Multimodal Emotion Recognition: Emotion Classification Through the Integration of EEG and Facial Expressions
Open accessThe DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index; 10 of the 21 sources its claims cite were checked for support.
Abstract
Despite advances in the field of emotion recognition, the research field still faces two main limitations: the use of deep models for increasingly complex calculations and the identification of emotions through various data types. This study aims to advance the knowledge on multimodal emotion recognition by combining electroencephalography (EEG) signals with facial expressions, using advanced models such as Transformer, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The results validate the effectiveness of this approach, demonstrating the high accuracy of the Gated Recurrent Unit (GRU) model, which achieved an average of 91.8% classification accuracy on unimodal (EEG-only) data and an average of 97.8% classification accuracy on multimodal (EEG and facial expressions) datasets in the multi-class emotion categories. The findings emphasize that by applying a multi-class classification framework, multimodal approaches offer significant improvements over traditional unimodal techniques. This work presents a framework that captures complex neural dynamics and visible emotional cues, enhancing the robustness and accuracy of emotion recognition systems. These results have important practical implications, showing how integrating various data sources with advanced models can overcome the limitations of single-modality systems.
Overview
CoChat Summary
TL;DR
This paper combines EEG signals and facial expressions from the DEAP dataset to classify emotions into four valence–arousal categories, comparing GRU, LSTM, and Transformer models. The GRU model performed best, reaching 91.8% average accuracy on EEG-only data and 97.8% on multimodal EEG plus facial expression data.
Key findings
- The GRU model achieved the highest accuracy in both settings: 91.8% for unimodal EEG-only classification and 97.8% for multimodal EEG plus facial expression classification.
- Multimodal data improved every model: the LSTM reached 96% overall accuracy with multimodal data versus 85% unimodal, and the Transformer reached 84% multimodal versus 69% unimodal.
- The GRU also had the lowest test loss: 0.278 for unimodal EEG and 0.104 for multimodal data, compared with LSTM at 0.45 and 0.179, and Transformer at 0.791 and 0.465.
- The study used four classes—HVHA, HVLA, LVHA, and LVLA—rather than binary valence/arousal classification, and reports that facial expressions plus EEG usually achieve higher emotion recognition performance.
Methods
- The DEAP dataset was used, containing 32-channel EEG recordings and facial expression videos for the first 22 participants; the paper reports 17,360 processed EEG signal samples and 3,000 images per 60-second video at 50 FPS.
- EEG data were segmented into one-second windows, labeled into four classes using valence and arousal thresholds of 5, and split into 70% training, 15% validation, and 15% testing.
- Facial expression analysis used FER with MTCNN and Haar Cascade face detection; missing facial data were filled with synthetic samples, and excess data were downsampled to match EEG sample counts.
- GRU, LSTM, and Transformer models were trained for 330 epochs with a learning rate of 0.0001, using accuracy, precision, recall, F1-score, confusion matrices, and loss curves for evaluation.
Limitations
- The paper states that future research should prioritize larger and more diverse datasets, explore novel deep learning architectures and modality integrations, and use feature extraction to distinguish contrasting emotional states within the same category.
- Evident from the text: facial video data were limited to only 22 participants who consented to recording, and technical issues during recording meant some participants had fewer than the expected 40 videos.
- Evident from the text: synthetic data were generated to fill gaps in facial expression data, and the paper notes fewer HVLA samples in the test data, which may affect class balance and model evaluation.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
7 Valid · 1 Not valid · 6 Not checked · 102 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Huang et al. achieved a prediction accuracy of 74.38% using only EEG data and 66.38% using only facial expression data, both of which are unimodal methods, for the four basic emotional states in the their custom dataset. However, by implementing two different data fusion techniques, they improved these accuracy rates to 81.25% and 82.75%.”
