Using Sentiment Analysis to Identify Student Emotional State to Avoid Dropout in E-Learning

Bóbó, Míria; Campos, Fernanda; Ströele, Victor; David, José; Braga, Regina; Torrent, Tiago Timponi

doi:10.4018/ijdet.305237

Cited by 6 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Em [Atiq and Loui 2022], é apresentado um estudo sobre as emoc ¸ões de estudantes durante a realizac ¸ão de atividades de programac ¸ão, com observac ¸ões qualitativas. A análise de sentimentos apresentada em [Bóbó et al 2022] é utilizada para prever o risco de evasão com dados coletados de textos presentes em um ambiente virtual de aprendizagem.…”

Section: Trabalhos Relacionadosunclassified

Análise de sentimentos em turmas de programação com vistas ao apoio à permanência estudantil

Pfitscher,

Camargo,

Moreira

et al. 2023

Anais Do XXXIV Simpósio Brasileiro De Informática Na Educação (SBIE 2023)

View full text Add to dashboard Cite

A evasão e a desistência são alguns dos principais problemas enfrentados no ensino superior do Brasil. Diferentes frentes de estudos têm buscado compreender os motivos pelos quais os estudantes desistem dos estudos, sejam estudos de ordem psicopedagógicas ou baseados em dados. Neste trabalho, a utilização da análise de sentimentos é direcionada à turmas de programação de computadores de duas instituições de ensino superior, em que dados foram coletados de forma ativa e classificados por meio de uma metodologia que combinou análise psicopedagógica e automatizada baseada em Processamento de Linguagem Natural. Os principais resultados deste estudo mostram: i) uma taxa de adesão baixa ao questionário (50%), com maior adesão quando os estudantes são constantemente incentivados; ii) os sentimentos são similares entre as instituições de ensino superior, com entre 20 e 30% sendo negativos, e; iii) uma acurácia de 68% com PLN, indicando possível utilização para ações de mitigação da desistência.

show abstract

Section: Trabalhos Relacionadosunclassified

Análise de sentimentos em turmas de programação com vistas ao apoio à permanência estudantil

Pfitscher,

Camargo,

Moreira

et al. 2023

Anais Do XXXIV Simpósio Brasileiro De Informática Na Educação (SBIE 2023)

View full text Add to dashboard Cite

show abstract

“…Text sentiment is essential for defining learners' motivational profile that depends on their activities in VLE. Students' class engagement can be identified by analyzing their frequency of access data and interactions [4].…”

Section: Literature Reviewmentioning

confidence: 99%

Multifaceted Sentiment Detection System (MSDS) to Avoid Dropout in Virtual Learning Environment using Multi-class Classifiers

T¹,

J²

2023

IJACSA

View full text Add to dashboard Cite

Sentiment analysis with machine learning plays a vital role in Higher Educational Institutions (HEI) for decision making. Technology-enabled interactions can only be successful when a strong student-teacher link is established, and the emotions of students are clearly comprehended. The paper aims at proposing Multifaceted Sentiment Detection System (MSDS) for detecting sentiments of higher education students participating in virtual learning and to classify the comments posted by them using Machine Learning (ML) algorithms. Present research evaluated a total of n=1590 students' comments with the presence of three specific multifaceted characteristics each providing 530 comments to perform Sentiment Analysis (SA) for monitoring their sentiments, opinions that facilitate predicting dropout in virtual learning environment (VLE). This begins with the phrase extraction; then data pre-processing techniques namely digits, punctuation marks and stop-words removal, spelling correction, tokenization, lemmatization, ngrams, and POS (Part of Speech) are applied. Texts are vectorized using two feature extraction techniques with count vectorization and TF-IDF metrics and classified with four multiclass supervised ML techniques namely Random Forest, Linear SVC, Multinomial Naive Bayes, and Logistic Regression for multifaceted sentiment classification. Analyzing students' feedback using sentiment analysis techniques classifies their positive, negative, or even more refined emotions that enables dropout prediction. Experimental results reveal that the highest mean accuracy result for device efficiency, cognitive behavior, technological expertise with cloud learning platform usage were achieved by Logistic Regression with 98.49%, Linear SVC with 93.58% and Linear SVC with 92.08% respectively. Practically, results confirm feasibility for detecting students' multifaceted behavioral patterns and risk of dropout in VLE.

