Cross-modality fusion with EEG and text for enhanced emotion detection in English writing
Jing Wang, Ci Zhang · 2025
Read Cross-modality fusion with EEG and text for enhanced emotion detection in English writing by Jing Wang, Ci Zhang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11782560.txt.
Description
Wang and Zhang propose a model that fuses brain signals with text to detect emotion in writing in twenty twenty-five. Text only methods can miss subtle emotional cues in English writing. Brain signals from EEG sensors may add a richer view of feeling. The team built a transformer model that reads both inputs at once.
EEG data are first cleaned and turned into features that complement text embeddings. Both streams are fused inside one transformer framework. That design captures context in the text and emotional state in the signals together. In experiments, the fused model beat text only and EEG only models. Gains appeared in both accuracy and F1 score across emotion categories. The authors see promise for human computer interaction and personalized content systems.
Catalog record
| CREATOR | Jing Wang, Ci Zhang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |