Downloads · 30 days
0
pchatz/palobert-base-greek-social-media-sentiment-v2
palobert-base-greek-social-media-sentiment-v2 is a text classification model from pchatz. Use it when you need a label for a piece of text.
A greek RoBERTa based model (PaloBERT: an updated version of palobert-base-greek-uncased-v1) fine-tuned for sentiment analysis.
Downloads · 30 days
0
Access
Public
Updated Apr 6, 2023
Repo size
540 MB
Likes
1
Public
Click a slice to open those files.
.bin270 MB · 99%
From the Hugging Face model README
A greek RoBERTa based model (PaloBERT: an updated version of palobert-base-greek-uncased-v1) fine-tuned for sentiment analysis.
The model is pre-trained on a corpus of 458,293 documents collected from greek social media (Twitter, Instagram, Facebook and YouTube). A RoBERTa tokenizer trained from scratch on the same corpus is also included. The fine-tuning process is done on a dataset of ~60,000 documents, also collected from greek social media.
The corpus as well as the annotated dataset have been provided by Palo LTD.
pip install transformers
pip install torch
In order to use this model, the text needs to be pre-processed as follows:
import re
import unicodedata
def preprocess(text, default_replace=""):
text = text.lower()
text = unicodedata.normalize('NFD',text).translate({ord('\N{COMBINING ACUTE ACCENT}'):None})
text = re.sub(r'[^\w\s]', default_replace, text)
return text
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("pchatz/palobert-base-greek-social-media-v2") #load PaloBERT pre-trained model
language_model = AutoModel.from_pretrained("pchatz/palobert-base-greek-social-media-v2")
Refer to GitHub code for details on ModelClass architecture
model = TheModelClass(*args, **kwargs) #load fine-tuned model as SentimentClassifier_v2
model.load_state_dict(torch.load(PATH))
model.eval()
You can use this sentiment analysis model directly on raw text:
#Example
class_names={0: 'neutral', 1:'positive', 2:'negative'}
text='οι εξετασεις ηταν πολυ καλες'
encoding=tokenizer(text,return_tensors='pt')
input_ids = encoding['input_ids']
attention_mask = encoding['attention_mask']
output = model(input_ids, attention_mask)
_,prediction = torch.max(output, dim=1)
print(f'sentiment : {class_names[prediction.item()]}') #positive
For detailed results refer to Thesis: 'Ανάλυση συναισθήματος κειμένου στα Ελληνικά με χρήση Δικτύων Μετασχηματιστών' (version - p2)
Pavlina Chatziantoniou, Georgios Alexandridis and Athanasios Voulodimos
http://artemis.cslab.ece.ntua.gr:8080/jspui/handle/123456789/18623
@Article{info12080331,
AUTHOR = {Alexandridis, Georgios and Varlamis, Iraklis and Korovesis, Konstantinos and Caridakis, George and Tsantilas, Panagiotis},
TITLE = {A Survey on Sentiment Analysis and Opinion Mining in Greek Social Media},
JOURNAL = {Information},
VOLUME = {12},
YEAR = {2021},
NUMBER = {8},
ARTICLE-NUMBER = {331},
URL = {https://www.mdpi.com/2078-2489/12/8/331},
ISSN = {2078-2489},
DOI = {10.3390/info12080331}
}