- Also stated in: § 24588 VOLUME 13, 2025 · plain
“The best results were achieved with the DCCA method, yielding average accuracy rates of 91.54% on the DEAP dataset and 93.86%on theMAHNOB-HCI dataset. Using only EEGdata, average accuracy rates of 74.57% and 83.27% were achieved on the DEAP and MAHNOB-HCI datasets, respectively, while using only facial expressions, accuracy rates of 90.5% and 92.4% were obtained on the same datasets, respectively.”
What the sources say
- Partly supportedcites [15] sourceExperimental — accuracy not yet measured
The Discussions section reports that both fusion methods outperformed either unimodal method, with accuracies of 81.25% and 82.75%. But the citing sentence reverses the unimodal results: the paper gives 74.38% for facial expressions and 66.88% for EEG, not 74.38% for EEG and 66.38% for facial expressions. (LLM, conf=0.94)
- Partly supportedcites [16] sourceExperimental — accuracy not yet measured
The Experimental Results (sections 4.2–4.5; page not provided) support the broad point: this paper reports higher accuracy for its EEG–facial fusion model than for either unimodal model. But its comparison with Huang et al. in section 4.5 reports fusion accuracies of 69.75% for valence and 70.00% for arousal; it does not substantiate the citing sentence’s four accuracy figures for Huang. (LLM, conf=0.87)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 24588 VOLUME 13, 2025 · plain
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Using fusion techniques at the feature and decision levels, Zheng et al. [12] showed, for example, that combining EEG and eye movement data could improve emotion recognition performance.”
What the sources say
- Not checked — no full text of the sourcecites [12] source
- Partly supportedcites [15] sourceExperimental — accuracy not yet measured
The Discussion reports that Zheng combined EEG with eye-tracker pupillary responses using both feature-level and decision-level fusion, so the source supports that example of multimodal emotion recognition. It gives fusion accuracies but does not report Zheng’s unimodal results, so it does not establish that Zheng’s approach improved performance over unimodal methods. The paper’s own improvement finding concerns EEG combined with facial expressions, not eye-tracker data. (LLM, conf=0.84)
- Partly supportedcites [16] sourceExperimental — accuracy not yet measured
The Related Work section (2.3; page unavailable) reports that Zheng et al. used EEG and eye movements for emotion recognition, and the Introduction says multimodal methods can outperform unimodal ones. But the cited paper is not Zheng et al.’s study, and our copy does not say that Zheng et al. used both feature-level and decision-level fusion or establish that their method improved performance. (LLM, conf=0.83)
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Overall, the model demonstrated effective performance with 85% accuracy [39].”
What the sources say
- Could not verifycites [39] sourceExperimental — accuracy not yet measured
Section 2.2 defines accuracy as a classification metric, while Section 7 reports an experiment using an SVM on the Iris dataset. Searches for LSTM, EEG, and 85% accuracy found no passage reporting the attributed test-set result. (LLM, conf=0.76)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The proposed study demonstrated a marginally higher performance, achieving an accuracy of 97.80%, compared to Wang et al.'s [23] 96.89% using the DEAP dataset by combining EEG and facial expressions.”
What the sources say
- Partly supportedcites [23] sourceExperimental — accuracy not yet measured
In Experimental results and analysis (Table IV; page unavailable), Wang et al. report DEAP accuracies of 96.63% for valence and 97.15% for arousal using EEG and facial expressions. Their arithmetic mean is 96.89%, but the paper does not report 96.89% as a single accuracy. The citing study’s 97.80% result is not a result attributed to Wang et al. (LLM, conf=0.88)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results validate the effectiveness of this approach, demonstrating the high accuracy of the Gated Recurrent Unit (GRU) model, which achieved an average of 91.8% classification accuracy on unimodal (EEG-only) data and an average of 97.8% classification accuracy on multimodal (EEG and facial expressions) datasets in the multi-class emotion categories.”
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
47 more claims
Create a free account to see all 116 claims and to verify the 1 reference still open.
