pymlask 0.3.2

Emotion analyzer for Japanese

pymlask

pymlask is a Python version of ML-Ask (eMotive eLement and Expression Analysis system)

For details about ML-Ask, See http://arakilab.media.eng.hokudai.ac.jp/~ptaszynski/repository/mlask.htm

See also http://qiita.com/yukinoi/items/ef6fb48b5e3694e9659c (in Japanese)

Contributions are welcome!

Installation

Modified dictionary version

pip install pymlask

ML-Ask Original dictionary version (same as Ptaszynski’s Perl version)

pip install git+https://github.com/ikegami-yukino/pymlask@original

Example

from mlask import MLAsk
emotion_analyzer = MLAsk()
emotion_analyzer.analyze('彼のことは嫌いではない！(;´Д`)')
# => {'text': '彼のことは嫌いではない！(;´Д`)',
#     'emotion': defaultdict(<class 'list'>,{'yorokobi': ['嫌い*CVS'], 'suki': ['嫌い*CVS']}),
#     'orientation': 'POSITIVE',
#     'activation': 'NEUTRAL',
#     'emoticon': ['(;´Д`)'],
#     'intension': 2,
#     'intensifier': {'exclamation': ['！'], 'emotikony': ['´Д`', 'Д`', '´Д', '(;´Д`)']},
#     'representative': ('yorokobi', ['嫌い*CVS'])
#     }

LICENSE

The BSD 3-Clause License

Copyright

ML-Ask Python: The BSD 3-Clause License (c) 2017 Yukino Ikegami. All Rights Reserved.

ML-Ask (original): The BSD 3-Clause License (c) 2007-2013, Michal Ptaszynski, Pawel Dybala, Rafal Rzepka, Kenji Arakii. All Rights Reserved.

CHANGES

0.3.2 (2019-07-09)

• Fix bugs about emotion pattern matching (thanks @brunotoshio)

• Fix bug about activation count (thanks @brunotoshio)

0.3.1 (2019-05-22)

• Use MeCab.Tagger().parse() instead of MeCab.Tagger().parseToNode

0.3 (2019-05-17)

• The 712 emotional words from Kanjou kotoba erabi jiten (感情ことば選び辞典) are newly added

• Support Python 3.7

• Unsupport Python 2.6 and 3.3

0.2.5 (2017-09-14)

• Fix bugs about MeCab (thanks @Kensuke-Mitsuzawa)

• Delete install_requires

0.2.4 (2017-03-01)

• Fix many bugs

• Add some emotional words

• Delete invalid words

• Correct typo

0.2.1 (2017-02-23)

• Add 67 emotional words

0.2 (2017-02-22)

• Support Python 2.X

• Add 52 emotional words

• Fix bug

0.1.1 (2017-02-15)

• Delete debug print (thanks @ssirai)

0.1 (2017-02-10)

• First release.