This model is a fine-tuned version of RoBERTa-large [1]. It was trained on 2,100 VR game reviews to measure sentiment on UX dimensions. Specifically, this model measures the sentiment on the UX dimension Engagement.

The model assigns one of 3 possible labels:

0 (neutral): The text describes the UX dimension neutrally or is not discussed
1 (positive): The text describes the UX dimension positively
2 (negative): The text describes the UX dimension negatively

References
[1] Liu, Y.; Ott, M.; Goyal, N.; Du, J.; Joshi, M.; Chen, D.; ... & Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.

Downloads last month
7
Safetensors
Model size
355M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.