- Probably not a substantial claim. 35
- It may state two separate claims as one. 37
- The quote only partly states this claim. 8
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ 24592 VOLUME 13, 2025
“Each model was trained for 330 epochs”
§ 24598 VOLUME 13, 2025
“The training accuracy curve reaches almost 92% at the 400th epoch”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 24588 VOLUME 13, 2025
“they obtained a classification accuracy of 97.7% with multimodal data, 93.9% with EEG signals alone, and 91.3% with facial expression features alone.”
§ V. DISCUSSION
“Chaparro et al. [19] and Muhammad et al. [16] achieved accuracies of 97.00% and 93.86%, respectively, using the MAHNOB-HCI dataset combined with EEG and facial expressions.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 24596 VOLUME 13, 2025
“Table 5 presents the classification report of the Trans- former model, revealing precision values of 64% for HVHA, 75% for HVLA, 72% for LVHA, and 74% for LVLA. Recall rates were calculated as 83% for HVLA, 60% for HVHA, 64% for LVHA, and 63% for LVLA. The F1-scores are 72% for HVHA, 67% for HVLA, 67% for LVHA, and 68% for LVLA.”
§ 24594 VOLUME 13, 2025
“The F1-score [38] is the harmonic mean of precision and recall metrics”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 24594 VOLUME 13, 2025
“FIGURE 4. Training performance of the unimodal LSTM model: a) accuracy, b) loss.”
§ 24594 VOLUME 13, 2025
“The accuracy graph in Figure 4a illustrates the performance of the LSTM model on the combined EEG and facial expression training and validation datasets”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 24588 VOLUME 13, 2025
“accuracy rates of 53.9% and 85.1%, respectively, using unimodal methods.”
§ 24588 VOLUME 13, 2025
“By integrating the data, they improved these rates to 91.01% and 83.25%”
1 more finding
Create a free account to see every finding of this check.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
(2014) · Cited by 33,419
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks
Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2603342 · Cited by 6,214
Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
Powers, D. M. W. (2020) · arXiv · doi:10.48550/arxiv.2010.16061 · Cited by 5,440
DEAP: A Database for Emotion Analysis ;Using Physiological Signals
Koelstra, S., Muhl, C., Soleymani, M., Lee, J.-S., Yazdani, A., Ebrahimi, T., Pun, T., Nijholt, A., & Patras, I. (2012) · IEEE Transactions on Affective Computing · doi:10.1109/t-affc.2011.15 · Cited by 5,093
Classification assessment methods
Tharwat, A. (2021) · Applied Computing and Informatics · doi:10.1016/j.aci.2018.08.003 · Cited by 2,417
Gate-variants of Gated Recurrent Unit (GRU) neural networks
Dey, R., & Salem, F. M. (2017) · 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas.2017.8053243 · Cited by 2,186
Prechelt, L. (1998) · Lecture Notes in Computer Science · doi:10.1007/3-540-49430-8_3 · Cited by 1,649
Feature selection, L 1 vs. L 2 regularization, and rotational invariance
Ng, A. Y. (2004) · Twenty-first international conference on Machine learning - ICML '04 · doi:10.1145/1015330.1015435 · Cited by 1,572
ACTIVATION FUNCTIONS IN NEURAL NETWORKS
Sharma, S., Sharma, S., & Athaiya, A. (2020) · International Journal of Engineering Applied Sciences and Technology · doi:10.33564/ijeast.2020.v04i12.054 · Cited by 1,197
The relationship between Recall and Precision
Buckland, M., & Gey, F. (1994) · Journal of the American Society for Information Science · doi:10.1002/(sici)1097-4571(199401)45:1<12::aid-asi2>3.0.co;2-l · Cited by 961
Emotion recognition using multi-modal data and machine learning techniques: A tutorial and review
Zhang, J., Yin, Z., Chen, P., & Nichele, S. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.01.011 · Cited by 806
Houssein, E. H., Hammad, A., & Ali, A. A. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07292-4 · Cited by 426
Emotion Recognition Using Multimodal Deep Learning
Liu, W., Zheng, W.-L., & Lu, B.-L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46672-9_58 · Cited by 301
Multimodal emotion recognition using EEG and eye tracking data
Zheng, W.-L., Dong, B.-N., & Lu, B.-L. (2014) · 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc.2014.6944757 · Cited by 230
Emotion Recognition using Multimodal Residual LSTM Network
Ma, J., Tang, H., Zheng, W.-L., & Lu, B.-L. (2019) · Proceedings of the 27th ACM International Conference on Multimedia · doi:10.1145/3343031.3350871 · Cited by 230 · cited 2×
“Studies by Ma et al. [14] and Huang et al. [15] used EEG with other physiological signals and custom datasets, achieving accuracies of 92.87% and 82.75%, respectively.”
