Measuring User Satisfaction of Educational Service Applications using Text Mining and Multicriteria Decision-Making Approach

Abstract

Rapid growth of educational technology services today means that there are more applications in the market. Users may find it hard to choose the most suitable application, so they look for references. Experience shared in the form of text reviews and numerical rating can provide references. Text re-views are particularly specific and so they can provide insights to user satis-faction. In this study, we use text mining and multicriteria decision-making approach to measure the user satisfaction. The data is crawled and collected from seven educational applications: Coursera, edX, Khan Academy, LinkedIn Learning, Quipper, Socratic and Udemy. Nine attributes are used to measure the user reviews according to quality model of e-learning sys-tems. The result is in favor of Khan Academy, while Quipper is ranked the lowest. The v-values used range between 0 and1 and what is unique is that the rank of Khan Academy and Quipper are not affected by v-value while the ranks of the other applications are. It indicates that Khan Academy has high user satisfaction in terms of utility and low complaint from individuals. Quipper shows the opposite.

Real-time Twitter Sentiment Analysis for Moroccan Universities using Machine Learning and Big Data Technologies

“…Numerous studies have shown that Twitter sentiment analysis is more efficient when used in certain domains including healthcare [2][3], banking sector [4], marketing [5][6], tourism [7], and politics [8]. Moreover, sentiment analysis is used in the education field to improve the quality of the educational institution's services [9][10], enhance the learning process by analyzing students' feelings [11] and orientation [12], and extract useful information about the teaching methodology of a teacher. In particular, recent studies have shifted their focus to sentiment analysis to detect the strengths and weaknesses of courses in higher education by analyzing students' online opinions [13] and measuring specific university indicators such as university reputation from social media for constructing a ranking mechanism [14].…”

Text mining and sentiment analysis of teacher performance satisfaction in the virtual learning environment

“…As indicated in [24], the predictive model through sentiment analysis allowed students of the applied basic statistics subject to be motivated and satisfied to use the application of data science during the virtual teaching-learning process. The results obtained show that it is possible to obtain a reference point on student satisfaction using text mining techniques and sentiment analysis, in the same way as indicated in [11] it is possible to perform sentiment analysis in different assessment instruments of student satisfaction allowing an efficient allocation of resources to programs or faculties within educational institutions. for its part, in [23] where the EmotiBlog was evaluated through sentiment analysis, focusing on the automatic detection and classification of sentences with subjective information, the validity of EmotiBlog was demonstrated, suggesting for this reason to apply the developed model.…”

“…Traditionally, the measurement of satisfaction is carried out through surveys. However, in the context of virtualization, it seeks to implement new methods and procedures, taking advantage of the increased use of the Internet and the production of data that it generates [11].…”

Analysis of the Educational Application Users Satisfaction Levels by Using the Integrated Entropy Weight VIKOR Method

“…Since Dina 23 , et al used VIKOR as one of the MCDM techniques during the assessment of user satisfaction, it was then implemented as the comparative baseline against this present analysis. In addition, the EWM was presently assigned before implementing the VIKOR technique, to 0.000 0.000 0.000 0.000 0.006 0.000 0.000 0.000 Table 6.…”

“…From this description, VIKOR is used to investigate and consider ranking processes for the possibilities 21 meeting specific conditions. 15 To assess the quality of mobile apps, [22][23] VIKOR has reportedly been implemented by several reports, such as Dina, 23 et al In this analysis, the decision matrix was modified by counting TF-IDF, to improve ranking output. This indicates that VIKOR is an MCDM method ranking and selecting possibilities from a list criterion.…”