Challenges and Solutions to the Student Dropout Prediction Problem in Online Courses

Prenkaj, Bardh; Stilo, Giovanni; Madeddu, Lorenzo

doi:10.1145/3340531.3412172

Cited by 10 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Yu, Lee, and Kizilcec 2021) proposed a fair student dropout prediction system from educational database. (Prenkaj, Stilo, and Madeddu 2020a) analyzed the challenges of student dropout from static database that involves definition, machine learning techniques to be used, evaluation measures and privacy concerns.…”

Section: Related Workmentioning

confidence: 99%

“…Many researchers have proposed to model factors impacting student dropout from large scale educational database using statistical and machine learning models. Most researchers have focused on using static or temporal structured data, such as GPA, SAT scores etc., that are readily available in institutional databases (Prenkaj, Stilo, and Madeddu 2020a). Some of the researchers proposed to use unstructured text analysis such as advising notes, forum post, social media status, online chats and email mining using natural language processing techniques to predict student dropout (Jayaraman 2020;Tinto 1993).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

College Student Retention Risk Analysis from Educational Database Using Multi-Task Multi-Modal Neural Fusion

Alam

2022

AAAI

View full text Add to dashboard Cite

We develop a Multimodal Spatiotemporal Neural Fusion network for MTL (MSNF-MTCL) to predict 5 important students' retention risks: future dropout, next semester dropout, type of dropout, duration of dropout and cause of dropout. First, we develop a general purpose multi-modal neural fusion network model MSNF for learning students' academic information representation by fusing spatial and temporal unstructured advising notes with spatiotemporal structured data. MSNF combines a Bidirectional Encoder Representations from Transformers (BERT)-based document embedding framework to represent each advising note, Long-Short Term Memory (LSTM) network to model temporal advising note embeddings, LSTM network to model students' temporal performance variables and students' static demographics altogether. The final fused representation from MSNF has been utilized on a Multi-Task Cascade Learning (MTCL) model towards building MSNF-MTCL for predicting 5 student retention risks. We evaluate MSNF-MTCL on a large educational database consists of 36,445 college students over 18 years period of time that provides promising performances comparing with the nearest state-of-art models. Additionally, we test the fairness of such model given the existence of biases.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

College Student Retention Risk Analysis from Educational Database Using Multi-Task Multi-Modal Neural Fusion

Alam

2022

AAAI

View full text Add to dashboard Cite

show abstract

“…There is a major concern among educational researchers with the disengagement of the students from the learning activities, which frequently leads to academic failure and, lastly, dropout. This issue is even more noticeable in distance learning [1], which became the default way of learning in many countries in times of the current pandemic. One way to counteract this problem is through gamification, which has been proven as a capable tool to reduce the dropout rate [2].…”

Section: Introductionmentioning

confidence: 99%

“…OneUp [7], a customizable platform aimed at facilitating the process of gamifying academic courses, has been developed as a response to these challenges in education in general (i.e., not only programming). Unfortunately, to the best of the authors' knowledge, (1) it remains a closed prototype (source code not available and access to a live deployment is only granted by request), (2) formats for sharing and reusing exercise packages and gamification layers are not public (if they exist), and (3) supported gamification elements could be enriched (i.e., more than points, badges, leaderboards, levels, and virtual currency).…”

Section: Introductionmentioning

confidence: 99%

Managing Gamified Programming Courses with the FGPE Platform

et al. 2022

View full text Add to dashboard Cite

E-learning tools are gaining increasing relevance as facilitators in the task of learning how to program. This is mainly a result of the pandemic situation and consequent lockdown in several countries, which forced distance learning. Instant and relevant feedback to students, particularly if coupled with gamification, plays a pivotal role in this process and has already been demonstrated as an effective solution in this regard. However, teachers still struggle with the lack of tools that can adequately support the creation and management of online gamified programming courses. Until now, there was no software platform that would be simultaneously open-source and general-purpose (i.e., not integrated with a specific course on a specific programming language) while featuring a meaningful selection of gamification components. Such a solution has been developed as a part of the Framework for Gamified Programming Education (FGPE) project. In this paper, we present its two front-end components: FGPE AuthorKit and FGPE PLE, explain how they can be used by teachers to prepare and manage gamified programming courses, and report the results of the usability evaluation by the teachers using the platform in their classes.

show abstract

“…Furthermore, those involving coding skills belong to the top-five best paid of the fifteen [6]. The existing difficulties in teaching and learning programming, however, only worsened [2] as educational institutions are now massively pushing towards online learning and keeping students engaged at distance is even more challenging [11].…”

Section: Introductionmentioning

confidence: 99%

FGPE Gamification Service: A GraphQL Service to Gamify Online Education

Paiva

Haraszczuk

Queirós

et al. 2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Keeping students engaged while learning programming is becoming more and more imperative. Of the several proposed techniques, gamification is presumably the most widely studied and has already proven as an effective means to engage students. However, there is a complete lack of public and customizable solutions to gamified programming education that can be reused with personalized rules and learning material. FGPE Gamification Service (FGPE GS) is an open-source GraphQL service that transforms a package containing the gamification layer -adhering to a dedicated open-source language, GEdIL -into a game. The game provides students with a gamified experience leveraging on the automaticallyassessable activities referenced by the challenges. This paper presents FGPE GS, its architecture, data model, and validation.

show abstract

Challenges and Solutions to the Student Dropout Prediction Problem in Online Courses

Cited by 10 publications

References 8 publications

College Student Retention Risk Analysis from Educational Database Using Multi-Task Multi-Modal Neural Fusion

College Student Retention Risk Analysis from Educational Database Using Multi-Task Multi-Modal Neural Fusion

Managing Gamified Programming Courses with the FGPE Platform

FGPE Gamification Service: A GraphQL Service to Gamify Online Education

Contact Info

Product

Resources

About