InfluentialCross-Subject Multimodal Emotion Recognition Based on Hybrid Fusion
Cimtay, Y., Ekmekcioglu, E., & Caglar-Ozhan, S. (2020) · IEEE Access · doi:10.1109/access.2020.3023871 · Cited by 200
Leong, S. C., Tang, Y. M., Lai, C. H., & Lee, C. (2023) · Computer Science Review · doi:10.1016/j.cosrev.2023.100545 · Cited by 151
Multimodal Emotion Recognition From EEG Signals and Facial Expressions
Wang, S., Qu, J., Zhang, Y., & Zhang, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3263670 · Cited by 124
Fusion of Facial Expressions and EEG for Multimodal Emotion Recognition
Huang, Y., Yang, J., Liao, P., & Pan, J. (2017) · Computational Intelligence and Neuroscience · doi:10.1155/2017/2107451 · Cited by 115 · cited 2×
“Studies by Ma et al. [14] and Huang et al. [15] used EEG with other physiological signals and custom datasets, achieving accuracies of 92.87% and 82.75%, respectively.”
InfluentialKılıç, B., & Aydın, S. (2022) · Neuroinformatics · doi:10.1007/s12021-022-09579-2 · Cited by 112
A multimodal emotion recognition method based on facial expressions and electroencephalography
Tan, Y., Sun, Z., Duan, F., Solé-Casals, J., & Caiafa, C. F. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103029 · Cited by 88 · cited 1×
“Tan et al. [21] and Cimtay et al. [22] both found that multimodal methods improved accuracy and robustness, especially in situations involving deceptive facial expressions or human-robot interaction systems.”
Huang, W., Wu, W., Lucas, M. V., Huang, H., Wen, Z., & Li, Y. (2021) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2021.3134183 · Cited by 67
Emotion Recognition Using Feature-level Fusion of Facial Expressions and Body Gestures
Keshari, T., & Palaniswamy, S. (2019) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces45898.2019.9002175 · Cited by 67
Wu, D., Zhang, J., & Zhao, Q. (2020) · IEEE Access · doi:10.1109/access.2020.3010311 · Cited by 51 · cited 1×
“The benefits of combining facial expressions with EEG signals were further highlighted by research by Wu et al. [17] and and Rayatdoost et al. [18].”
Dogan, G., & Akbulut, F. P. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09036-4 · Cited by 51
Self-citationAydın, S., & Onbaşı, L. (2024) · Cognitive Neurodynamics · doi:10.1007/s11571-023-09931-5 · Cited by 46 · cited 1×
“Previous studies [10], [11] investigating the relationship between EEG-based graph-theoretical measures and discrete emotional states highlight the potential of EEG signals in distinguishing complex emotional conditions.”
Neural dynamics of emotion and cognition: From trajectories to underlying neural geometry
Pessoa, L. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.08.007 · Cited by 37
Muhammad, F., Hussain, M., & Aboalsamh, H. (2023) · Diagnostics · doi:10.3390/diagnostics13050977 · Cited by 36 · cited 2×
“Chaparro et al. [19] and Muhammad et al. [16] achieved accuracies of 97.00% and 93.86%, respectively, using the MAHNOB-HCI dataset combined with EEG and facial expressions.”
