herbert-base-cased-sentiment Open-source Model - Free Implementation of Positive, Negative, and Neutral Sentiment Classification for Polish Texts

Herbert Base Cased Sentiment

Developed by Voicelab

HerBERT-based Polish sentiment analysis model capable of classifying Polish texts into positive, neutral, or negative sentiments

Text Classification

Transformers

Other#Polish sentiment analysis #User comment classification #HerBERT architecture

Downloads 703

Release Time : 11/2/2022

Model Overview

This model is a Polish sentiment classifier based on the HerBERT architecture, specifically designed to analyze sentiment tendencies in Polish texts, supporting negative, neutral, and positive sentiment classifications.

Model Features

Polish language specialized

Sentiment analysis model specifically optimized for Polish

Three-class sentiment analysis

Accurately identifies negative, neutral, and positive sentiments

Based on HerBERT architecture

Uses the Polish pre-trained model HerBERT as its foundation, with excellent language understanding capabilities

Model Capabilities

Polish text classification

Sentiment tendency analysis

Natural language processing

Use Cases

Customer service

Customer feedback analysis

Analyzes sentiment tendencies in customer reviews and feedback

Helps identify dissatisfied customers for priority handling

Social media monitoring

Social media sentiment analysis

Monitors brand sentiment tendencies on social media

Provides real-time understanding of public attitude changes toward the brand

🚀 Sentiment Classification in Polish

This project focuses on sentiment classification in Polish, providing a practical solution for analyzing the sentiment of Polish text.

🚀 Quick Start

The following is a simple example of using the model for sentiment classification:

import numpy as np
from transformers import AutoTokenizer, AutoModelForSequenceClassification

id2label = {0: "negative", 1: "neutral", 2: "positive"}
tokenizer = AutoTokenizer.from_pretrained("Voicelab/herbert-base-cased-sentiment")
model = AutoModelForSequenceClassification.from_pretrained("Voicelab/herbert-base-cased-sentiment")

input = ["Ale fajnie, spadł dzisiaj śnieg! Ulepimy dziś bałwana?"]

encoding = tokenizer(
          input,
          add_special_tokens=True,
          return_token_type_ids=True,
          truncation=True,
          padding='max_length',
          return_attention_mask=True,
          return_tensors='pt',
        )
output = model(**encoding).logits.to("cpu").detach().numpy()
prediction = id2label[np.argmax(output)]
print(input, "--->", prediction)

The predicted output is:

['Ale fajnie, spadł dzisiaj śnieg! Ulepimy dziś bałwana?'] ---> positive

💻 Usage Examples

Basic Usage

import numpy as np
from transformers import AutoTokenizer, AutoModelForSequenceClassification

id2label = {0: "negative", 1: "neutral", 2: "positive"}
tokenizer = AutoTokenizer.from_pretrained("Voicelab/herbert-base-cased-sentiment")
model = AutoModelForSequenceClassification.from_pretrained("Voicelab/herbert-base-cased-sentiment")

input = ["Ale fajnie, spadł dzisiaj śnieg! Ulepimy dziś bałwana?"]

encoding = tokenizer(
          input,
          add_special_tokens=True,
          return_token_type_ids=True,
          truncation=True,
          padding='max_length',
          return_attention_mask=True,
          return_tensors='pt',
        )
output = model(**encoding).logits.to("cpu").detach().numpy()
prediction = id2label[np.argmax(output)]
print(input, "--->", prediction)

📚 Documentation

Overview

Property	Details
Model Type	allegro/herbert-base-cased
Language	pl
Training Data	Reviews + own data
Blog Post	Sentiment analysis - COVID-19 – the source of the heated discussion

📄 License

This project is licensed under the cc-by-4.0 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