Skip to main content

A sentiment analysis package used for traditional Chinese.

Project description

senti_c (sentiment analysis toolkit for traditional Chinese)

簡介

本工具為繁體中文情感分析套件,支援三種類型分析:句子情感分類、屬性術語提取、屬性情感分類;同時提供函數供使用者應用其它資料重新微調模型。

目錄


執行環境

  • python3.7

安裝方式

  1. pip
pip install senti_c 
  1. from source
git clone https://github.com/julielanblue/senti_c
cd senti_c
python3 setup.py install

功能介紹

  1. 句子情感分類:預測
from senti_c import SentenceSentimentClassification

sentence_classifier = SentenceSentimentClassification()

test_data = ["我很喜歡這家店!超級無敵棒!","這個服務生很不親切..."]  
result = sentence_classifier.predict(test_data,run_split=True,aggregate_strategy=False)  # 可依據需求調整參數
  • 結果如下:

Sample

  1. 句子情感分類:重新微調模型
from senti_c import SentenceSentimentModel

sentence_classifier = SentenceSentimentModel()
sentence_classifier.train(data_dir="./data/sentence_data",output_dir="test_fine_tuning_sent")  # 可依據需求調整參數
  1. 屬性情感分析:預測
from senti_c import AspectSentimentAnalysis

aspect_classifier = AspectSentimentAnalysis()

test_data = ["我很喜歡這家店!超級無敵棒!","這個服務生很不親切..."]   
result = aspect_classifier.predict(test_data,output_result="all")  # 可依據需求調整參數
  • 結果如下:

Sample

Sample

Sample

Sample

  1. 屬性情感分析:重新微調模型
from senti_c import AspectSentimentModel

aspect_classifier = AspectSentimentModel()
aspect_classifier.train(data_dir="./data/aspect_data",output_dir="test_fine_tuning_aspect")  # 可依據需求調整參數

範例程式

相關功能demo可參考examples資料夾中的function_demo檔案。

資料

本研究蒐集Google評論上餐廳與飯店領域評論內容、並進行句子情感分類、屬性情感分析標記 (屬性標記與情感標記)。

相關資料格式請見data資料夾。

引用

引用請註記來源:NTU BAEIR lab

致謝

本套件基於 Hugging Face 團隊開源的 transformers

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

senti_c-0.0.4.tar.gz (37.6 kB view hashes)

Uploaded Source

Built Distribution

senti_c-0.0.4-py3-none-any.whl (48.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page