InfluentialMultimodal EEG Emotion Recognition Based on the Attention Recurrent Graph Convolutional Network
Chen, J., Liu, Y., Xue, W., Hu, K., & Lin, W. (2022) · Information · doi:10.3390/info13110550 · Cited by 34
Multimodal Gated Information Fusion for Emotion Recognition from EEG Signals and Facial Behaviors
Rayatdoost, S., Rudrauf, D., & Soleymani, M. (2020) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3382507.3418867 · Cited by 28
Emotion Recognition from EEG and Facial Expressions: a Multimodal Approach
Chaparro, V., Gomez, A., Salgado, A., Quintero, O. L., Lopez, N., & Villa, L. F. (2018) · 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512407 · Cited by 27 · cited 2×
“Chaparro et al. [19] and Muhammad et al. [16] achieved accuracies of 97.00% and 93.86%, respectively, using the MAHNOB-HCI dataset combined with EEG and facial expressions.”
InfluentialBiosignal based emotion-oriented video summarization
Derdıyok, Ş., & Akbulut, F. P. (2023) · Multimedia Systems · doi:10.1007/s00530-023-01071-4 · Cited by 13
Self-citationEVALUATING THE EFFECTS OF THE AUTONOMIC NERVOUS SYSTEM AND SYMPATHETIC ACTIVITY ON EMOTIONAL STATES
Akbulut, F. P. (2022) · İstanbul Ticaret Üniversitesi Fen Bilimleri Dergisi · doi:10.55071/ticaretfbd.1125431 · Cited by 12
Self-citationLuz Junior, J. D. A., & Rodrigues, M. A. F. (2023) · Symposium on Virtual and Augmented Reality · doi:10.1145/3625008.3625014 · Cited by 5
EEG-based multimodal emotion recognition with optimal trained hybrid classifier
Chakravarthy, G. K., Suchithra, M., & Thatavarti, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17489-x · Cited by 4
Untitled work
Srivastava (2014) · doi:10.5555/2627435.2670313
Research works printed but not linked: 1
- 10.5555/3045118.3045167 · doi:10.5555/3045118.3045167
Cited by
Wafa, A. A., Eldefrawi, M. M., & Farhan, M. S. (2025) · Journal Of Big Data · doi:10.1186/s40537-025-01264-w · Cited by 38
EEG-based fusion approaches in multimodal emotion recognition: An in-depth review
Yılmaz, B. H., Yılmaz, Ç. M., & Köse, C. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132235 · Cited by 13
Zhang, X., Zhang, H., & Xu, M. (2026) · AI · doi:10.3390/ai7020063 · Cited by 9
A Novel EEG–ECG Based Fusion Model for Multimodal Emotional Classification
Gornale, S. S., Shivakumara, P., Unki, A., & Moreno‐García, C. F. (2026) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001426590081 · Cited by 2
Ma, Q., Zhang, D., Shen, Z., et al. (2025) · doi:10.1109/prmvai65741.2025.11108463 · Cited by 1
Metadata
- Authors
- Erdem Güler, S., & Patlar Akbulut, F.
- Affiliations
- Department of Computer Engineering, Istanbul Kültür University, İstanbul, Türkiye
- Venue
- IEEE Access
- Published
- 2025
- Volume
- 13
- Pages
- 24587-24603
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4407128417
- Semantic Scholar
- e78c09d000b678cc670f5c90e3e8a274f8988224
- Cited by
- 21
- References
- 40
- Citations by year
- 2026: 11 · 2025: 10
- FWCI
- 21.87
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- multimodal emotion recognition, EEG, facial expressions, emotion classification, gated recurrent unit, LSTM, transformer models, neural dynamics, emotional cues
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.