Sentiment Analysis to Evaluate Teaching Performance

Abstract

Feedback Evaluation is a necessary part of any institute to maintain and monitor the academic quality of the system. Traditionally, a questionnaire based system is used to evaluate the performance of teachers of an institute. Here, we propose an automatic evaluation system based on sentiment analysis, which shall be more versatile and meaningful than existing system. In our proposed system, feedback is collected in the form of running text and sentiment analysis is performed to identify important aspects along with the orientations using supervised and semi supervised machine learning technique

Internal Medicine Clerkship ID Curriculum Flip: Will They Prefer to Pre-learn?

“…The technique classifies text sentiment on a numeric-continuous scale by matching individual words to those found in previously validated, positive and negative world lists [ 12 – 14 ]. Prior applications include satisfaction in online discussion boards, evaluating teachers, and comparing tweets about health care [ 15 – 17 ]. The R package “sentimentr” was used to analyze comments ( N = 147).…”

Sentiment analysis on massive open online course evaluations: A text mining and deep learning approach

“…In the classification phase, Naïve Bayes algorithm, support vector machines, maximum entropy classifier, and random forest algorithm have been utilized. In another study, Adinolfi et al [3] presented a sentiment analysis framework to examine student satisfaction on different platforms, such as massive open online courses, learning diaries, and Twitter. In the presented scheme, the students' and teachers' behaviors have been also modeled.…”

Lexical based automated teaching evaluation via students’ short reviews

“…At present, a few of the students’ sentiment texts analyzing research concentrated on online education, which focused most of their attention on system design [4,31]. Adinolfi et al conducted emotional analysis on the online platform. They focused on proposing an architecture of sentiment analysis for higher education purposes and showing how it is employed to monitor student satisfaction on different online platforms.…”

“…We found that negative evaluations are more evidence-based to support their viewpoints than positive ones, which help to further teacher modeling researches. Compared with the previous research, the main contribution of this paper are described as follows: (1) In knowledge-based approach, we used the word co-occurrence method and word-embedding similarity method to automatically build and expand the universal sentiment dictionary. Accordingly, the accuracy of the sentiment analysis at the domain of teacher evaluation is improved; (2) A variety of machine learning models and multi-lexical features were used, and finally obtain a machine learning model with 12.11% higher accuracy than using general sentiment lexicon; and (3) The textual characteristics of student reviews are analyzed.…”

“…Automatic calculating the emotional polarity of student assessment text to teachers makes teacher evaluation module more objective and reduce the process workload. In practical applications, the calculation of emotion often depends on the universal emotion model . Furthermore, to summarize, there is currently neither a widely accepted sentiment analysis approach, nor customized practical applications on the subject of student review to the best of our knowledge.…”