MétaCan
Menu
Back to cohort
Record W4392349009 · doi:10.18280/ts.410120

Enhancing Emotion Recognition in College Students' Online Learning: A Research on Integrating Feature Fusion and Attention Mechanisms

2024· article· en· W4392349009 on OpenAlexvenueno aff
Xinlu Sun, Jun Liu, Yubing Qian

Bibliographic record

VenueTraitement du signal · 2024
Typearticle
Languageen
FieldComputer Science
TopicEducational Technology and Pedagogy
Canadian institutionsnot available
Fundersnot available
KeywordsFeature (linguistics)PsychologyFusionOnline learningEmotion recognitionComputer scienceCognitive psychologyArtificial intelligenceMathematics educationMultimediaLinguistics

Abstract

fetched live from OpenAlex

Aiming at key challenges in emotional recognition for college students in online learning, including the lack of experimental data sets, the imperfect emotion classification system, and the poor robustness of emotion recognition algorithms, this paper constructs an emotion recognition model for college students' online learning based on feature fusion and attention mechanism. First, based on face recognition technology, the Convolutional Neural Network (CNN) deep features, Histogram of Oriented Gradients (HOG) texture features, and Scale-Invariant Feature Transform (SIFT) features of images are extracted and fused, because three feature extraction algorithms have different feature extraction capabilities and have certain robustness to changes in image lighting, rotation, scale, and other factors, fusion can make feature vectors more comprehensive and rich in information, thereby improving the accuracy and robustness of detection and recognition; second, a ResNet network is constructed to complete the basic classification of learning expressions and verify the experimental results; In order to enhance the ability of deep learning methods to learn discriminative features from noisy signals and further improve classification accuracy, then, by combining the channel attention mechanism and soft thresholding to improve the ResNet network, a Deep Residual Shrinkage Network (DRSN) is constructed to achieve emotion recognition of college students' online learning; finally, through a horizontal comparison experiment of multiple different network structures, the effectiveness of the soft threshold attention mechanism is verified. This method obtains more complete facial expression features for emotion classification through feature fusion, and combines the channel attention mechanism module. The recognition accuracy of DRSN network is 84.12%, which is about 4.17% higher than the original ResNet network (79.95%). The application of this research can assess the concentration of college students in online learning and measure the degree of emotional engagement of college students. Through the analysis of model result data, teachers can understand the course content that college students are interested in, adjust teaching plans according to the learning status of students, help realize personalized teaching, and consolidate teaching results.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.002
Threshold uncertainty score0.005

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.064
GPT teacher head0.380
Teacher spread0.316 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueTraitement du signalSame topicEducational Technology and PedagogyFrench-language works237,207