Update README.md

README.md

@@ -9,4 +9,15 @@ widget:
 ---
 This is a BERTweet-base model that has been further pre-trained with preferential masking of emotion words for 100k steps on about 6.3M Vent posts.
 
-This model is meant to be fine-tuned on labeled data or used as feature extractor for downstream tasks.
+This model is meant to be fine-tuned on labeled data or used as feature extractor for downstream tasks.
+
+## Citation
+Please cite the following paper if you find the model useful for your work:
+```bibtex
+@article{aroyehun2023leia,
+  title={LEIA: Linguistic Embeddings for the Identification of Affect},
+  author={Aroyehun, Segun Taofeek and Malik, Lukas and Metzler, Hannah and Haimerl, Nikolas and Di Natale, Anna and Garcia, David},
+  journal={arXiv preprint arXiv:2304.10973},
+  year={2023}
+}
+```