show abstract

“…Supervised Machine Learning Algorithms Articles Decision Tree(DT) [1], [2], [5], [6], [8], [12], [13], [15], [16]], [17], [18], [21], [22], [26], [30], [33], [38], [40], [45], [47], [50],[ Support Vector Machine(SVM) [51], [52], [55], [58], [59], [61], [67], [68], [71], [72], [73],…”

Section: Table (7) Analysis Of Supervised and Unsupervised Machine Le...mentioning

confidence: 99%

“…[32], [42], [58], [80] These are websites, blogs, journals etc where matters relating to the education sector are discussed. Social media and blogs [6], [8], [13], [15], [32], [34], [42], [55], [58] Social media and blogs are online platforms where students are free to express their feelings and emotions at any given time. It is a big source of data collection point.…”

Section: Table (7) Analysis Of Supervised and Unsupervised Machine Le...mentioning

confidence: 99%

Baseline Study of Different Sentiment Analysis Computing Methods to Enhance Quality Assurance In Teaching and Learning

Oghu,

Ogbuju,

Abiodun

et al. 2023

AIMS Research Publication

View full text Add to dashboard Cite

The idea of modernization has become a norm in society, and the quality of the education sector that is been delivered to society is worth being assessed, and this will reflect the caliber of graduands these institutions are producing. As the key to this assessment is to x-ray clear-cut metrics used in the assessment of these institutions of higher learning by regulating authorities, parents, and other stakeholders These institutions' academic deliverables in terms of availability of experienced teachers, modern teaching and learning amenities, open access to learning materials, open access to assessment results, and timely responses to transcripts application to mention just a few needs proper evaluation. A lot of institutions' indices of performance are not encouraging, which translates to a high level of students dropping out, poor student performance, and low productivity which affects the standard of living and overall planned change that education is supposed to bring to the generality of the society at large. We must appreciate the efforts of previous researchers who have spent precious time using various sentiment analysis tools to unveil these challenges facing our education institutions and providing far-reaching measures that will make these institutions improve all indexes of measurement approved by regulating authorities globally as a mark of global competitiveness. Literature reviews by researchers using natural language processing and other machine learning techniques to get students and other stakeholders’ feedback by applying sentiment analysis to improve the quality of teaching and learning in the education sector have yielded the required results. Given the above this research effort aimed at reviewing published papers geared towards improving learners' experiences and enhancing quality assurance in the education system from published articles between 2016 to 2023 in referenced databases from high-impact journals. The research study collated 80 useful articles from the pool of 4595 that were earlier surfed using eligibility criteria which entailed employing exclusion and inclusion characteristics. The outcome of the literature reviews showed that 70% of researchers have used sentiment analysis as feedback and improvement analysis tools in enhancing the student learning experience and quality assurance in the higher education sector. The highly used sentiment analysis algorithms are lexicon-based, Support Vector Machine (SVM), Naïve Bayes(NB), Linear Regression(LR), and Artificial Neural Network(ANN). Keywords: Sentiment Analysis, Education Sector, Supervised Machine Learning Algorithms, social media, Questionnaires, Lexicon-based, Natural Language Processing(NLP) Emughedi Oghu, Emeka Ogbuju, Taiwo Abiodun & Francisca Oladipo.. (2023): Baseline Study of Different Sentiment Analysis Computing Methods to Enhance Quality Assurance In Teaching and Learning. Journal of Advances in Mathematical & Computational Science. Vol. 10, No. 4. Pp 1-20 Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V11N3P1

show abstract

Using Sentiment Analysis to Identify Student Emotional State to Avoid Dropout in E-Learning

Cited by 6 publications

References 39 publications

Análise de sentimentos em turmas de programação com vistas ao apoio à permanência estudantil

Análise de sentimentos em turmas de programação com vistas ao apoio à permanência estudantil

Multifaceted Sentiment Detection System (MSDS) to Avoid Dropout in Virtual Learning Environment using Multi-class Classifiers

Baseline Study of Different Sentiment Analysis Computing Methods to Enhance Quality Assurance In Teaching and Learning

Contact Info

Product

Resources

About