fine-tuned-sentiment-model-imdb

Model Card for Fine-Tuned Sentiment Analysis Model on IMDB Dataset

<!-- Provide a quick summary of what the model is/does. -->

This model is a fine-tuned version of a pre-trained transformer model, specifically designed for sentiment analysis on the IMDB dataset. It classifies movie reviews as either "positive" or "negative" based on the sentiment expressed.

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

This is the model card of a 🤗 transformers model that has been fine-tuned on the IMDB dataset, consisting of 50,000 movie reviews. The model is designed to perform binary sentiment classification, identifying whether a given review expresses a positive or negative sentiment.

• Developed by: Melek Sahlia
• Funded by [optional]: Self-funded / [Optional sponsor name]
• Shared by [optional]: Melek
• Model type: SequenceClassification
• Language(s) (NLP): English
• License: [More Information Needed]
• Finetuned from model [optional]: DistilBERT-base-uncased

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: [Link to the Hugging Face repository]
• Paper [optional]: [Optional if there's a related paper]
• Demo [optional]: [Link to a demo, if available]

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

This model can be directly used for sentiment analysis tasks, particularly for classifying movie reviews or similar texts as "positive" or "negative."

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import pipeline

pipe = pipeline("text-classification", model="MALEKSAHLIA/fine-tuned-sentiment-model-imdb")

Example usage

sentence = "This movie was fantastic!" result = nlp(sentence)

def evaluate_sentence(sentence, result): sentiment = "Positive" if result[0]['label'] == 'LABEL_1' else "Negative" # Assuming '1' indicates good sentiment print(f"'{sentence}' is classified as {sentiment}")

evaluate_sentence(sentence, result)

Training Details

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

The model was fine-tuned on the IMDB dataset, which contains 50,000 movie reviews labeled as either positive or negative.

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Preprocessing [optional] Standard preprocessing steps included tokenization using the "distilbert-base-uncased" tokenizer.

Training Hyperparameters

training_args = TrainingArguments( output_dir="./results", evaluation_strategy="epoch", learning_rate=2e-5, per_device_train_batch_size=16, per_device_eval_batch_size=16, num_train_epochs=3, weight_decay=0.01, )

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Testing Data, Factors & Metrics Testing Data

<!-- This should link to a Dataset Card if possible. -->

The model was evaluated on the IMDB test dataset, which consists of 2,000 movie reviews.

Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

Evaluation focused on the binary classification of sentiment in movie reviews.

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

The following metrics were used to evaluate the model (Finetuned model):

Accuracy: 94% Precision: 93% Recall: 94% F1-Score: 94% Evaluation Loss: 0.29 Results

<!-- Insert result metrics here -->

The following results were observed for the non finetuned model: Accuracy: 50% Precision: 78% Recall: 2% F1-Score: 2% Evaluation Loss: 0.67 These results show that the fine-tuned model significantly outperforms the pre-trained model in terms of accuracy, precision, recall, and F1-score.

Visualization Here is a comparison of the fine-tuned model versus the pre-trained model on various metrics:

import gradio as gr from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer

Load the model from the hub

model = AutoModelForSequenceClassification.from_pretrained("MALEKSAHLIA/fine-tuned-sentiment-model-imdb") tokenizer = AutoTokenizer.from_pretrained("MALEKSAHLIA/fine-tuned-sentiment-model-imdb")

Create a pipeline for sentiment analysis

nlp = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)

def predict_sentiment(sentence): result = nlp(sentence) sentiment = "Positive" if result[0]['label'] == 'LABEL_1' else "Negative" # Adjust the label to match your model's output return sentiment

iface = gr.Interface( fn=predict_sentiment, inputs="text", outputs="text", title="Sentiment Analysis", description="Enter a sentence to get the sentiment (Positive or Negative)." )

iface.launch()

This model card is now more complete and ready to be shared with others on Hugging Face Hub.