Sentiment analysis for formative assessment in higher education: a systematic literature review

Abstract

Sentiment Analysis (SA), a technique based on applying artificial intelligence to analyze textual data in natural language, can help to characterize interactions between students and teachers and improve learning through timely, personalized feedback, but its use in education is still scarce. This systematic literature review explores how SA has been applied for learning assessment in online and hybrid learning contexts in higher education. Findings from this review show that there is a growing field of research on SA, although most of the papers are written from a technical perspective and published in journals related to digital technologies. Even though there are solutions involving different SA techniques that can help predicting learning performance, enhancing feedback and giving teachers visual tools, its educational applications and usability are still limited. The analysis evidence that the inclusion of variables that can affect participants’ different sentiment expression, such as gender or cultural context, remains understudied and should need to be considered in future developments.

Analysis of social metrics on scientific production in the field of emotion-aware education through artificial intelligence

“…If we break down the social impact of studies based on their social source, the 10 research papers that had the greatest impact on Twitter (tweets or retweets) were “Emotional AI and EdTech: serving the public good?” ( McStay, 2020 ) with 86 records, “Deploying a robotic positive psychology coach to improve college students’ psychological well-being” with 22 records ( Jeong et al, 2023 ), “Sentiment analysis for formative assessment in higher education: a systematic literature review” with 14 records ( Grimalt-Álvaro and Usart, 2023 ), “Towards AI-powered personalization in MOOC learning” with 14 records ( Yu et al, 2017 ), “Predicting regulatory activities for socially shared regulation to optimize collaborative learning” with 13 records ( Järvelä et al, 2023 ), “Engagement detection in online learning: a review” with 12 records ( Dewan et al, 2019 ), “Artificial intelligence in early childhood education: A scoping review” with 12 records ( Su and Yang, 2022 ), “Humanoid Robots as Teachers and a Proposed Code of Practice” with 9 records ( Newton and Newton, 2019 ), “Sentiment Analysis of Students’ Feedback with NLP and Deep Learning: A Systematic Mapping Study” with 8 records ( Kastrati et al, 2021 ), and “Deep Learning-Based Cost-Effective and Responsive Robot for Autism Treatment” with 8 records ( Singh et al, 2023 ).…”

Virtual Voices, Real Insights: Sentiment and Topic Analysis of Discussions about Educational Dropout in YouTube comments

“…Other studies show how topic modeling can support student counselling via course recommendations or identification of students at risk [23,24]. Students' satisfaction or learning difficulties can be monitored based on evaluations of online courses [17,25].…”

Rethinking assessment in the digital era: Designing a pilot study on hybridization in higher education

“…Teachers can use this information to make timely and appropriate adjustments to their teaching methods, thus enhancing the overall quality of the learning process. Simultaneously, students can engage in self-reflection (Grimalt-Álvaro & Usart, 2023).…”