This model and other models from the word2affect line are finetuned to predict emotional load for singular words, not longer utterances. Their accuracy on long-form text is unknown.

This transformer-based model is designed to extrapolate affective norms for Polish words, including metrics such as valence, arousal, dominance, concreteness, age of acquisition, origin, significance, and imageability. It has been finetuned from the Polish RoBerta Model (https://github.com/sdadas/polish-roberta), enhanced with additional layers to predict the affective dimensions. This model was first released as a part of the publication: "Extrapolation of affective norms using transformer-based neural networks and its application to experimental stimuli selection." (Plisiecki, Sobieszek; 2023) [ https://doi.org/10.3758/s13428-023-02212-3 ]

The model was trained on the Polish affective norms dataset by Imbir (2016) [ https://doi.org/10.3389/fpsyg.2016.01081 ], which includes 4900 words rated by participants on various emotional and semantic dimensions. The dataset was split into training, validation, and test sets in an 8:1:1 ratio.

The model achieved the following Pearson correlations with human judgments on the test set:

You can use the model and tokenizer as follows:

First run the bash code below to clone the repository (this will take some time). Because of the custom model class, this model cannot be run with the usual huggingface Model setups.

Proceed as follows:

If you use this model please cite the following paper.