These are embeddings for the top 500 keywords of each of the cateogories considered in HappyDB (https://github.com/megagonlabs/HappyDB).
The embeddings and metadata are meant to be visualized using Tensorflow Projector (https://projector.tensorflow.org).
These keywords were extracted from the HappyDB corpus using the spaCy pipeline extension TextRank.
https://github.com/DerwenAI/pytextrank
These files were generated by running Lingmotif 2.0 on the original HappyDB corpus.
Classification results obtained with Lingmotif and HuggingFace-DistilBERT
https://huggingface.co/docs/transformers/model_doc/distilbert
Please use the following reference if you use any of the contents in this repository:
Moreno-Ortiz, A, Pérez-Hernández, C. & García-Gámez, M (2022). "The Language of Happiness in Self-reported Descriptions of Happy Moments: Words, concepts, and entities.". Humanities and Social Sciences Communications. Springer Nature.