Haxxsh/AffectDynamics-SemEval2026Task2

AffectDynamics (Team AGI)-Longitudinal Affect Prediction Model

AffectDynamics is a temporal affect modeling system developed for SemEval-2026 Task 2: Predicting Variation in Emotional Valence and Arousal over Time from Ecological Essays.

The model predicts emotional valence and arousal from longitudinal text written by users across time. It combines transformer-based text encoding with temporal modeling and user-level conditioning to capture both stable emotional baselines and dynamic emotional changes.

Model Details

Model name: AffectDynamics-SemEval2026Task2 Developer: Harsh Rathva Institution: Sardar Vallabhbhai National Institute of Technology (SVNIT), Surat Email: u24ai036@aid.svnit.ac.in

Architecture

The system consists of four main components:

1. Text Encoder

• —RoBERTa-Large transformer encoder
• —Produces contextual embeddings for each text input.

Different pooling strategies are used depending on text type:

• —Essays → CLS / pooler representation
• —Feeling word lists → mean pooled token embeddings

2. Temporal Encoder

• —Unidirectional GRU
• —Models longitudinal emotional dynamics across user timelines
• —Ensures causal temporal modeling (no future information leakage)

3. User Conditioning

• —Gated user embedding
• —Uses user statistics such as:
• —number of samples
• —timeline length
• —emotional entropy

This allows interpolation between user-specific and global representations.

4. Prediction Heads

Training Data

The model was trained using the official SemEval-2026 Task 2 dataset.

Dataset statistics

• —Total texts: 5,285
• —Training texts: 2,764
• —Users: 182 total (137 training users)
• —Time span: 2021–2024

Each entry contains:

The texts were written by U.S. service-industry workers describing their emotional state.

Training Details

Optimization

• —Optimizer: AdamW
• —Scheduler: OneCycleLR
• —Batch size: 4
• —Training epochs: 10

Learning Rates

Loss Functions

Evaluation Results

Official evaluation results from SemEval-2026 Task 2:

The model demonstrates strong performance on absolute affect prediction, but exhibits limitations in change detection tasks, highlighting a trade-off between temporal stability and sensitivity to emotional transitions.

Intended Use

This model is intended for research purposes, including:

• —longitudinal affect modeling
• —emotion prediction from text
• —temporal NLP modeling
• —ecological momentary assessment analysis

Limitations

1. 1.Stability bias
2. 2.Temporal modeling smooths predictions and reduces sensitivity to abrupt changes.

1. 1.Dataset domain
2. 2.Data originates from a specific population (U.S. service-industry workers).

1. 1.Limited users
2. 2.Only 137 users in training data.

1. 1.Change prediction difficulty
2. 2.Predicting emotional deltas is harder than predicting absolute states.

Ethical Considerations

Emotion prediction models must be used responsibly.

Potential concerns include:

• —privacy risks from modeling personal emotional data
• —misuse for manipulation or surveillance
• —dataset demographic bias

This model should not be used for clinical or psychological diagnosis.

Reproducibility

Code and training pipeline:

https://github.com/ezylopx5/AffectDynamics-SemEval2026Task2

Model weights:

https://huggingface.co/Haxxsh/AffectDynamics-SemEval2026Task2

Citation

Please cite the following paper if you use this model in your work:

@inproceedings{rathva-2026-agi,
  author = {Harsh Rathva},
  title = {{AGI} Team at {S}em{E}val-2026 Task 2: Predicting Variation in Emotional Valence and Arousal over Time from Ecological Essays},
  booktitle = {Proceedings of the 20th International Workshop on Semantic Evaluation (SemEval-2026)},
  publisher = {Association for Computational Linguistics},
  address = {San Diego, California, USA},
  year = {2026},
  month = jul,
  pages = {140--145},
  doi = {10.18653/v1/2026.semeval-1.21},
  url = {https://aclanthology.org/2026.semeval-1.21/}
}