Fig 1 - uploaded by Ramón Zatarain Cabada
Content may be subject to copyright.
Context in source publication
Context 1
... idea behind Sentiment Text Recognition module is to take the students opinions about the system programming exercises, and then, the module will be made Sentiment Analysis to determine if the exercise's polarity is positive (like) or negative (not like). With this information, the course administrators and teachers will be able to evaluate the student's opinion and determine the programming exercises quality and then, they will be able to know how to improve the programming exercises based on student's opinion. Fig. 1 shows the idea about how to work Sentiment Analysis in Java Sensei. ...
Similar publications
Abstract. Most systems that recognize emotions that are used in learning systems are oriented towards the detection of basic emotions such as happy, sad or angry.
However, an intelligent tutor system must be able to detect, in a student, secondary emotions that have to do with learning as boring or frustrated. In the case of sentiment analysis in t...
![Fig. 1. Multidisciplinary nature of intelligent tutoring systems [2].](profile/Ramon-Toala/publication/334266547/figure/fig1/AS:1010319145054214@1617890263810/Multidisciplinary-nature-of-intelligent-tutoring-systems-2_Q320.jpg)
![Fig. 3. Generic Architecture of ITS [10].](profile/Ramon-Toala/publication/334266547/figure/fig3/AS:1010319149244416@1617890264074/Generic-Architecture-of-ITS-10_Q320.jpg)
![Fig. 4. System's Framework [23].](profile/Ramon-Toala/publication/334266547/figure/fig4/AS:1010319149264898@1617890264545/Systems-Framework-23_Q320.jpg)
Citations
... Unfortunately, the niche has been struggling to tackle many issues in the past decades. The recent discovery has shown a strong correlation between emotions and learning [11], currently, this has been the focus. Although there are existing services like ASSISTments [38] that show potential, it's not innovative compared to other subdomains. ...
Predicting student performance has attracted significant research interest in recent years, owing primarily to its potential benefits to both students, in terms of improving outcomes and post-graduation prospects, and educational institutions, in terms of addressing issues such as differential attainment and targeted proactive support of students at risk of lower performance. Substantial research effort has been devoted to exploring data analysis and machine learning techniques in this context. One of the main challenges is the availability of large and high-quality datasets and associated issues such as data imbalance and limited scope of data analysis. Additionally, most researchers focus on predicting performance in the form of a single predicted score, as opposed to a range of potential outcomes.
In this thesis, the aforementioned research gaps are addressed through a computational framework to predict student performance ranges using data analysis and machine learning. The framework contains a unique combination of layers ranging from data pre-processing to statistical analysis and learning prediction models, with each layer carefully positioned to avoid any biased outcomes. This increases confidence in the produced outcomes.
The proposed framework is validated using a rich, anonymised dataset provided by the University of Huddersfield that contains significantly more samples and relevant variables than what is commonly observed in the literature. Experiments focus on predicting the performance of students based on data available at the point of enrolment. This includes students that are completing their pre-qualifications for entrance (e.g. A Levels) and allows exploring the widest possible group of students available in the dataset. The predictions produced from the conducted experiments represent a range of overall grade achievement (boundaries) at the end of their course.
Results show an accuracy of 84%/86% (worst/common case scenario). Baseline comparison shows an improvement of 3%/5% (worst/common case scenario) compared to existing literature. In most cases, improvement is seen in both the best and the worst performing models. This robustness of the framework can be partly attributed to including means of tackling data imbalance, as well as exploring a wide range of data analysis and machine learning models.
The main contributions of this thesis and the included framework involve: predicting students' performance in the form of a range; integrating approaches to tackle imbalanced data; performing in-depth data analysis using a range of statistical methods; and considering both supervised and unsupervised learning algorithms. It is envisioned that the framework can be integrated into existing student performance dashboard systems, allowing academics and administrators to harness its predictive capabilities and drive decision-making to improve outcomes across the student body or targeted efforts, such as reducing differential attainment.
