Dictionary based Sentiment Analysis for Japanese
Project description
oseti
Dictionary based Sentiment Analysis for Japanese
INSTALLATION
$ pip install oseti
USAGE
import oseti
analyzer = oseti.Analyzer()
analyzer.analyze('天国で待ってる。')
# => [1.0]
analyzer.analyze('遅刻したけど楽しかったし嬉しかった。すごく充実した!')
# => [0.3333333333333333, 1.0]
analyzer.count_polarity('遅刻したけど楽しかったし嬉しかった。すごく充実した!')
# => [{'positive': 2, 'negative': 1}, {'positive': 1, 'negative': 0}])
analyzer.count_polarity('そこにはいつもと変わらない日常があった。')
# => [{'positive': 0, 'negative': 0}]
analyzer.analyze_detail('お金も希望もない!')
# => [{'positive': [], 'negative': ['お金-NEGATION', '希望-NEGATION'], 'score': -1.0}])
analyzer.analyze_detail('お金がないわけではない')
# => [{'positive': ['お金'], 'negative': [], 'score': 1.0}]
# Applying user's dictionary
analyzer = oseti.Analyzer(word_dict={'カワイイ': 'p', 'ブサイク': 'n'},
wago_dict={'イカ する': 'ポジ', 'まがまがしい': 'ネガ'})
analyzer.analyze_detail("カワイイ")
# => [{'positive': ['カワイイ'], 'negative': [], 'score': 1.0}]
analyzer.analyze_detail("ブサイクだ")
# => [{'positive': [], 'negative': ['ブサイク'], 'score': -1.0}]
analyzer.analyze_detail("まがまがしい")
# => [{'positive': [], 'negative': ['まがまがしい'], 'score': -1.0}]
analyzer.analyze_detail("イカすよ")
# => [{'positive': ['イカ する'], 'negative': [], 'score': 1.0}]
ACKNOWLEDGEMENT
This module uses 日本語評価極性辞書(用言編)ver.1.0 and 日本語評価極性辞書(名詞編)ver.1.0
小林のぞみ,乾健太郎,松本裕治,立石健二,福島俊一. 意見抽出のための評価表現の収集. 自然言語処理,Vol.12, No.3, pp.203-222, 2005. / Nozomi Kobayashi, Kentaro Inui, Yuji Matsumoto, Kenji Tateishi. Collecting Evaluative Expressions for Opinion Extraction, Journal of Natural Language Processing 12(3), 203-222, 2005.
東山昌彦, 乾健太郎, 松本裕治, 述語の選択選好性に着目した名詞評価極性の獲得, 言語処理学会第14回年次大会論文集, pp.584-587, 2008. / Masahiko Higashiyama, Kentaro Inui, Yuji Matsumoto. Learning Sentiment of Nouns from Selectional Preferences of Verbs and Adjectives, Proceedings of the 14th Annual Meeting of the Association for Natural Language Processing, pp.584-587, 2008.
CHANGES
0.4.1 (2022-08-21)
Enable user’s dictionary
Solve install issue
PEP8
0.3.1 (2022-08-17)
Improve dictionaries
Use Bunkai module instead of sengiri
0.2 (2019-10-07)
Add new methods count_polarity (thanks @yskn67) and analyze_detail
Drop support Python 3.3
Use sengiri package
Support parallel negation (e.g. お金も希望もない is negative)
Support “arujanai” expression (e.g. お金があるじゃない is positive)
0.1.2 (2019-02-18)
Fix missing CHANGES.rst
0.1.1 (2019-02-13)
Set install_requires
0.1 (2019-02-12)
First release
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.