Supervised learning using support vector machine applied to sentiment analysis of teacher performance satisfaction

Abstract

Satisfaction with teaching performance is an important measurement process in higher education institutions, for this reason, applying sentiment analysis to the opinions of university students through the support vector machine (SVM) Fine Gaussian supervised learning algorithm represents an important contribution to the academic literature. This article identifies the best classification algorithm according to performance parameters for predicting student satisfaction with teaching performance through sentiment analysis; the subsequent implementation of the research has the purpose of strengthening teaching practices, in addition to allowing continuous training of teaching for the benefit of student learning. This article has provided a compact predictive model, with literature review based on SVM and sentiment analysis techniques. Through the machine learning classification learner technique, it is identified that the SVM algorithm: Fine Gaussian SVM is the one with the best accuracy equal to 98.3%. Likewise, the performance metrics for the four classes of the model were identified, which have a sensitivity equal to 88.89%, a specificity of 98.04%, a precision of 99.21% and an accuracy of 98.85%.

Student satisfaction in the context of hybrid learning through sentiment analysis

“…So also Puraivan et al [33], applied sentiment analysis on a population made up of first-cycle university students, in the context of a health emergency, through which they managed to characterize four groups, identified by hierarchical clusters, which are characterized by their perception of the COVID-19 context, belonging to said groups is validated through discriminant analysis, in which the first dimension obtained 59.90% of the variability, and the second, 24.80%. Empirical studies such as those carried out by several researchers [36], [37] showed the feasibility of identifying satisfaction in any field, including the university educational field, through comments or opinions extracted from social networks such as Twitter and integrated into sentiment analysis techniques, which show a strategy with application of form crossed in other organizational areas.…”

Factor analysis influencing Mobile JKN user experience using sentiment analysis

“…Sentiment analysis commonly employs machine learning technologies such as support vector machine (SVM) and Naïve Bayes (NB) due to their ability to deliver accurate outcomes with fast processing times while necessitating minimal training data [10]. Several previous studies have conducted sentiment analysis using both classification models to analyze government applications using review data from the Google Play Store [11], in fintech applications using data from Twitter [12], [13], and analyzing the impact of the COVID-19 pandemic using Twitter data [14]- [16]. But in crawling data, class imbalance often occurs.…”

Machine learning prediction of video-based learning with technology acceptance model

“…Unlike prior studies [7]- [10] that employed traditional statistical method, this study attempts to construct video-based learning usage based on students' perception and attitudes to be analyzed with machine learning prediction technique. Previous research that used machine learning for prediction, classification and detection problems in financial, accounting and education domains highlighted the effectiveness and accuracy of such methods to that of traditional statistical methods in problems such as in detection of financial fraud [12], students and teachers' performance [13], [14], firm performance [15] and education technologies adoption [16]- [23]. Despite the wiser used machine learning in accounting and education areas, yet study on machine learning prediction and classification on accounting education is inadequate.…”