Article: Big data-driven deep mining of online teaching assessment data under affective factor conditions Journal: International Journal of Information and Communication Technology (IJICT) 2024 Vol.25 No.11 pp.35 - 51 Abstract: As online education platforms continue to expand, the effective assessment of teaching quality has become increasingly important. This paper examines the role of emotional factors in evaluating teaching quality within online education and proposes a deep mining approach grounded in big data. We introduce the EduSent-Dig model, which integrates Bi-LSTM and Word2Vec techniques to extract and analyse sentiment-related factors from online assessment data. The model exhibited robust performance on diverse datasets, as indicated by its correct rate, sensitivity, and the F1 metric. Although there are limitations, including dataset bias and model complexity, future research will aim to enhance the model's capabilities in multilingual processing, optimise real-time data analysis, and simplify its structure to improve its overall applicability and effectiveness in enhancing the online education experience. Inderscience Publishers - linking academia, business and industry through research

Title: Big data-driven deep mining of online teaching assessment data under affective factor conditions

Authors: Ruiting Bai

Addresses: Puyang Medical College, Puyang 457000, China

Abstract: As online education platforms continue to expand, the effective assessment of teaching quality has become increasingly important. This paper examines the role of emotional factors in evaluating teaching quality within online education and proposes a deep mining approach grounded in big data. We introduce the EduSent-Dig model, which integrates Bi-LSTM and Word2Vec techniques to extract and analyse sentiment-related factors from online assessment data. The model exhibited robust performance on diverse datasets, as indicated by its correct rate, sensitivity, and the F1 metric. Although there are limitations, including dataset bias and model complexity, future research will aim to enhance the model's capabilities in multilingual processing, optimise real-time data analysis, and simplify its structure to improve its overall applicability and effectiveness in enhancing the online education experience.

Keywords: affective factors; big data; online teaching assessment; deep mining.

DOI: 10.1504/IJICT.2024.143412

International Journal of Information and Communication Technology, 2024 Vol.25 No.11, pp.35 - 51

Received: 16 Oct 2024
Accepted: 01 Nov 2024
Published online: 18 Dec 2024 *

Title: Big data-driven deep mining of online teaching assessment data under affective factor conditions

Keep up-to-date