Using sentiment analysis to evaluate qualitative students’ responses

Abstract

Text analytics in education has evolved to form a critical component of the future SMART campus architecture. Sentiment analysis and qualitative feedback from students is now a crucial application domain of text analytics relevant to institutions. The implementation of sentiment analysis helps understand learners’ appreciation of lessons, which they prefer to express in long texts with little or no restriction. Such expressions depict the learner’s emotions and mood during class engagements. This research deployed four classifiers, including Naïve Bayes (NB), Support Vector Machine (SVM), J48 Decision Tree (DT), and Random Forest (RF), on a qualitative feedback text after a semester-based course session at the University of Education, Winneba. After enough training and testing using the k-fold cross-validation technique, the SVM classification algorithm performed with a superior accuracy of 63.79%.

Sentiment analysis of student feedback using attention-based RNN and transformer embedding

“…GloVe embedding is a technique used to learn word vectors where the objective of the training is to obtain vectors such that the dot product of any two vectors is equivalent to the logarithm of the probability of the two corresponding words appearing together [22]. This association establishes a connection between the logarithmic ratios of co-occurrence probabilities and vector disparities in the word vector space [6], [19]. By leveraging this relationship, GloVe embedding produces vectors that excel at capturing semantic relationships among words.…”

“…Feedback represents the response of end-users, whether online or offline, regarding provided services or their level of satisfaction [4]. SA techniques play a vital role in the development and enhancement of both commercial [5] and educational services [6]. User feedback, whether provided online or offline, reflects their satisfaction with the services received, particularly in the realm of education.…”

Internet of Things (IoT) Applications in Education: Benefits and Implementation Challenges in Ghanaian Tertiary Institutions

“…Sentiment modelling is possible with unstructured data where the tonation behind a text is determined using natural language processing (NLP) (Dake & Gyimah, 2023). Machine learning sentiment detection in an IoT-based environment that generates smart data has become more relevant during the COVID-19 pandemic (Mujahid et al, 2021).…”

A Review of Sentiment Analysis Approaches for Quality Assurance in Teaching and Learning (RETRACTED)

“…Relevant papers were obtained by constructing a search phrase using keywords based on the previously stated research question. Seven (7) common database indexes, Scopus, EBSCOhost, Science Direct, IEEE Xplore, Web Science, SpringerLink, and ACM DL, were used to conduct the searches. The search strings are eleven (11) in total; they are "sentiment analysis", "opinion mining", "technologies used in sentiment analysis", "sentiment analysis framework", "sentiment analysis algorithms", "sentiment analysis tools", "students' feedback", "teacher assessment", "feedback assessment", "learners' feedback sentiment analysis reviews" and "quality assurance".…”