Icssdaf_sentiment Analysis for Evaluating Teaching Effectiveness in Higher Education
i-manager's Journal on Data Science & Big Data Analytics · 20.06.2026 · 4 (1) · 1
DOI: 10.26634/jds.4.1.901 ↗Kurz gefasst
Fachartikel in der Zeitschrift i-manager's Journal on Data Science & Big Data Analytics, online erschienen am 15.06.2026. Verfasst von Zulu Loshangu Ruth. Die Arbeit nennt 16 Literaturangaben.
Abstract (Originalsprache)
Evaluating teaching effectiveness is a critical component of quality assurance in higher education because it creates room for students to provide their insights and feedback concerning their learning experience in higher education. Existing systems often rely on traditional methods, such as end-of-semester surveys and manual reviews, which are typically time-consuming, laborintensive, and susceptible to subjective biases. Delayed feedback, lack of real-time insights, and limited nuance and scalability hinder prompt interventions, making it difficult to capture the detailed aspects of teaching quality and analyze feedback efficiently. Sentiment analysis for evaluating teaching effectiveness in higher education addresses the main challenges of the existing system by offering immediate feedback that supports continuous improvement and a nuanced analysis of feedback datasets that create a platform for higher learning institutions to address issues early and enhance the overall learning experience of students more effectively than traditional methods. The system leverages an automated framework that applies sentiment analysis to the feedback and ratings provided by students. Raw text data were collected and pre-processed through text filtering, a natural language processing technique, before being handed over to the sentiment analyzer that performs text analysis using Naïve Bayes to classify text data and VADER sentiment to generate sentiment scores. An education-focused transformer model, BERT, and its education-specific variants classify sentiment polarity and extract key aspects related to teaching quality, such as clarity, engagement, and course organization. Aggregated sentiment scores are mapped and visualized through interactive dashboards for students and administrators, providing timely and detailed insights into lectures’ performance.
Zitieren
APA
Ruth, Z. L. (2026). Icssdaf_sentiment Analysis for Evaluating Teaching Effectiveness in Higher Education. i-manager's Journal on Data Science & Big Data Analytics, 4(1), 1. https://doi.org/10.26634/jds.4.1.901
Vancouver
Ruth ZL. Icssdaf_sentiment Analysis for Evaluating Teaching Effectiveness in Higher Education. i-manager's Journal on Data Science & Big Data Analytics. 2026;4(1):1. doi:10.26634/jds.4.1.901
BibTeX
@article{Ruth2026,
author = {Ruth, Zulu Loshangu},
title = {Icssdaf_sentiment Analysis for Evaluating Teaching Effectiveness in Higher Education},
journal = {i-manager's Journal on Data Science & Big Data Analytics},
year = {2026},
volume = {4},
number = {1},
pages = {1},
doi = {10.26634/jds.4.1.901}
}
EUVIMED