout are extracted through an attribute selection algorithm and machine learning techniques such as decision trees. The results of our research suggest that higher education institutions should be aware of the need to identify early the profile of students who are at potential risk of dropping out. Moreover, the developed model is useful for strategic planning of additional mechanisms to improve the efficiency of study at maritime higher education institutions.
Izvorni jezik
Engleski
Znanstvena područja
Tehnologija prometa i transport, Biotehnologija, Informacijske i komunikacijske znanosti
POVEZANOST RADA
Ustanove:
Pomorski fakultet, Split