start

README.md

@@ -1,3 +1,52 @@
 ---
-license: mit
+language: 
+  - en
+
+tags:
+  - emotion-analysis
+
 ---
+# Emotion Analysis in English
+## bertweet-base-emotion-analysis
+
+Repository: [https://github.com/finiteautomata/pysentimiento/](https://github.com/finiteautomata/pysentimiento/)
+
+
+Model trained with EmoEvent corpus for Emotion detection in English. Base model is [BerTweet](https://huggingface.co/vinai/bertweet-base).
+
+
+## License
+
+`pysentimiento` is an open-source library for non-commercial use and scientific research purposes only. Please be aware that models are trained with third-party datasets and are subject to their respective licenses. 
+
+1. [TASS Dataset license](http://tass.sepln.org/tass_data/download.php)
+2. [SEMEval 2017 Dataset license]()
+
+## Citation
+
+If you use `pysentimiento` in your work, please cite [this paper](https://arxiv.org/abs/2106.09462)
+
+```
+@misc{perez2021pysentimiento,
+      title={pysentimiento: A Python Toolkit for Sentiment Analysis and SocialNLP tasks},
+      author={Juan Manuel Pérez and Juan Carlos Giudici and Franco Luque},
+      year={2021},
+      eprint={2106.09462},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+
+and also the dataset related paper
+
+```
+@inproceedings{del2020emoevent,
+  title={EmoEvent: A multilingual emotion corpus based on different events},
+  author={del Arco, Flor Miriam Plaza and Strapparava, Carlo and Lopez, L Alfonso Urena and Mart{\'\i}n-Valdivia, M Teresa},
+  booktitle={Proceedings of the 12th Language Resources and Evaluation Conference},
+  pages={1492--1498},
+  year={2020}
+}
+```
+
+Enjoy! 🤗

added_tokens.json

@@ -0,0 +1 @@
+{"<mask>": 64000}

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "vinai/bertweet-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "others",
+    "1": "joy",
+    "2": "sadness",
+    "3": "anger",
+    "4": "surprise",
+    "5": "disgust",
+    "6": "fear"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": 3,
+    "disgust": 5,
+    "fear": 6,
+    "joy": 1,
+    "others": 0,
+    "sadness": 2,
+    "surprise": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertweetTokenizer",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bd6088ef2036d65cb99f80b54130e9d3a17f3a0b3c7f95c8f8c421fcdf9a98
+size 539646676

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb2a82fac7350eaa0baf9aa30fb9ebc9884cb9d6c48746ae6034e89771311dc
+size 539706835

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"normalization": false, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 128, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "vinai/bertweet-base"}