Lan-ce-lot/pythorch-text-classification
对豆瓣影评进行文本分类情感分析，利用爬虫豆瓣爬取评论，进行数据清洗，分词，采用BERT、CNN、LSTM等模型进行训练，采用tensorboardX可视化训练过程，自然语言处理项目\A project for text classification, based on torch 1.7.1
Implements multiple transformer and RNN architectures (BERT, ERNIE, BiLSTM, CNN) with comparative performance metrics, achieving 92% test accuracy on binary sentiment classification. Includes a PyQt GUI for real-time inference and TensorBoard integration for training visualization. Handles Douban anti-scraping measures through randomized request timing and User-Agent rotation.
170 stars. No commits in the last 6 months.
Stars
170
Forks
10
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Lan-ce-lot/pythorch-text-classification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
IBM/MAX-Text-Sentiment-Classifier
Detect the sentiment captured in short pieces of text
danielegrattarola/twitter-sentiment-cnn
An implementation in TensorFlow of a convolutional neural network (CNN) to perform sentiment...
jerbarnes/semeval22_structured_sentiment
SemEval-2022 Shared Task 10: Structured Sentiment Analysis
latishab/turnsense
A lightweight end-of-utterance detection model fine-tuned on SmolLM2-135M, optimized for...
pabitralenka/Customer-Feedback-Analysis
Multi Class Text (Feedback) Classification using CNN, GRU Network and pre trained Word2Vec...