... This can happen in any kind of human activity such as learning online [13]. Recently, researchers have acknowledged the role of emotions in online learning in improving learning outcomes and enhancing students' experience [14][15][16]. The significance of incorporating emotional states with the learning process has necessitated the development of ATSs, which is the extended research of ITSs and with the ability to adapt to the learner's adverse emotion effectively to spark the learner's motivation to learn [17]. ...
Education is the key to achieving sustainable development goals in the future, and quality education is the basis for improving the quality of human life and achieving sustainable development. In addition to quality education, emotions are an important factor to knowledge acquisition and skill training. Affective computing makes computers more humane and intelligent, and good emotional performance can create successful learning. In this study, affective computing is combined with an intelligent tutoring system to achieve relevant and effective learning results through affective intelligent learning. The system aims to change negative emotions into positive ones of learning to improve students’ interest in learning. With a total of 30 participants, this study adopts quantitative research design to explore the learning situations. We adopt the System Usability Scale (SUS) to evaluate overall availability of the system and use the Scan Path to explore if the subject stays longer in learning the course. This study found that both availability and satisfaction of affective tutoring system are high. The emotional feedback mechanism of the system can help users in transforming negative emotions into positive ones. In addition, the system is able to increase the learning duration the user spends on learning the course as well.
... Furthermore, Barron Estrada from Mexico developed ITS to present the sentiment analysis module's implementation and analyze student feedback using a sentiment analysis approach. In addition, the ITS application built can be used by teachers or tutors to improve teaching materials based on the results of sentiment analysis assessments from student feedback in the form of unstructured data [18]. In addition, another application in ITS for learning in computer science is the construction of ITS by Al-Rekhawi for independent learning of making android applications for students at a university in Gaza City, Palestine. ...
Indonesia has so many local cultures and languages that spread from Sabang to Merauke, and most Indonesians do not know how to speak two or more regional languages in Indonesia. Most Indonesians only know familiar tribes that are only commonly heard. Because of this problem, governments in the Indonesian provinces have included lessons on Indonesian culture. The lesson will explain Indonesia's national and local culture for their area. In this way, the government can also help Indonesians learn more about their local language. This paper proposes a solution to create a learning portal website for users, both from Indonesia and other countries, to learn Indonesian culture and regional languages. In this way, the author hopes that users can learn about Indonesian local culture and language and contribute to preserving Indonesian local culture and language. This application was built on a web-based basis by applying the following HTML, CSS, and javascript using Personal Home Pages (PHP) for database connection using MySQL. The built application was designed using a use case diagram and class diagram to describe the database relations.
... Further implementations of sentiment analysis with an affective intelligent tutoring system that analyzes students' feedback and provides information to the instructor to improve the teaching quality. At the end of an exercise, the system enquires about the student's opinion about the course and sends feedback to the teacher [30]. Another study [31] focused on the extraction of emotional knowledge of students' fora. ...
The Covid-19 emergency has brought a mandatory shift to online systems in the education sector worldwide. This document gives an overview about the online teaching challenges encountered from the teachers’ point view, restitutes how the teacher’s role in online settings can be determining in the successfulness of the learning experience and more importantly provides insights into Artificial Intelli-gence techniques that can solve the equation of transferring the role of teachers in face-to-face settings to distance learning environments.
... In the system proposed in a work [18], in addition to emotion recognition from the face, a module called "Semantic Clues Emotion Voting" was used to detect the learner's affective state based on a glossary of keywords that students use in the classroom, and ultimately the content was modified based on a combination of the results of the two methods. A person's affective state can be estimated not only from the face but also through the method called sentiment analysis [19], [20] and the analysis of biometric information [21]. In a study [20], comments and feedbacks of a group of learners in an exam were analyzed and classified into two categories of positive and negative sentiments and the results were used to evaluate the quality of exercises and design better exams. ...
