roberta-base-imdb Open-source Sentiment Analysis Model - Freely and Quickly Determine the Sentiment Tendency of Texts

Roberta Base Imdb

Developed by aychang

A base model based on the roBERTa architecture, trained on the IMDB dataset for sentiment analysis tasks.

Text Classification EnglishOpen Source License:MIT #IMDB Sentiment Analysis #High Accuracy (94.6%)#Movie Review Classification

Downloads 341

Release Time : 3/2/2022

Model Overview

This model is a sentiment analysis model based on the roBERTa architecture, specifically trained on the IMDB movie review dataset, and can accurately determine the sentiment tendency (positive/negative) of the text.

Model Features

High Accuracy

Achieved an accuracy of 94.67% on the IMDB test set

Balanced Performance

The F1 score shows that the model performs evenly on positive and negative samples (0.947 for positive and 0.946 for negative)

Efficient Inference

The evaluation speed reaches 102 samples per second

Model Capabilities

Text Sentiment Analysis

Movie Review Classification

English Text Processing

Use Cases

Film and Television Review Analysis

Movie Review Sentiment Classification

Automatically determine whether the user's evaluation of the movie is positive or negative

Accuracy 94.67%

Product Feedback Analysis

User Review Sentiment Analysis

Analyze the sentiment tendency of users' evaluations of products

🚀 IMDB Sentiment Task: roberta-base

A simple base roBERTa model trained on the "imdb" dataset for sentiment analysis.

🚀 Quick Start

This README provides details about a simple base roBERTa model trained on the "imdb" dataset. It includes information on model usage, limitations, training data, training procedures, and evaluation results.

✨ Features

Trained on the "imdb" dataset for sentiment analysis.
Can be used with popular libraries like Transformers and AdaptNLP.

💻 Usage Examples

Basic Usage

Transformers

# Load model and tokenizer
from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Use pipeline
from transformers import pipeline

model_name = "aychang/roberta-base-imdb"

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

results = nlp(["I didn't really like it because it was so terrible.", "I love how easy it is to watch and get good results."])

AdaptNLP

from adaptnlp import EasySequenceClassifier

model_name = "aychang/roberta-base-imdb"
texts = ["I didn't really like it because it was so terrible.", "I love how easy it is to watch and get good results."]

classifer = EasySequenceClassifier
results = classifier.tag_text(text=texts, model_name_or_path=model_name, mini_batch_size=2)

📚 Documentation

Intended uses & limitations

Limitations and bias

This is minimal language model trained on a benchmark dataset.

📦 Installation

No specific installation steps are provided in the original document.

🔧 Technical Details

Training data

IMDB https://huggingface.co/datasets/imdb

Training procedure

Hardware

One V100

Hyperparameters and Training Args

from transformers import TrainingArguments

training_args = TrainingArguments(
    output_dir='./models',
    overwrite_output_dir=False,
    num_train_epochs=2,
    per_device_train_batch_size=8,
    per_device_eval_batch_size=8,
    warmup_steps=500,
    weight_decay=0.01,
    evaluation_strategy="steps",
    logging_dir='./logs',
    fp16=False,
    eval_steps=800,
    save_steps=300000
)

📄 License

This project is licensed under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご