Sen1 Sentiment Analysis Model
This model is trained to perform sentiment analysis on movie reviews. It's based on the BERT model and fine-tuned on the IMDB dataset, which contains 50,000 movie reviews labeled as either positive or negative. This dataset is more suitable for binary sentiment analysis (positive vs negative).
Model Details
Model architecture: BERT Training data: 25000 imdb movie reviews Evaluation data: 25000 imdb movie review Training algorithm: The model was trained using the Trainer class from the transformers library, with a batch size of X, for Y epochs.
Performance: The model achieved high accuracy 93.8% after 6 epochs of training on the evaluation dataset.
How to Use
Here's a simple example of how to use this model for sentiment analysis:
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
tokenizer = AutoTokenizer.from_pretrained("ControX/Sen1")
model = AutoModelForSequenceClassification.from_pretrained("ControX/Sen1")
text = "Write your text for review here"
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
print(probs)
Limitations and Bias Model is limited to binary analysis of text. Potential bias could be that a typical movie reviewing audience might not represent the average person in relation to any type of text.