... A person's affective state can be estimated not only from the face but also through the method called sentiment analysis [19], [20] and the analysis of biometric information [21]. In a study [20], comments and feedbacks of a group of learners in an exam were analyzed and classified into two categories of positive and negative sentiments and the results were used to evaluate the quality of exercises and design better exams. In the system proposed in a study [19], the learning process continues if the learner's emotion was assessed to be positive. ...
In recent years, the main problem in e-learning has shifted from analyzing content to personalization of learning environment by Intelligence Tutoring Systems (ITSs). Therefore, by designing personalized teaching models, learners are able to have a successful and satisfying experience in achieving their learning goals. Affective Tutoring Systems (ATSs) are some kinds of ITS that can recognize and respond to affective states of learner. In this study, we designed, implemented, and evaluated a system to personalize the learning environment based on the facial emotions recognition, head pose estimation, and cognitive style of learners. First, a unit called Intelligent Analyzer (AI) created which was responsible for recognizing facial expression and head angles of learners. Next, the ATS was built which mainly made of two units: ITS, IA. Results indicated that with the ATS, participants needed less efforts to pass the tests. In other words, we observed when the IA unit was activated, learners could pass the final tests in fewer attempts than those for whom the IA unit was deactivated. Additionally, they showed an improvement in terms of the mean passing score and academic satisfaction.
... Considering a direct correlation between emotions and learning [40] recently, ITS have also started focusing on emotional state of students while learning to offer a more contextualized learning experience [24]. ...
In the past few decades, technology has completely transformed the world around us. Indeed, experts believe that the next big digital transformation in how we live, communicate, work, trade and learn will be driven by Artificial Intelligence (AI) [83]. This paper presents a high-level industrial and academic overview of AI in Education (AIEd). It presents the focus of latest research in AIEd on reducing teachers’ workload, contextualized learning for students, revolutionizing assessments and developments in intelligent tutoring systems. It also discusses the ethical dimension of AIEd and the potential impact of the Covid-19 pandemic on the future of AIEd’s research and practice. The intended readership of this article is policy makers and institutional leaders who are looking for an introductory state of play in AIEd.
... On the other hand, Barron-Estrada et al. (2017) proposed the use of sentiment analysis to improve the performance of an affective intelligent tutoring system by better gauging the opinions of students about the course contents. To that end, the authors used a collection of texts containing more than 68,000 Twitter messages written in Spanish and transformed them into numerical feature vectors along with their associated sentiment. ...
The emergence and continued reliance on the Internet and related technologies has resulted in the generation of large amounts of data that can be made available for analyses. However, humans do not possess the cognitive capabilities to understand such large amounts of data. Machine learning (ML) provides a mechanism for humans to process large amounts of data, gain insights about the behavior of the data, and make more informed decision based on the resulting analysis. ML has applications in various fields. This review focuses on some of the fields and applications such as education, healthcare, network security, banking and finance, and social media. Within these fields, there are multiple unique challenges that exist. However, ML can provide solutions to these challenges, as well as create further research opportunities. Accordingly, this work surveys some of the challenges facing the aforementioned fields and presents some of the previous literature works that tackled them. Moreover, it suggests several research opportunities that benefit from the use of ML to address these challenges.
... Social media, blogs, and forums [12,35,37,38,52,57,59,63,64,68,77,80,81,87,89,93] This category of datasets consists of data collected from online social networking and micro-blogging sites, discussion forums etc. such as Facebook and Twitter ...
