Performance and Feedback Analyzer

2020

Document represents supplementary material of the paper entitled "Opinion Mining in Higher Education: A Corpus-Based Approach" published in Enterprise Information System, special issue The Artificial Intelligence-enabled Enterprise Information Systems. It summarizes statistical and linguistic analysis of annotated corpus in domain of online reviews of higher education. Linguistic and statistical analysis were performed in order to provide an in-depth insight into the structure of the corpus. Our detail observations are given in this document.

WSEAS transactions on information science and applications, 2024

The pandemic has given rise to challenges across different sectors, particularly in educational institutions. The mode of instruction has shifted from in-person to flexible learning, leading to increased stress and concerns for key stakeholders such as teachers, parents, and students. The ongoing spread of diseases has made in-person classes unfeasible. Even if limited face to face classes will be allowed, online teaching is deemed to remain a practice to support instructional delivery to students. Therefore, it is essential to understand the challenges and issues encountered in online teaching, particularly from the perspective of students. This knowledge is crucial for supervisors and administrators, as it provides insights to aid in planning intervention measures. These interventions can support teachers in enhancing their online teaching performance for the benefit of their students. A process that can be applied to achieve this goal is sentiment analysis. In the field of education, one of the applications of sentiment analysis is in the evaluation of faculty teaching performance. It has been a practice in educational institutions to periodically assess their teachers' performance. However, it has not been easy to take into account the students' comments due to the lack of methods for automated text analytics. In line with this, techniques in sentiment analysis are presented in this study. Base models such as Naïve Bayes, Support Vector Machines, Logistic Regression, and Random Forest were explored in experiments and compared to a combination of the four called ensemble. Outcomes indicate that the ensemble of the four outperformed the base models. The utilization of Ngram vectorization in conjunction with ensemble techniques resulted in the highest F1 score compared to Count and TF-IDF methods. Additionally, this approach achieved the highest Cohen's Kappa and Matthews Correlation Coefficient (MCC), along with the lowest Cross-entropy, signifying its preference as the model of choice for sentiment classification. When applied in conjunction with an ensemble, Count vectorization yielded the highest Cohen's Kappa and Matthews Correlation Coefficient (MCC) and the lowest Cross-entropy loss in topic classification. Visualization techniques revealed that 65.4% of student responses were positively classified, while 25.5% were negatively classified. Meanwhile, predictions indicated that 47% of student responses were related to instructional design/delivery, 45.3% described the personality/behavior of teachers, 3.4% focused on the use of technology, 2.9% on content, and 1.5% on student assessment.

International Journal of Innovative Computing

This study investigates the performance of machine learning algorithms for sentiment analysis of students’ opinions on programming assessment. Previous researches show that Support Vector Machines (SVM) performs the best among all techniques, followed by Naïve Bayes (NB) in sentiment analysis. This study proposes a framework for classifying sentiments, as positive or negative using NB algorithm and Lexicon-based approach on small data set. The performance of NB algorithm was evaluated using SVM. NB and SVM conquer the Lexicon-based approach opinion lexicon technique in terms of accuracy in the specific area for which it is trained. The Lexicon-based technique, on the other hand, avoids difficult steps needed to train the classifier. Data was analyzed from 75 first year undergraduate students in School of Computing, Universiti Teknologi Malaysia taking programming subject. The student’s sentiments were gathered based on their opinions for the zero-score policy for unsuccessful compil...

Enterprise Information Systems, 2020

Student recruitment and retention heavily depend on student satisfaction and word of mouth voiced through surveys, social media, and review websites. The amount of online reviews makes their manual analysis intractable, revealing the need for automated approaches. The paper presents the first Serbian language corpus manually annotated for opinions in the domain of higher education. Agreement among annotators was calculated using the Fleiss' kappa and agr metrics. Statistical and linguistic analyses of the corpus revealed information useful for hand-crafted rules for sentiment analysis. Using developed corpus, dictionary-and machine learning-based approaches to sentiment analysis are benchmarked. Both exhibit high performance.

IRJCS:: AM Publications,India, 2024

In education, the importance of gathering and understanding student feedback cannot be over stated. Traditional methods of gathering feedback through surveys and assessments often suffer from limitations such as low response rates and subjectivity. This paper proposes a new approach to improve the feedback collection process by implementing a Student Feedback Mining System using sentiment analysis. The goal of this system is to automatically analyze and extract sentiment from student feedback and provide educators and institutions with valuable insights into students' overall satisfaction and feelings toward various aspects of their academic experience. The system uses natural language processing (NLP) techniques to process unstructured text data, identify sentiments, and categorize feedback into positive, negative, or neutral feelings. Collecting student feedback through various channels such as online surveys, discussion forums and other feedback mechanisms. Cleaning and preprocessing the collected text data to remove noise, irrelevant information and standardize the format for analysis. Using state of the art NLP algorithms and sentiment analysis techniques to determine the emotional tone of feedback. This includes classifying sentiment as positive, negative, or neutral. Grouping feedback based on specific criteria such as course content, teaching methods, facilities and overall learning experience to provide a comprehensive understanding of the various aspects affecting student satisfaction. Presenting analyzed data through intuitive visualizations and reports, making it easy for educators and administrators to interpret and respond to feedback. Creating feedback that enables continuous improvement by providing actionable insights for educators to improve their teaching methods, curriculum and overall learning environment. The proposed system aims to overcome the limitations of traditional feedback collection methods by automating the analysis process, providing real-time insights and supporting a data-driven approach to improving education. Using sentiment analysis, educators and institutions can proactively solve problems, improve the quality of education, and create a more positive and engaging learning environment.

