Author(s)

Jin Lu

Affiliation(s)

Guangdong Key Laboratory of Big Data Intelligence for Vocational Education, Shenzhen Polytechnic University, Shenzhen 518000, Guangdong, China.

Corresponding Author

Jin Lu

ABSTRACT

With the popularity of online education, how to evaluate online teaching quality scientifically and comprehensively has become an urgent problem. Traditional teaching quality evaluation methods often rely on single text data (e.g., student feedback, teacher self-assessment, etc.), which has shortcomings such as strong subjectivity and incomplete information. The multimodal affective state analysis technology can capture multiple affective states of students in the learning process (e.g., facial expression, voice tone, body posture, etc.), thus providing a more comprehensive and objective basis for teaching quality evaluation. This paper proposes an intelligent modern quality evaluation scheme, using multimodal machine learning technology, integrating multidimensional information to comprehensively assess students, and realizing the organic combination of process evaluation, comprehensive ability evaluation and dynamic evaluation. The scheme proposed in this paper can achieve intelligent online teaching evaluation and establish an accurate portrait of teachers and students' learning, and gradually realize trace-free and accompanying teaching evaluation.The experimental results show that the multimodal emotion recognition method for online learning using fused video semantic information in this paper is able to increase the accuracy of emotion recognition by 6% in practical applications. This indicates that the method has great potential in online teaching and can provide teachers with more accurate feedback on students' affective states, so as to better adjust teaching strategies and improve teaching effectiveness.

KEYWORDS

Multimodal emotional analysis; Online teaching quality evaluation; Adaptive teaching system; Video semantic information

CITE THIS PAPER

Jin Lu. Typical cases of online teaching quality evaluation based on multimodal affective state analysis. Trends in Social Sciences and Humanities Research. 2024, 2(9): 1-8. DOI: https://doi.org/10.61784/tsshr3083.

REFERENCES

[1] Shuyan W. Multi-attribute decision-making methods based on Aczel-Alsina power aggregation operators for English blended teaching quality evaluation under single-valued neutrosophic sets. International Journal of Knowledge-based and Intelligent Engineering Systems, 2024, 28(3): 539-552.

[2] Arega B, Mengistu M, Mersha A, et al. Evaluation of hospital quality of care outcomes in a teaching hospital in Ethiopia: a retrospective database study. BMJ open, 2024, 14(9): e082908.

[3] Guo S, Yang X, Farizan H N, et al. The analysis of teaching quality evaluation for the college sports dance by convolutional neural network model and deep learning. Heliyon, 2024, 10(16): e36067-e36067.

[4] Sharma A ,Nishadham V, Gupta P, et al. Evaluation of Turnaround Times of Diagnostic Biopsies: A Metric of Quality in Surgical Pathology. International journal of surgical pathology, 2024, 10668969241261561.

[5] Liu M. A combined exponential TODIM-GRA framework for multiple-attribute group decision-making under 2-tuple linguistic Pythagorean fuzzy sets and applications to art teaching quality evaluation in higher education institutions. Soft Computing, 2024, 28(17-18): 10317-10330.

[6] Ma W, Chu N. Evaluation of online teaching quality in colleges and universities based on digital monitoring technology. Journal of Intelligent Systems, 2024, 33(1).

[7] Camilo S, Edwin M, Jose A. Analysis of different affective state multimodal recognition approaches with missing data-oriented to virtual learning environments. Heliyon, 2021, 7(6): e07253-e07253.

[8] Caridakis G, Karpouzis K, Wallace M, et al. Multimodal user’s affective state analysis in naturalistic interaction. Journal on Multimodal User Interfaces, 2010, 3(1-2): 49-66.

[9] Johnstone E, Liao H M, Strani K. How does it feel? Space and text as affective affordances in the multimodal museum. Multimodality & Society, 2024, 4(3): 314-329.

[10] VillenaGonzalez M. Caresses, whispers and affective faces: A theoretical framework for a multimodal interoceptive mechanism underlying ASMR and affective touch: An evolutionary and developmental perspective for understanding ASMR and affective touch as complementary processes within affiliative interactions. BioEssays, 2023, 45(12): e2300095-e2300095.

[11] Xiaoshuang G. Multimodality in language education: implications of a multimodal affective perspective in foreign language teaching. Frontiers in Psychology, 2023, 141283625-1283625.

[12] Olsen D. Media Arts Education:Transforming Education Through Multimodal Cognition, Holistic Learning, and Techno-Embodiment. Taylor & Francis: 2024-09-25. DOI:10.4324/9781003430834.

[13] Kewalramani S, Aranda G, Sun J, et al. A Systematic Review of the Role of Multimodal Resources for Inclusive STEM Engagement in Early-Childhood Education. Education Sciences, 2024, 14(6): 604-604.

[14] Anne-Marie H, M S M, P T H, et al. Falls After Hospital Discharge: A Randomized Clinical Trial of Individualized Multimodal Falls Prevention Education. The journals of gerontology. Series A, Biological sciences and medical sciences, 2019, 74(9): 1511-1517.

[15] Giannakos N M, Lee-Cultura S, Sharma K. Sensing-Based Analytics in Education: The Rise of Multimodal Data Enabled Learning Systems. IT Professional Magazine, 2021, 23(6): 31-38.