Exploring Technology-Enhanced Learning Key Terms using TF-IDF Weighting

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Technology-enhanced learning (TEL) covers a broad spectrum of discussion. Having a holistic viewpoint and use it to augment TEL is a challenge. We need extensive literature reviews requiring coverage of as many articles as possible discussing TEL. Accordingly, we may look for the key terms with discriminant power to explain this topic. This study processed 40 TEL articles, published no earlier than 2010, taken from IEEE Xplore research database. In previous work, we applied Luhn's significant words as a qualitative approach. However, the reliability of subjective justification become an issue. This study answers the issue by applying term frequency-inverse document frequency (TF-IDF) weight, to find the key terms. This research produces 23 key terms from 685 TF-IDF important words compared to 381 significant words. The finding indicates that some of the significant words also appear in the highest TF-IDF weight cluster. Further analysis could be done using other research databases for more articles.

Original languageEnglish
Title of host publicationProceedings of 2019 4th International Conference on Informatics and Computing, ICIC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728122076
DOIs
Publication statusPublished - Oct 2019
Event4th International Conference on Informatics and Computing, ICIC 2019 - Semarang, Indonesia
Duration: 23 Oct 201924 Oct 2019

Publication series

NameProceedings of 2019 4th International Conference on Informatics and Computing, ICIC 2019

Conference

Conference4th International Conference on Informatics and Computing, ICIC 2019
Country/TerritoryIndonesia
CitySemarang
Period23/10/1924/10/19

Keywords

  • key terms
  • technology-enhanced learning
  • tf-idf

Fingerprint

Dive into the research topics of 'Exploring Technology-Enhanced Learning Key Terms using TF-IDF Weighting'. Together they form a unique fingerprint.

Cite this