International Journal of Knowledge Society Research, 2016

The aim of this work is to review a specific learning analytics method - sentiment analysis - in the field of Higher Education, showing how it is employed to monitor student satisfaction on different platforms, and to propose an architecture of Sentiment Analysis for Higher Education purposes, which trace and unify what emerges from the literature review. First, a literature review is carried out, which proves the widespread and increasing interest of the communities, of both scholars and practitioners, in the use of sentiment analysis in the field of Higher Education. The analysis, focused on three different e-learning domains, identifies weaknesses and gaps, and in particular the lack of a unifying approach which is able to deal with the different domains. Secondly, a prototype architecture – LADEL (Learning Analytics Dashboard for E-Learning) - is introduced, which is able to deal with the different e-learning domains. Some preliminary experiments are carried out, highlighting so...

5th KES International Conference on Intelligent Decision Technologies, 2013

Educational data mining (EDM) is an important research area that is used to improve education by monitoring students performance and trying to understand the students’ learning. Taking feedback from students at the end of the semester, however, has the disadvantage of not benefiting the students that have already taken the course. To benefit the current students, feedback should be given in real time and addressed in real time. This would enable students and lecturers to address teaching and learning issues in the most beneficial way for the students. Analysing students’ feedback using sentiment analysis techniques can identify the students’ positive or negative feelings, or even more refined emotions, that students have towards the current teaching. Feedback can be collected in a variety of ways, with previous research using student response systems such as clickers, SMS and mobile phones. This paper will discuss how feedback can be collected via social media such as Twitter and how using sentiment analysis on educational data can help improve teaching. The paper also introduces our proposed system Sentiment Analysis for Education (SA-E).

Computer Applications in Engineering Education, 2019

Opinion mining is a fast-developing field of study with numerous applications. It raises economic and political interests, especially in decision-making processes. In this paper, we are interested in educational opinion mining. We propose an educational guidance process that aims to improve university orientation after the secondary school cycle. Unlike the ordinary orientation processes, our process integrates the opinions of pupil, parents, and teachers, collected periodically. These opinions are treated to sort out the studies' domains in a positive polarity order. An orientation score is then calculated based on these opinions, the student's aptitudes and the continuous evaluation marks to guide pupils toward the most favourable discipline. The experimentations conducted on a sample of pupils (300) give a better convergence to the pupils' explicit choices using our proposal with a κ coefficient of 0.71, against 0.29 using only marks.

E-learning is becoming more powerful and popular medium for learning through online. It is very important to identify the opinions of the users of E-learning. E-learning commonly refers to teaching efforts propagated through the use of computers to impart knowledge in a non traditional classroom environment. It is difficult to find the users mind whether they are satisfied with the E-courses. Sentiment analysis helps to find about the users who are visiting the E-learning portals. Sentiment analysis refers to the use of natural language processing text analysis and computational linguistics to identify and extract subjective information in source materials. It aims to determine the attitude of speaker or a writer with respect to some topic or overall contextual polarity of a document. Automated sentiment analysis helps to identify the sentiment of the users from the E-portal pages in which users generally browse on a topic or area they are interested. This information can be used by E-learning system to identify the user's emotional factors and can analyse the user's activity each time. The user's sentiments towards a course can serve feedback for E-learning portals in online learning environment. In the proposed E-learning system the automated sentiment analysis helps to analyse the E-portal visited pages by the user. This helps the developer and educator to know where the learner concentrating on specified areas with any manual work or any feed backs from the user. Here for automated sentiment analysis the Bayesian statistics classification, Naive Bayes classifier is used.

International Journal of Engineering Trends and Technology, 2020

Sentiment analysis (SA) is prevalent now; because it can yield useful insight from high-volume subjects and unstructured data mainly from social media networking sites and micro-blog websites or known as user-generated contents. SA in user-generated contents is difficult due to the informal nature of the communication. The informal nature introduces additional variables and properties that have to be evaluated compared to formal texts, necessitating additional resources spent on annotating the data and training the classifiers. We explore two most common methods in classifying user-generated contents called lexicon-based approach by using VADER Sentiment Analyser and Machine Learning (ML) approaches by using Naïve Bayes and Decision Tree classifiers. Our primary objective is to study the accuracy of the solutions and then apply the best solution to 126 students' feedbacks 126 student feedbacks toward an e-learning environment. The purpose is to extract the sentiment against it to acquire the initial picture of student's perception on the implementation of e-learning; so the effectiveness of its implementation can be improved. The data pre-processed and then analysed using Python as programming tool. The results show VADER outperformed two selected ML classifiers, it can achieve approximately 90% in accuracy. From the results, we conclude that VADER sentiment analyser was doing well and better than ML in SA toward user-generated content. The results on the e-learning environment also suggest further analysis should be done towards this e-learning platform to complete this initial study.