In the last decade, sentiment analysis has been widely applied in many domains, including business, social networks and education. Particularly in the education domain, where dealing with and processing students’ opinions is a complicated task due to the nature of the language used by students and the large volume of information, the application of sentiment analysis is growing yet remains challenging. Several literature reviews reveal the state of the application of sentiment analysis in this domain from different perspectives and contexts. However, the body of literature is lacking a review that systematically classifies the research and results of the application of natural language processing (NLP), deep learning (DL), and machine learning (ML) solutions for sentiment analysis in the education domain. In this article, we present the results of a systematic mapping study to structure the published information available. We used a stepwise PRISMA framework to guide the search process and searched for studies conducted between 2015 and 2020 in the electronic research databases of the scientific literature. We identified 92 relevant studies out of 612 that were initially found on the sentiment analysis of students’ feedback in learning platform environments. The mapping results showed that, despite the identified challenges, the field is rapidly growing, especially regarding the application of DL, which is the most recent trend. We identified various aspects that need to be considered in order to contribute to the maturity of research and development in the field. Among these aspects, we highlighted the need of having structured datasets, standardized solutions and increased focus on emotional expression and detection.
... On the other hand, Barron-Estrada et al. (2017) proposed the use of sentiment analysis to improve the performance of an affective intelligent tutoring system by better gauging the opinions of students about the course contents. To that end, the authors used a collection of texts containing more than 68,000 Twitter messages written in Spanish and transformed them into numerical feature vectors along with their associated sentiment. ...
... -Consider more features such as phonemic and history-based features as well as investigate their impact on the performance of the developed model. NB was used to predict the sentiment of text messages to be used to improve an affective intelligent tutoring system (Barron-Estrada et al., 2017) -Study the performance of other classifiers such as NN and SVM to determine whether the classifiers previously proposed in the literature are biased. ...
The emergence and continued reliance on the Internet and related technologies has resulted in the generation of large amounts of data that can be made available for analyses. However, humans do not possess the cognitive capabilities to understand such large amounts of data. Machine learning (ML) provides a mechanism for humans to process large amounts of data, gain insights about the behavior of the data, and make more informed decision based on the resulting analysis. ML has applications in various fields. This review focuses on some of the fields and applications such as education, healthcare, network security, banking and finance, and social media. Within these fields, there are multiple unique challenges that exist. However, ML can provide solutions to these challenges, as well as create further research opportunities. Accordingly, this work surveys some of the challenges facing the aforementioned fields and presents some of the previous literature works that tackled them. Moreover, it suggests several research opportunities that benefit from the use of ML to address these challenges.
... No contexto de educação, a aplicação de análise de sentimento, permitem entender a partir do feedback dos estudantes, por exemplo, que determinado conteúdo em uma plataforma de e-learning não é adequado ou precisa de melhorias [24]. Pode servir também para, a partir da opinião dos alunos sobre as aulas, facilitar a compreensão das necessidades dos alunos pelos professores, para que estes adequem suas aulas presenciais [8] Em alguns trabalhos [24,25] foram realizadas a análise de sentimento integrado a um sistema tutor com foco no ensino de programação, porém estes trabalhos foram voltados para textos em espanhol. ...
... No contexto de educação, a aplicação de análise de sentimento, permitem entender a partir do feedback dos estudantes, por exemplo, que determinado conteúdo em uma plataforma de e-learning não é adequado ou precisa de melhorias [24]. Pode servir também para, a partir da opinião dos alunos sobre as aulas, facilitar a compreensão das necessidades dos alunos pelos professores, para que estes adequem suas aulas presenciais [8] Em alguns trabalhos [24,25] foram realizadas a análise de sentimento integrado a um sistema tutor com foco no ensino de programação, porém estes trabalhos foram voltados para textos em espanhol. ...
... Algumas das abordagens para a tarefa de análise de sentimento são a aprendizagem de máquina, baseada em léxico e abordagem híbrida [23,24]. A abordagem utilizada no modelo proposto é a abordagem híbrida, conforme descrito na seção 4.5. ...
The massive amount of information currently available on the Internetmakes it difficult for teachers to curate quality educationalcontent or to select material for self-regulated study by students.Aiming to facilitate these steps in the teaching and/or learningprocess this article presents an approach to assist the discovery ofeducational content from the hybrid recommendation system andlater classification from the feedback evaluation with sentimentanalysis techniques trained with the Re-Li corpus. This paper describesthe proposed model, the implementation of a prototype andits application in non-formal training involving 13 participants.
