This paper reports the results of a survey conducted to examine the root causes leading to student dropout at a Greek distance education university. Data was gathered from two different courses – an undergraduate course leading to a Bachelors degree in Informatics (characterized by high dropout rates), and a postgraduate course leading to a Masters degree in education (characterized by low dropout rates). A comparative analysis of these two different courses revealed important similarities in dropout percentages and the reasons cited by students for dropping out. Our analysis also revealed important differences as well. This paper presents the results of a survey designed to investigate the relationship between dropout with intrinsic (student-related) factors such as sickness, work/ school conflict etc., and extrinsic (institutional-related) factors such as study methods and materials, educational approach, and tutor influence.
26 January 2016 in European Journal of Open, Distance and E-Learning
Online fora have become not only one of the most popular communication tools in e-learning environments, but also one of the key factors of the learning process, especially in distance learning, as they can provide to the students involved, motivation for collaboration in order to achieve a common goal. The purpose of this study is to analyse data related to the participation of postgraduate students in the online forum of their course at the Hellenic Open University. The content of the messages posted is analysed by using text mining techniques, while the network through which the students interact is processed through social network analysis techniques. Furthermore, sentiment analysis and opinion mining is applied on the same dataset. Our aim is to study students’ attitude towards the course and its features, as well as to model their sentiment behaviour over time, and finally to detect if and how this affected their overall performance. The combined knowledge attained from the aforementioned techniques can provide tutors with practical and valuable information for the structure and the content of the students’ exchanged messages, the patterns of interaction among them, the trend of sentiment polarity during the course, so as to improve the educational process. Περίληψη Οι διαδικτυακές ομάδες συζήτησης (Forum) είναι ένα από τα δημοφιλέστερα εργαλεία επικοινωνίας σε μαθησιακά περιβάλλοντα. Αποτελούν έναν από τους βασικούς παράγοντες της μαθησιακής διαδικασίας, ειδικά στην εκπαίδευση από απόσταση, καθώς παρέχουν στους συμμετέχοντες εκπαιδευόμενους τα απαραίτητα κίνητρα συνεργασίας για την επίτευξη κοινών μαθησιακών στόχων. Σκοπός αυτής της εργασίας είναι η ανάλυση δεδομένων από τη συμμετοχή μεταπτυχιακών φοιτητών του Ελληνικού Ανοικτού Πανεπιστημίου σε διαδικτυακή ομάδα συζήτησης στα πλαίσια μαθημάτων του Προγράμματος Σπουδών τους. Το περιεχόμενο των δημοσιευμένων μηνυμάτων των συμμετεχόντων αναλύθηκε χρησιμοποιώντας μεθόδους και τεχνικές εξόρυξης κειμένου, ενώ η αλληλεπίδραση των φοιτητών μελετήθηκε μέσω τεχνικών ανάλυσης κοινωνικών δικτύων. Επιπλέον, στο ίδιο σύνολο δεδομένων εφαρμόστηκαν τεχνικές ανάλυσης συναισθήματος και...
13 July 2019 in Education and Information Technologies
Attrition is one of the main concerns in distance learning due to the impact on the incomes and institutions reputation. Timely identification of students at risk has high practical value in effective students’ retention services. Big Data mining and machine learning methods are applied to manipulate, analyze, and predict students’ failure, supporting self-directed learning. Despite the extensive application of data mining to education, the imbalance problem in minority classes of students’ attrition is often overlooked in conventional models. This document proposes a large data frame using the Hadoop ecosystem and the application of machine learning techniques to different datasets of an academic year at the Hellenic Open University. Datasets were divided into 35 weeks; 32 classifiers were created, compared and statistically analyzed to address the minority classes’ imbalance of student’s failure. The algorithms MetaCost-SMO and C4.5 provide the most accurate performance for each target class. Early predictions of timeframes determine a remarkable performance, while the importance of written assignments and specific quizzes is noticeable. The models’ performance in any week is exploited by developing a prediction tool for student attrition, contributing to timely and personalized intervention.
1 October 2002 in The International Review of Research in Open and Distributed Learning
This study traces the root causes of dropout rates in one post-graduate course “Studies in Education,” offered by the Hellenic Open University (HOU). From our research findings, it was found that the main cause of dropping out stem from a combination of adult learners’ obligations, specifically balancing their academic workload with their employment commitments and family obligations (mainly for female students). The second reason for dropout rates among adult distance education learners include students’ miscalculation of the available time for studying and their underestimation of the extra effort required for effective learning. These reasons can be compared to the educational material, which, in general, was not considered overly difficult and did not appear to compel students to abandon their studies. Key terms: dropout, distance education, adults education
29 September 2021 in Education and Information Technologies