# Longitudinal Affect Assessment on SemEval-2026 Task 2 Subtask 1 (test)

Source: [Longitudinal Affect Assessment on SemEval-2026 Task 2 Subtask 1 (test)](<https://www.sota2.com/research/sota/longitudinal-affect-assessment-on-semeval-2026-task-2-subtask-1-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-24T08:23:49.353Z

Evaluation of Longitudinal Affect Assessment performance on the test split of the SemEval Task 2 Subtask 1 dataset, measured using correlation (r) and Mean Absolute Error (MAE) for Valence and Arousal dimensions.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Longitudinal Affect Assessment |
| Dataset (including any stated split) | SemEval-2026 Task 2 Subtask 1 (test) |
| Metric | Valence Correlation (r) composite |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Valence Correlation (r) composite](<https://www.sota2.com/research/sota/longitudinal-affect-assessment-on-semeval-2026-task-2-subtask-1-test.md?metric=Valence%20Correlation%20(r)%20composite>): Higher is better; unit: SCALAR.

- [Valence MAE composite](<https://www.sota2.com/research/sota/longitudinal-affect-assessment-on-semeval-2026-task-2-subtask-1-test.md?metric=Valence%20MAE%20composite>): Lower is better; unit: SCALAR.

- [Arousal Correlation (r) composite](<https://www.sota2.com/research/sota/longitudinal-affect-assessment-on-semeval-2026-task-2-subtask-1-test.md?metric=Arousal%20Correlation%20(r)%20composite>): Higher is better; unit: SCALAR.

- [Arousal MAE composite](<https://www.sota2.com/research/sota/longitudinal-affect-assessment-on-semeval-2026-task-2-subtask-1-test.md?metric=Arousal%20MAE%20composite>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Valence Correlation (r) composite | Result date | Report paper |
| --- | --- | --- | --- |
| submission | 0.667 | Not recorded | 69eaf93455a3c32af89f8a9f |
| Ising | 0.589 | Not recorded | 69eaf93455a3c32af89f8a9f |
| linear(BERT) | 0.557 | Not recorded | 69eaf93455a3c32af89f8a9f |

### submission

Valence Correlation (r) composite: 0.667. Result ID: 69eb288247f34ce924d35e3f.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93455a3c32af89f8a9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69eaf93455a3c32af89f8a9f.md>)

Recorded evaluation configuration: {"Approach":"LLM-based","Backbone":"GPT-5"}. This record does not assert independent reproduction.

### Ising

Valence Correlation (r) composite: 0.589. Result ID: 69eb288247f34ce924d35e40.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93455a3c32af89f8a9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69eaf93455a3c32af89f8a9f.md>)

Recorded evaluation configuration: {"Approach":"MaxEnt"}. This record does not assert independent reproduction.

### linear(BERT)

Valence Correlation (r) composite: 0.557. Result ID: 69eb288247f34ce924d35e41.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93455a3c32af89f8a9f.md>)

Recorded evaluation configuration: {"Approach":"Baseline"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
